# ContextForge MCP Gateway MCP server

Agent View of the PolicyLayer registry record for ContextForge MCP Gateway: identity, probed posture, risk grade, and all 221 tools classified. HTML page: https://policylayer.com/tools/jrmatherly-mcp-context-forge

## Facts

- Server id: `jrmatherly/mcp-context-forge`
- Homepage: https://github.com/jrmatherly/mcp-context-forge
- Registry record: grade F, identity unverified
- Lifecycle: active
- Rate-limited: no
- Tools: 221
- Tool categories present: Destructive, Execute, Read, Write
- Tags: jrmatherly mcp context forge, admin, automation
- Record last modified: 2026-08-15T12:20:15.780Z

## Tools (221)

| Tool | Category | Risk | Record |
| --- | --- | --- | --- |
| `clear_cache` | Destructive | Critical | https://policylayer.com/tools/jrmatherly-mcp-context-forge/clear-cache.md |
| `delete_slide` | Destructive | Critical | https://policylayer.com/tools/jrmatherly-mcp-context-forge/delete-slide.md |
| `agent.benchmark_performance` | Execute | High | https://policylayer.com/tools/jrmatherly-mcp-context-forge/agent.benchmark-performance.md |
| `bitbucket_trigger_pipeline` | Execute | High | https://policylayer.com/tools/jrmatherly-mcp-context-forge/bitbucket-trigger-pipeline.md |
| `build_schedule` | Execute | High | https://policylayer.com/tools/jrmatherly-mcp-context-forge/build-schedule.md |
| `calculate_stats` | Execute | High | https://policylayer.com/tools/jrmatherly-mcp-context-forge/calculate-stats.md |
| `compile_document` | Execute | High | https://policylayer.com/tools/jrmatherly-mcp-context-forge/compile-document.md |
| `critical_path_analysis` | Execute | High | https://policylayer.com/tools/jrmatherly-mcp-context-forge/critical-path-analysis.md |
| `execute_code` | Execute | High | https://policylayer.com/tools/jrmatherly-mcp-context-forge/execute-code.md |
| `generate_qr_code` | Execute | High | https://policylayer.com/tools/jrmatherly-mcp-context-forge/generate-qr-code.md |
| `judge.rank_responses` | Execute | High | https://policylayer.com/tools/jrmatherly-mcp-context-forge/judge.rank-responses.md |
| `performance.evaluate_throughput_scaling` | Execute | High | https://policylayer.com/tools/jrmatherly-mcp-context-forge/performance.evaluate-throughput-scaling.md |
| `query_data` | Execute | High | https://policylayer.com/tools/jrmatherly-mcp-context-forge/query-data.md |
| `render_graph` | Execute | High | https://policylayer.com/tools/jrmatherly-mcp-context-forge/render-graph.md |
| `robustness.assess_distribution_shift` | Execute | High | https://policylayer.com/tools/jrmatherly-mcp-context-forge/robustness.assess-distribution-shift.md |
| `robustness.measure_input_sensitivity` | Execute | High | https://policylayer.com/tools/jrmatherly-mcp-context-forge/robustness.measure-input-sensitivity.md |
| `robustness.test_adversarial_inputs` | Execute | High | https://policylayer.com/tools/jrmatherly-mcp-context-forge/robustness.test-adversarial-inputs.md |
| `statistical_test` | Execute | High | https://policylayer.com/tools/jrmatherly-mcp-context-forge/statistical-test.md |
| `transform_data` | Execute | High | https://policylayer.com/tools/jrmatherly-mcp-context-forge/transform-data.md |
| `workflow.run_evaluation` | Execute | High | https://policylayer.com/tools/jrmatherly-mcp-context-forge/workflow.run-evaluation.md |
| `agent.analyze_reasoning` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/agent.analyze-reasoning.md |
| `agent.evaluate_tool_use` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/agent.evaluate-tool-use.md |
| `agent.measure_task_completion` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/agent.measure-task-completion.md |
| `analyze_code` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/analyze-code.md |
| `analyze_csv` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/analyze-csv.md |
| `analyze_dataset` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/analyze-dataset.md |
| `analyze_document` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/analyze-document.md |
| `analyze_feed` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/analyze-feed.md |
| `analyze_graph` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/analyze-graph.md |
| `analyze_text` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/analyze-text.md |
| `analyze_workbook` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/analyze-workbook.md |
| `baseline_vs_actual` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/baseline-vs-actual.md |
| `batch_convert` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/batch-convert.md |
| `bias.assess_cultural_sensitivity` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/bias.assess-cultural-sensitivity.md |
| `bias.detect_demographic_bias` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/bias.detect-demographic-bias.md |
| `bias.detect_linguistic_bias` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/bias.detect-linguistic-bias.md |
| `bias.evaluate_outcome_equity` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/bias.evaluate-outcome-equity.md |
| `bias.measure_intersectional_fairness` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/bias.measure-intersectional-fairness.md |
| `bias.measure_representation_fairness` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/bias.measure-representation-fairness.md |
| `bitbucket_get_pipeline` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/bitbucket-get-pipeline.md |
| `bitbucket_get_pr` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/bitbucket-get-pr.md |
| `bitbucket_get_repo` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/bitbucket-get-repo.md |
| `bitbucket_list_pipelines` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/bitbucket-list-pipelines.md |
| `bitbucket_list_prs` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/bitbucket-list-prs.md |
| `bitbucket_list_repos` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/bitbucket-list-repos.md |
| `bitbucket_search_code` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/bitbucket-search-code.md |
| `calibration.test_judge_agreement` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/calibration.test-judge-agreement.md |
| `change_request_tracker` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/change-request-tracker.md |
| `chat_with_csv` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/chat-with-csv.md |
| `chunk_markdown` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/chunk-markdown.md |
| `chunk_text` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/chunk-text.md |
| `cluster_by_topic` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/cluster-by-topic.md |
| `convert_file` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/convert-file.md |
| `convert_url` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/convert-url.md |
| `decode_qr_code` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/decode-qr-code.md |
| `divide_numbers` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/divide-numbers.md |
| `document_search` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/document-search.md |
| `document_template_library` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/document-template-library.md |
| `earned_value_calculator` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/earned-value-calculator.md |
| `echo` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/echo.md |
| `extract_classes` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/extract-classes.md |
| `extract_functions` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/extract-functions.md |
| `extract_text` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/extract-text.md |
| `fetch_rss` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/fetch-rss.md |
| `filter_by_date` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/filter-by-date.md |
| `find_by_author` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/find-by-author.md |
| `find_duplicates` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/find-duplicates.md |
| `find_related_entries` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/find-related-entries.md |
| `fixed_size_chunk` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/fixed-size-chunk.md |
| `get_capabilities` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/get-capabilities.md |
| `get_csv_info` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/get-csv-info.md |
| `get_document_info` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/get-document-info.md |
| `get_feed_metadata` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/get-feed-metadata.md |
| `get_feed_statistics` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/get-feed-statistics.md |
| `get_latest_entries` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/get-latest-entries.md |
| `get_model_info` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/get-model-info.md |
| `get_presentation_info` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/get-presentation-info.md |
| `get_sandbox_info` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/get-sandbox-info.md |
| `get_server_info` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/get-server-info.md |
| `get_strategies` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/get-strategies.md |
| `get_supported_charts` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/get-supported-charts.md |
| `get_templates` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/get-templates.md |
| `glossary_lookup` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/glossary-lookup.md |
| `hybrid_search` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/hybrid-search.md |
| `inspect_feed_schema` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/inspect-feed-schema.md |
| `judge.evaluate_response` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/judge.evaluate-response.md |
| `judge.evaluate_with_reference` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/judge.evaluate-with-reference.md |
| `judge.pairwise_comparison` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/judge.pairwise-comparison.md |
| `lessons_learned_catalog` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/lessons-learned-catalog.md |
| `list_authors` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/list-authors.md |
| `list_categories` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/list-categories.md |
| `list_generated_datasets` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/list-generated-datasets.md |
| `list_layouts` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/list-layouts.md |
| `list_presets` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/list-presets.md |
| `list_supported_formats` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/list-supported-formats.md |
| `load_dataset` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/load-dataset.md |
| `meeting_minutes_summarizer` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/meeting-minutes-summarizer.md |
| `multilingual.assess_cultural_adaptation` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/multilingual.assess-cultural-adaptation.md |
| `multilingual.detect_language_mixing` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/multilingual.detect-language-mixing.md |
| `multilingual.evaluate_translation_quality` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/multilingual.evaluate-translation-quality.md |
| `multilingual.measure_cross_lingual_consistency` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/multilingual.measure-cross-lingual-consistency.md |
| `multiply_numbers` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/multiply-numbers.md |
| `open_presentation` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/open-presentation.md |
| `performance.assess_computational_efficiency` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/performance.assess-computational-efficiency.md |
| `performance.measure_response_latency` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/performance.measure-response-latency.md |
| `performance.monitor_memory_usage` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/performance.monitor-memory-usage.md |
| `privacy.assess_consent_clarity` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/privacy.assess-consent-clarity.md |
| `privacy.assess_data_minimization` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/privacy.assess-data-minimization.md |
| `privacy.assess_privacy_by_design` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/privacy.assess-privacy-by-design.md |
| `privacy.detect_data_leakage` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/privacy.detect-data-leakage.md |
| `privacy.detect_pii_exposure` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/privacy.detect-pii-exposure.md |
| `privacy.evaluate_consent_compliance` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/privacy.evaluate-consent-compliance.md |
| `privacy.evaluate_data_retention_compliance` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/privacy.evaluate-data-retention-compliance.md |
| `privacy.measure_anonymization_effectiveness` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/privacy.measure-anonymization-effectiveness.md |
| `project_health_dashboard` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/project-health-dashboard.md |
| `prompt.assess_relevance` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/prompt.assess-relevance.md |
| `prompt.evaluate_clarity` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/prompt.evaluate-clarity.md |
| `prompt.measure_completeness` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/prompt.measure-completeness.md |
| `prompt.test_consistency` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/prompt.test-consistency.md |
| `quality.assess_toxicity` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/quality.assess-toxicity.md |
| `quality.evaluate_factuality` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/quality.evaluate-factuality.md |
| `quality.measure_coherence` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/quality.measure-coherence.md |
| `rag.assess_answer_groundedness` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/rag.assess-answer-groundedness.md |
| `rag.assess_citation_accuracy` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/rag.assess-citation-accuracy.md |
| `rag.benchmark_retrieval_systems` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/rag.benchmark-retrieval-systems.md |
| `rag.detect_hallucination_vs_context` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/rag.detect-hallucination-vs-context.md |
| `rag.evaluate_retrieval_coverage` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/rag.evaluate-retrieval-coverage.md |
| `rag.evaluate_retrieval_relevance` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/rag.evaluate-retrieval-relevance.md |
| `rag.measure_chunk_relevance` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/rag.measure-chunk-relevance.md |
| `rag.measure_context_utilization` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/rag.measure-context-utilization.md |
| `read_data` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/read-data.md |
| `resource_allocator` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/resource-allocator.md |
| `retrieve_dataset` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/retrieve-dataset.md |
| `robustness.evaluate_prompt_injection_resistance` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/robustness.evaluate-prompt-injection-resistance.md |
| `robustness.measure_consistency_under_perturbation` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/robustness.measure-consistency-under-perturbation.md |
| `safety.assess_instruction_following` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/safety.assess-instruction-following.md |
| `safety.detect_harmful_content` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/safety.detect-harmful-content.md |
| `safety.evaluate_refusal_appropriateness` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/safety.evaluate-refusal-appropriateness.md |
| `safety.measure_value_alignment` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/safety.measure-value-alignment.md |
| `sample_data_catalog` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/sample-data-catalog.md |
| `schedule_optimizer` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/schedule-optimizer.md |
| `scope_guardrails` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/scope-guardrails.md |
| `search_all` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/search-all.md |
| `search_descriptions` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/search-descriptions.md |
| `search_multi_field_semantic` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/search-multi-field-semantic.md |
| `search_subtitles_semantic` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/search-subtitles-semantic.md |
| `search_summaries_semantic` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/search-summaries-semantic.md |
| `search_titles` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/search-titles.md |
| `semantic_chunk` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/semantic-chunk.md |
| `sentence_chunk` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/sentence-chunk.md |
| `server.get_available_judges` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/server.get-available-judges.md |
| `server.get_cache_stats` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/server.get-cache-stats.md |
| `server.get_evaluation_results` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/server.get-evaluation-results.md |
| `server.get_evaluation_suites` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/server.get-evaluation-suites.md |
| `similarity_search` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/similarity-search.md |
| `split_code` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/split-code.md |
| `status_report_generator` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/status-report-generator.md |
| `summarize_dataset` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/summarize-dataset.md |
| `time_series_analysis` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/time-series-analysis.md |
| `validate_code` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/validate-code.md |
| `validate_email` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/validate-email.md |
| `validate_graph` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/validate-graph.md |
| `validate_mermaid` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/validate-mermaid.md |
| `validate_qr_data` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/validate-qr-data.md |
| `workflow.compare_evaluations` | Read | Low | https://policylayer.com/tools/jrmatherly-mcp-context-forge/workflow.compare-evaluations.md |
| `action_item_tracker` | Write | Medium | https://policylayer.com/tools/jrmatherly-mcp-context-forge/action-item-tracker.md |
| `add_content` | Write | Medium | https://policylayer.com/tools/jrmatherly-mcp-context-forge/add-content.md |
| `add_edge` | Write | Medium | https://policylayer.com/tools/jrmatherly-mcp-context-forge/add-edge.md |
| `add_figure` | Write | Medium | https://policylayer.com/tools/jrmatherly-mcp-context-forge/add-figure.md |
| `add_formula` | Write | Medium | https://policylayer.com/tools/jrmatherly-mcp-context-forge/add-formula.md |
| `add_heading` | Write | Medium | https://policylayer.com/tools/jrmatherly-mcp-context-forge/add-heading.md |
| `add_image` | Write | Medium | https://policylayer.com/tools/jrmatherly-mcp-context-forge/add-image.md |
| `add_node` | Write | Medium | https://policylayer.com/tools/jrmatherly-mcp-context-forge/add-node.md |
| `add_numbers` | Write | Medium | https://policylayer.com/tools/jrmatherly-mcp-context-forge/add-numbers.md |
| `add_section` | Write | Medium | https://policylayer.com/tools/jrmatherly-mcp-context-forge/add-section.md |
| `add_shape` | Write | Medium | https://policylayer.com/tools/jrmatherly-mcp-context-forge/add-shape.md |
| `add_slide` | Write | Medium | https://policylayer.com/tools/jrmatherly-mcp-context-forge/add-slide.md |
| `add_table` | Write | Medium | https://policylayer.com/tools/jrmatherly-mcp-context-forge/add-table.md |
| `add_text` | Write | Medium | https://policylayer.com/tools/jrmatherly-mcp-context-forge/add-text.md |
| `add_text_box` | Write | Medium | https://policylayer.com/tools/jrmatherly-mcp-context-forge/add-text-box.md |
| `bitbucket_create_pr` | Write | Medium | https://policylayer.com/tools/jrmatherly-mcp-context-forge/bitbucket-create-pr.md |
| `bitbucket_merge_pr` | Write | Medium | https://policylayer.com/tools/jrmatherly-mcp-context-forge/bitbucket-merge-pr.md |
| `bitbucket_pr_comments` | Write | Medium | https://policylayer.com/tools/jrmatherly-mcp-context-forge/bitbucket-pr-comments.md |
| `calibration.optimize_rubrics` | Write | Medium | https://policylayer.com/tools/jrmatherly-mcp-context-forge/calibration.optimize-rubrics.md |
| `communications_planner` | Write | Medium | https://policylayer.com/tools/jrmatherly-mcp-context-forge/communications-planner.md |
| `configure_model` | Write | Medium | https://policylayer.com/tools/jrmatherly-mcp-context-forge/configure-model.md |
| `convert_batch` | Write | Medium | https://policylayer.com/tools/jrmatherly-mcp-context-forge/convert-batch.md |
| `convert_content` | Write | Medium | https://policylayer.com/tools/jrmatherly-mcp-context-forge/convert-content.md |
| `convert_document` | Write | Medium | https://policylayer.com/tools/jrmatherly-mcp-context-forge/convert-document.md |
| `create_bar_chart` | Write | Medium | https://policylayer.com/tools/jrmatherly-mcp-context-forge/create-bar-chart.md |
| `create_chart` | Write | Medium | https://policylayer.com/tools/jrmatherly-mcp-context-forge/create-chart.md |
| `create_diagram` | Write | Medium | https://policylayer.com/tools/jrmatherly-mcp-context-forge/create-diagram.md |
| `create_document` | Write | Medium | https://policylayer.com/tools/jrmatherly-mcp-context-forge/create-document.md |
| `create_flowchart` | Write | Medium | https://policylayer.com/tools/jrmatherly-mcp-context-forge/create-flowchart.md |
| `create_from_template` | Write | Medium | https://policylayer.com/tools/jrmatherly-mcp-context-forge/create-from-template.md |
| `create_gantt_chart` | Write | Medium | https://policylayer.com/tools/jrmatherly-mcp-context-forge/create-gantt-chart.md |
| `create_graph` | Write | Medium | https://policylayer.com/tools/jrmatherly-mcp-context-forge/create-graph.md |
| `create_line_chart` | Write | Medium | https://policylayer.com/tools/jrmatherly-mcp-context-forge/create-line-chart.md |
| `create_presentation` | Write | Medium | https://policylayer.com/tools/jrmatherly-mcp-context-forge/create-presentation.md |
| `create_scatter_plot` | Write | Medium | https://policylayer.com/tools/jrmatherly-mcp-context-forge/create-scatter-plot.md |
| `create_sequence_diagram` | Write | Medium | https://policylayer.com/tools/jrmatherly-mcp-context-forge/create-sequence-diagram.md |
| `create_user` | Write | Medium | https://policylayer.com/tools/jrmatherly-mcp-context-forge/create-user.md |
| `create_visualization` | Write | Medium | https://policylayer.com/tools/jrmatherly-mcp-context-forge/create-visualization.md |
| `create_workbook` | Write | Medium | https://policylayer.com/tools/jrmatherly-mcp-context-forge/create-workbook.md |
| `format_cells` | Write | Medium | https://policylayer.com/tools/jrmatherly-mcp-context-forge/format-cells.md |
| `format_text` | Write | Medium | https://policylayer.com/tools/jrmatherly-mcp-context-forge/format-text.md |
| `generate_batch_qr_codes` | Write | Medium | https://policylayer.com/tools/jrmatherly-mcp-context-forge/generate-batch-qr-codes.md |
| `generate_dataset` | Write | Medium | https://policylayer.com/tools/jrmatherly-mcp-context-forge/generate-dataset.md |
| `generate_work_breakdown` | Write | Medium | https://policylayer.com/tools/jrmatherly-mcp-context-forge/generate-work-breakdown.md |
| `merge_documents` | Write | Medium | https://policylayer.com/tools/jrmatherly-mcp-context-forge/merge-documents.md |
| `produce_gantt_diagram` | Write | Medium | https://policylayer.com/tools/jrmatherly-mcp-context-forge/produce-gantt-diagram.md |
| `project_brief_generator` | Write | Medium | https://policylayer.com/tools/jrmatherly-mcp-context-forge/project-brief-generator.md |
| `risk_register_manager` | Write | Medium | https://policylayer.com/tools/jrmatherly-mcp-context-forge/risk-register-manager.md |
| `save_presentation` | Write | Medium | https://policylayer.com/tools/jrmatherly-mcp-context-forge/save-presentation.md |
| `set_attributes` | Write | Medium | https://policylayer.com/tools/jrmatherly-mcp-context-forge/set-attributes.md |
| `set_slide_content` | Write | Medium | https://policylayer.com/tools/jrmatherly-mcp-context-forge/set-slide-content.md |
| `set_slide_title` | Write | Medium | https://policylayer.com/tools/jrmatherly-mcp-context-forge/set-slide-title.md |
| `sprint_planning_helper` | Write | Medium | https://policylayer.com/tools/jrmatherly-mcp-context-forge/sprint-planning-helper.md |
| `stakeholder_matrix` | Write | Medium | https://policylayer.com/tools/jrmatherly-mcp-context-forge/stakeholder-matrix.md |
| `workflow.create_evaluation_suite` | Write | Medium | https://policylayer.com/tools/jrmatherly-mcp-context-forge/workflow.create-evaluation-suite.md |
| `write_data` | Write | Medium | https://policylayer.com/tools/jrmatherly-mcp-context-forge/write-data.md |

## Tool descriptions

- `clear_cache` — Clear the RSS feed cache
- `delete_slide` — Delete a slide from the presentation
- `agent.benchmark_performance` — Run comprehensive agent benchmarks comparing against baselines
- `bitbucket_trigger_pipeline` — Trigger a new pipeline run
- `build_schedule` — Convert WBS into a simple sequential schedule model.
- `calculate_stats` — Perform calculation with multiple operations (testing complex output)
- `compile_document` — Compile a LaTeX document to PDF or other formats
- `critical_path_analysis` — Run critical path analysis over a schedule.
- `execute_code` — Execute Python code in a secure sandbox environment
- `judge.rank_responses` — Rank multiple responses from best to worst using LLM-as-a-judge
- `performance.evaluate_throughput_scaling` — Test concurrent request handling and scaling behavior
- `query_data` — Execute SQL-like queries on loaded datasets
- `render_graph` — Render a DOT graph to an image
- `robustness.assess_distribution_shift` — Test performance degradation on out-of-domain data
- `robustness.measure_input_sensitivity` — Test response stability to input variations and perturbations
- `robustness.test_adversarial_inputs` — Evaluate system response to malicious prompts and attack vectors
- `statistical_test` — Perform statistical hypothesis testing
- `transform_data` — Apply data transformations and cleaning operations
- `workflow.run_evaluation` — Execute evaluation suite on test data with parallel or sequential execution
- `agent.analyze_reasoning` — Evaluate agent
- `agent.evaluate_tool_use` — Assess agent
- `agent.measure_task_completion` — Evaluate end-to-end task success against measurable criteria
- `analyze_code` — Analyze code structure, complexity, and dependencies
- `analyze_csv` — Perform automated analysis of CSV data
- `analyze_dataset` — Perform comprehensive dataset analysis and profiling
- `analyze_document` — Analyze document structure and content
- `analyze_feed` — Comprehensive feed analysis with recommendations
- `analyze_graph` — Analyze a DOT graph structure and metrics
- `analyze_text` — Analyze text and recommend optimal chunking strategy
- `analyze_workbook` — Analyze workbook content, structure, and formulas
- `baseline_vs_actual` — Compare baseline vs actual metrics
- `batch_convert` — Convert multiple URLs to markdown in parallel
- `bias.assess_cultural_sensitivity` — Evaluate cross-cultural appropriateness and cultural awareness
- `bias.detect_demographic_bias` — Identify bias against protected groups using pattern matching and LLM assessment
- `bias.detect_linguistic_bias` — Identify language-based discrimination and dialect bias
- `bias.evaluate_outcome_equity` — Check for disparate impacts across protected groups in outcomes
- `bias.measure_intersectional_fairness` — Evaluate compound bias effects across multiple identity dimensions
- `bias.measure_representation_fairness` — Assess balanced representation across groups in different contexts
- `bitbucket_get_pipeline` — Get status and details for a specific pipeline run
- `bitbucket_get_pr` — Get details for a specific pull request including diff
- `bitbucket_get_repo` — Get details for a specific repository
- `bitbucket_list_pipelines` — List pipeline runs for a repository
- `bitbucket_list_prs` — List pull requests for a repository
- `bitbucket_list_repos` — List repositories accessible to the authenticated user
- `bitbucket_search_code` — Search code across repositories in a workspace
- `calibration.test_judge_agreement` — Measure agreement between different judges and human evaluators
- `change_request_tracker` — Summarise change request impacts
- `chat_with_csv` — Chat with CSV data using natural language queries
- `chunk_markdown` — Chunk markdown text with header awareness
- `chunk_text` — Chunk text using various strategies (recursive, semantic, sentence, fixed_size)
- `cluster_by_topic` — Cluster feed entries by semantic similarity
- `convert_file` — Convert a local file to markdown format
- `convert_url` — Convert URL content to markdown format with multiple engines and options
- `decode_qr_code` — Decode QR code from image file
- `divide_numbers` — Divide two numbers with error handling in output
- `document_template_library` — Expose packaged PM templates
- `earned_value_calculator` — Compute earned value management metrics
- `echo` — Simple echo tool without output schema (for comparison)
- `extract_classes` — Extract class definitions from code
- `extract_functions` — Extract function definitions from code
- `extract_text` — Extract all text content from a document
- `fetch_rss` — Fetch and parse an RSS feed from URL
- `filter_by_date` — Filter entries by date range
- `find_by_author` — Find entries by author/speaker
- `find_duplicates` — Find duplicate or near-duplicate entries using semantic similarity
- `find_related_entries` — Find related entries to a specific entry
- `fixed_size_chunk` — Fixed-size chunking with word boundary options
- `get_capabilities` — Get information about converter capabilities and available engines
- `get_csv_info` — Get comprehensive information about CSV data structure
- `get_document_info` — Get information about a document
- `get_feed_metadata` — Get feed metadata (title, description, author, etc.)
- `get_feed_statistics` — Get comprehensive feed statistics and analysis
- `get_latest_entries` — Get N most recent entries from feed
- `get_presentation_info` — Get information about the presentation
- `get_sandbox_info` — Get current sandbox capabilities and configuration
- `get_server_info` — Get server information and capabilities
- `get_strategies` — List available chunking strategies and capabilities
- `get_supported_charts` — Get list of supported chart types and capabilities
- `get_templates` — Get Mermaid diagram templates
- `glossary_lookup` — Provide glossary definitions for common PM terms
- `inspect_feed_schema` — Inspect feed schema and available fields
- `judge.evaluate_response` — Evaluate a single response using LLM-as-a-judge with customizable criteria and rubrics
- `judge.evaluate_with_reference` — Evaluate response against a gold standard reference using LLM-as-a-judge
- `judge.pairwise_comparison` — Compare two responses and determine which is better using LLM-as-a-judge
- `lessons_learned_catalog` — Aggregate lessons learned entries
- `list_authors` — List all unique authors/speakers with entry counts
- `list_categories` — List all categories/tags with entry counts
- `list_generated_datasets` — List metadata about previously generated datasets
- `list_layouts` — List available layout engines and output formats
- `list_presets` — List available dataset presets with column definitions
- `list_supported_formats` — List supported input and output formats
- `load_dataset` — Load data from various sources and formats (CSV, JSON, Parquet, SQL, Excel)
- `meeting_minutes_summarizer` — Summarise meeting transcript into decisions and actions
- `multilingual.assess_cultural_adaptation` — Evaluate cultural appropriateness and localization quality
- `multilingual.detect_language_mixing` — Identify inappropriate code-switching or language mixing
- `multilingual.evaluate_translation_quality` — Assess translation accuracy and quality across languages
- `multilingual.measure_cross_lingual_consistency` — Check consistency across multiple language versions
- `multiply_numbers` — Multiply two numbers with structured output
- `open_presentation` — Open an existing PowerPoint presentation
- `performance.assess_computational_efficiency` — Measure resource usage and computational efficiency metrics
- `performance.measure_response_latency` — Track generation speed and response times with statistical analysis
- `performance.monitor_memory_usage` — Track memory consumption patterns during execution
- `privacy.assess_consent_clarity` — Evaluate clarity and comprehensibility of consent notices
- `privacy.assess_data_minimization` — Evaluate if data collection follows minimization principles
- `privacy.assess_privacy_by_design` — Evaluate privacy-by-design implementation in systems
- `privacy.detect_data_leakage` — Identify unintended data exposure or leakage in outputs
- `privacy.detect_pii_exposure` — Detect personally identifiable information in text with configurable sensitivity
- `privacy.evaluate_consent_compliance` — Assess consent mechanisms and compliance with privacy regulations
- `privacy.evaluate_data_retention_compliance` — Assess data retention policy compliance and effectiveness
- `privacy.measure_anonymization_effectiveness` — Evaluate effectiveness of data anonymization techniques
- `project_health_dashboard` — Produce project health dashboard summary
- `prompt.assess_relevance` — Measure semantic alignment between prompt and outputs using embeddings
- `prompt.evaluate_clarity` — Assess prompt clarity using multiple rule-based and LLM-based metrics
- `prompt.measure_completeness` — Evaluate if prompt generates complete responses covering expected components
- `prompt.test_consistency` — Test prompt consistency across multiple runs and temperature settings
- `quality.assess_toxicity` — Detect harmful or biased content using pattern matching and LLM analysis
- `quality.evaluate_factuality` — Check factual accuracy of responses against knowledge bases
- `quality.measure_coherence` — Analyze logical flow and consistency of text using rule-based and LLM metrics
- `rag.assess_answer_groundedness` — Verify answers are grounded in provided context by checking claim support
- `rag.assess_citation_accuracy` — Validate citation quality and accuracy against source documents
- `rag.benchmark_retrieval_systems` — Compare different retrieval approaches using standard IR metrics
- `rag.detect_hallucination_vs_context` — Identify when responses contradict provided context using statement verification
- `rag.evaluate_retrieval_coverage` — Measure if key information was retrieved by checking topic coverage
- `rag.evaluate_retrieval_relevance` — Assess relevance of retrieved documents to the query using semantic similarity and LLM judges
- `rag.measure_chunk_relevance` — Evaluate individual chunk relevance scores using semantic similarity and LLM assessment
- `rag.measure_context_utilization` — Check how well retrieved context is used in the generated answer
- `read_data` — Read data from a worksheet
- `resource_allocator` — Report resource allocation variance
- `retrieve_dataset` — Retrieve persisted dataset content in CSV or JSONL format
- `robustness.evaluate_prompt_injection_resistance` — Check prompt injection defenses and security measures
- `robustness.measure_consistency_under_perturbation` — Check output stability under various input perturbations
- `safety.assess_instruction_following` — Measure adherence to constraints and safety instructions
- `safety.detect_harmful_content` — Identify dangerous or harmful outputs across multiple risk categories
- `safety.evaluate_refusal_appropriateness` — Check when system appropriately refuses potentially harmful requests
- `safety.measure_value_alignment` — Assess alignment with human values and ethical principles
- `sample_data_catalog` — List packaged sample data assets
- `schedule_optimizer` — Suggest lightweight schedule optimisations
- `scope_guardrails` — Check proposed features against scope guardrails
- `search_all` — Search across all fields (title, description, author, categories)
- `search_descriptions` — Search RSS feed entries by description/content
- `search_multi_field_semantic` — Multi-field semantic search (custom field selection)
- `search_subtitles_semantic` — Semantic search in podcast subtitles (iTunes, Google Play, etc.)
- `search_summaries_semantic` — Semantic search in episode summaries/descriptions
- `search_titles` — Search RSS feed entries by title
- `semantic_chunk` — Semantic chunking based on content similarity
- `sentence_chunk` — Sentence-based chunking with configurable grouping
- `server.get_available_judges` — Get list of available judge models and their capabilities
- `server.get_cache_stats` — Get caching system statistics and performance metrics
- `server.get_evaluation_results` — List evaluation results with optional filtering
- `server.get_evaluation_suites` — List all created evaluation suites
- `similarity_search` — Semantic similarity search using AI embeddings
- `split_code` — Split code into logical segments using AST analysis
- `status_report_generator` — Render status report markdown via template
- `summarize_dataset` — Return summary statistics for a generated dataset
- `time_series_analysis` — Analyze time series data patterns, trends, and forecasting
- `validate_code` — Validate Python code without executing it
- `validate_email` — Validate email address format
- `validate_graph` — Validate DOT file syntax
- `validate_mermaid` — Validate Mermaid diagram syntax
- `validate_qr_data` — Validate and analyze QR code data before generation
- `workflow.compare_evaluations` — Compare results across multiple evaluation runs with statistical analysis
- `action_item_tracker` — Merge action item updates
- `add_content` — Add content to a LaTeX document
- `add_edge` — Add an edge to a DOT graph
- `add_figure` — Add a figure to a LaTeX document
- `add_formula` — Add a formula to a cell
- `add_heading` — Add a heading to a document
- `add_image` — Add an image to a slide
- `add_node` — Add a node to a DOT graph
- `add_numbers` — Add two numbers and return a structured result with output schema
- `add_section` — Add a section to a LaTeX document
- `add_shape` — Add a shape to a slide
- `add_slide` — Add a new slide to the presentation
- `add_table` — Add a table to a document
- `add_text` — Add text to a document
- `add_text_box` — Add a text box to a slide
- `bitbucket_create_pr` — Create a new pull request
- `bitbucket_merge_pr` — Merge a pull request
- `bitbucket_pr_comments` — List or add comments on a pull request
- `calibration.optimize_rubrics` — Tune evaluation rubrics for better alignment with human judgments
- `communications_planner` — Plan communications cadence per stakeholder
- `convert_batch` — Convert multiple documents to the same format
- `convert_content` — Convert raw HTML or text content to markdown
- `convert_document` — Convert a document to another format using LibreOffice
- `create_bar_chart` — Create bar chart for categorical data
- `create_chart` — Create a chart with flexible data input and configuration
- `create_diagram` — Create and optionally render a Mermaid diagram
- `create_document` — Create a new DOCX document
- `create_flowchart` — Create flowchart from structured data
- `create_from_template` — Create a LaTeX document from a template
- `create_gantt_chart` — Create Gantt chart from task data
- `create_graph` — Create a new DOT graph file
- `create_line_chart` — Create line chart for time series or continuous data
- `create_presentation` — Create a new PowerPoint presentation
- `create_scatter_plot` — Create scatter plot with advanced customization
- `create_sequence_diagram` — Create sequence diagram from participants and messages
- `create_user` — Create a user profile with structured validation
- `create_visualization` — Generate statistical plots and charts
- `create_workbook` — Create a new XLSX workbook
- `format_cells` — Format cells in a worksheet
- `format_text` — Format text in a document
- `generate_batch_qr_codes` — Generate multiple QR codes
- `generate_dataset` — Generate a synthetic dataset and persist it for later retrieval
- `generate_work_breakdown` — Generate a work breakdown structure from scope narrative.
- `merge_documents` — Merge multiple documents into one file
- `produce_gantt_diagram` — Generate gantt chart artefacts from schedule
- `project_brief_generator` — Generate project brief summary
- `risk_register_manager` — Manage and rank risks by severity
- `save_presentation` — Save the presentation to a file
- `set_attributes` — Set graph, node, or edge attributes
- `set_slide_content` — Set the main content of a slide
- `set_slide_title` — Set the title of a slide
- `sprint_planning_helper` — Assemble sprint backlog based on capacity and priority
- `stakeholder_matrix` — Produce stakeholder matrix diagram
- `workflow.create_evaluation_suite` — Define comprehensive evaluation pipeline with multiple tools and success criteria
- `write_data` — Write data to a worksheet

## Related servers

- UnClick (1662 tools) — https://policylayer.com/tools/io-github-malamutemayhem-unclick-mcp-server.md
- Delx Protocol — Agent Recovery & Continuity (1076 tools) — https://policylayer.com/tools/io-github-davidmosiah-delx-protocol.md
- Delx Mcp A2a (1068 tools) — https://policylayer.com/tools/io-github-davidmosiah-delx-mcp-a2a.md
- Nodebench (824 tools) — https://policylayer.com/tools/io-github-homenshum-nodebench.md
- MCP Framework Personal (811 tools) — https://policylayer.com/tools/inggerman-mcps.md
- Delx MCP Server (740 tools) — https://policylayer.com/tools/io-github-davidmosiah-delx-mcp-server.md
- Binance MCP Server (734 tools) — https://policylayer.com/tools/nirholas-binance-mcp.md
- Eda Agent (726 tools) — https://policylayer.com/tools/eda-agent.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=jrmatherly-mcp-context-forge · API: https://policylayer.com/registry/api · Recommended policies for every tool: https://policylayer.com/policies/jrmatherly-mcp-context-forge