// SCAN REPORT

Ia Qa Com/mcp llm and RAG testing Dev/QA toolbox

139 tools. 40 can modify or destroy data without limits.

1 destructive tool with no built-in limits. Policy required.

Last updated: 5 Jun 2026

40 can modify or destroy data

99 read-only

139 tools total

Free to start. No card required.

TOOL MAP

Read (99) Write / Execute (39) Destructive / Financial (1)

CONTEXT-WINDOW COST

21,468 tokens of tool definitions, loaded on every request

11% of a 200k context window

535 heaviest tool: run_vlm_test_suite

Full per-tool breakdown → Model it in the token calculator →

WHAT CAN GO WRONG

Destructive tools (truncate_to_tokens) permanently delete resources. There is no undo. An agent calling these in a retry loop causes irreversible damage.

Write operations (case_convert, color_convert, cookie_security_audit) modify state. Without rate limits, an agent can make hundreds of changes in seconds — faster than any human can review or revert.

Execute tools (build_rag_prompt, cron_parse, env_parse) trigger processes with side effects. Builds, notifications, workflows — all fired without throttling.

RECOMMENDED RULES

Deny destructive operations

{
  "truncate_to_tokens": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "case_convert": {
    "limits": [
      {
        "counter": "case_convert_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "ab_test_report": {
    "limits": [
      {
        "counter": "ab_test_report_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

ALL 139 IA QA COM/MCP LLM AND RAG TESTING DEV/QA TOOLBOX TOOLS

DESTRUCTIVE 1 tools

Destructive truncate_to_tokens

EXECUTE 16 tools

Execute build_rag_prompt Execute cron_parse Execute env_parse Execute mcp_server_evaluate Execute parse_csv Execute parse_http_headers Execute run_eval_contract Execute run_pr_gate_pipeline Execute run_semantic_tests Execute run_vlm_test_suite Execute run_vlm_test_suite_batch Execute strip_markdown Execute system_prompt_builder Execute transform_json_array Execute vector_quantize Execute web_security_audit

READ 99 tools

Read ab_test_report Read analyze_diff_bugs Read base64_decode Read base64_encode Read bias_detect Read bm25_score Read calculate_readability Read check_contrast_ratio Read compare_models Read compare_responses Read consistency_check Read context_window_check Read conversation_analyze Read cors_checker Read cors_test Read cot_analyzer Read count_code_lines Read count_tokens Read cron_validator Read decode_jwt Read detect_language Read detect_secrets Read diff_text Read embedding_similarity Read escape_html Read estimate_llm_cost Read extract_json_from_text Read extract_json_path Read extract_links Read extract_todos Read fetch_veille_feed Read few_shot_formatter Read find_tool Read flatten_json Read format_bytes Read format_json Read format_table Read function_call_validate Read get_testing_guidelines Read guardrail_test Read hallucination_check Read hash_text Read html_to_markdown Read http_status_lookup Read identify_caller Read json_diff Read json_schema_validate Read json_to_csv Read json_to_yaml Read latency_benchmark Read list_llm_models Read list_local_tests Read llm_fit_finder Read llm_format_check Read llm_json_schema_check Read llm_output_validator Read lorem_ipsum Read mcp_schema_lint Read mcp_server_health_check Read minify_js Read mock_from_schema Read model_info Read normalize_vector Read normalize_whitespace Read openapi_validate Read optimize_prompt_tokens Read pr_gatekeeper Read prompt_injection_scan Read prompt_test_suite Read rag_relevance_rank Read redact_pii Read regex_test Read rerank_evaluate Read response_quality_score Read score_geo_signals Read secret_scan Read security_headers_check Read shield_analyze Read similarity_score Read sort_lines Read split_chunks Read ssl_certificate_check Read test_skill Read text_stats Read token_budget_calculator Read toxicity_scan Read unescape_html Read url_decode Read url_encode Read validate_agent_trajectory Read validate_email Read validate_mcp_response Read validate_url Read vector_similarity Read vector_stats Read webhook_endpoint_requests Read word_frequency Read xml_to_json Read yaml_to_json

FAQ

Can an AI agent delete data through the Ia Qa Com/mcp llm and RAG testing Dev/QA toolbox MCP server? +

Yes. The Ia Qa Com/mcp llm and RAG testing Dev/QA toolbox server exposes 1 destructive tools including truncate_to_tokens. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Ia Qa Com/mcp llm and RAG testing Dev/QA toolbox? +

The Ia Qa Com/mcp llm and RAG testing Dev/QA toolbox server has 23 write tools including case_convert, color_convert, cookie_security_audit. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Ia Qa Com/mcp llm and RAG testing Dev/QA toolbox.

How many tools does the Ia Qa Com/mcp llm and RAG testing Dev/QA toolbox MCP server expose? +

139 tools across 4 categories: Destructive, Execute, Read, Write. 99 are read-only. 40 can modify, create, or delete data.

How do I enforce a policy on Ia Qa Com/mcp llm and RAG testing Dev/QA toolbox? +

Register the Ia Qa Com/mcp llm and RAG testing Dev/QA toolbox MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

// RELATED SERVERS

Other MCP servers with similar tools.

Starter policies for each. Same risk classification, live on your fleet in minutes.

Enforce policy on every Ia Qa Com/mcp llm and RAG testing Dev/QA toolbox tool call.

Deterministic rules across all 139 Ia Qa Com/mcp llm and RAG testing Dev/QA toolbox tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

SECURE IA QA COM/MCP LLM AND RAG TESTING DEV/QA TOOLBOX →

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.

Ia Qa Com/mcp llm and RAG testing Dev/QA toolbox

// TOOL MAP

// CONTEXT-WINDOW COST

// WHAT CAN GO WRONG

// RECOMMENDED RULES

// ALL 139 IA QA COM/MCP LLM AND RAG TESTING DEV/QA TOOLBOX TOOLS

// FAQ