// SCAN REPORT

Documcp

52 tools. 24 can modify or destroy data without limits.

3 destructive tools with no built-in limits. Policy required.

Last updated: 12 Jun 2026

24 can modify or destroy data

28 read-only

52 tools total

Community server · catalogue entry verified 12/06/2026

How to control Documcp ↓

TOOL MAP

What Documcp exposes to your agents

Read (28) Write / Execute (21) Destructive / Financial (3)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Documcp tools

Destructive · High cleanup_agent_artifacts The tool explicitly supports a 'clean' operation that removes files from the repository. Destructive · Medium memory_cleanup The tool 'memory_cleanup' is described as cleaning up 'old memories', which implies irreversible deletion of stored state or memory data. Destructive · High memory_pruning Memory pruning typically involves permanently deleting or removing stored information to optimize space/performance. Execute · Medium change_watcher This tool executes automated operations (drift detection workflows) triggered by repository events.

24 of Documcp's 52 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Documcp

PolicyLayer is an MCP gateway — it sits between your AI agents and Documcp, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations

{
  "cleanup_agent_artifacts": {
    "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

{
  "optimize_readme": {
    "limits": [
      {
        "counter": "optimize_readme_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "analyze_deployments": {
    "limits": [
      {
        "counter": "analyze_deployments_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

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

Create a free account and register Documcp — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON DOCUMCP →

Free to start. No card required.

FULL CATALOGUE

All 52 Documcp tools

DESTRUCTIVE 3 tools

Destructive cleanup_agent_artifacts Detect, classify, and clean up artifacts generated by AI coding agents (e.g., TODO.md, PLAN.md, agent markers, Destructive memory_cleanup Clean up old memories Destructive memory_pruning Intelligent memory pruning and optimization

EXECUTE 5 tools

Execute change_watcher Watch code changes and trigger documentation drift detection in near real-time. Execute deploy_pages [DEPRECATED — use deploy_site instead] Set up GitHub Pages deployment workflow. This alias will be removed in Execute deploy_site Set up deployment workflow for GitHub Pages or Vercel with deployment tracking and preference learning. Use th Execute memory_migration Create and execute migration plans between different memory systems Execute test_local_deployment Test documentation build and local server before deploying to GitHub Pages

WRITE 16 tools

Write optimize_readme Optimize README content by restructuring, condensing, and extracting detailed sections to separate documentati Write populate_diataxis_content Intelligently populate Diataxis documentation with project-specific content Write record_drift_outcome Record the host Write sync_code_to_docs Automatically synchronize documentation with code changes using AST-based drift detection (Phase 3) Write validate_documentation_freshness Validate documentation freshness, initialize metadata for files without it, and update timestamps based on cod Write generate_config Generate configuration files for the selected static site generator Write generate_contextual_content Generate context-aware documentation using AST analysis and knowledge graph insights (Phase 3) Write generate_llm_context Generate a comprehensive LLM context reference file documenting all tools, memory system, and workflows for ea Write generate_readme_template Generate standardized README templates for different project types with best practices Write manage_preferences Manage user preferences for documentation generation and SSG recommendations Write manage_sitemap Generate, validate, and manage sitemap.xml as the source of truth for documentation links. Sitemap.xml is used Write memory_agent_network Manage multi-agent memory sharing and collaboration Write memory_import_advanced Advanced memory import with validation and conflict resolution Write setup_playwright_tests Generate Playwright E2E test setup for documentation site (containers + CI/CD) Write setup_structure Create Diataxis-compliant documentation structure Write update_existing_documentation Intelligently analyze and update existing documentation using memory insights and code comparison

READ 28 tools

Read analyze_deployments Analyze deployment patterns and generate insights from historical deployment data Read analyze_readme Comprehensive README analysis with length assessment, structure evaluation, and optimization opportunities Read analyze_repository Analyze repository structure, dependencies, and documentation needs Read check_documentation_links Comprehensive link checking for documentation deployment with external, internal, and anchor link validation Read detect_documentation_gaps Analyze repository and existing documentation to identify missing content and gaps Read evaluate_readme_health Evaluate README files for community health, accessibility, and onboarding effectiveness Read get_community_insights Aggregate cross-project signals from the Knowledge Graph and surface community-level insights: deployment succ Read memory_contextual_search Perform contextual memory retrieval with intelligent ranking Read memory_enhanced_recommendation Get enhanced recommendations using learning and knowledge graph Read memory_insights Get insights and patterns from memory Read memory_intelligent_analysis Get intelligent analysis with patterns, predictions, and recommendations Read memory_knowledge_graph Query the knowledge graph for relationships and paths Read memory_learning_stats Get comprehensive learning and knowledge graph statistics Read memory_optimization_metrics Get comprehensive optimization metrics and recommendations Read memory_recall Recall memories about a project or topic Read memory_similar Find similar projects from memory Read memory_temporal_analysis Analyze temporal patterns and trends in memory data Read memory_visualization Generate visual representations of memory data Read read_directory List files and directories within allowed roots. Use this to discover files without requiring full absolute pa Read readme_best_practices Analyze README files against best practices checklist and generate templates for improvement Read recommend_ssg Recommend the best static site generator based on project analysis and user preferences Read track_documentation_freshness Scan documentation directory for staleness markers and identify files needing updates based on configurable ti Read validate_content Validate general content quality: broken links, code syntax, references, and basic accuracy Read validate_diataxis_content Validate the accuracy, completeness, and compliance of generated Diataxis documentation Read validate_readme_checklist Validate README files against community best practices checklist with detailed scoring Read verify_deployment Verify and troubleshoot GitHub Pages deployment Read memory_export Export memories to JSON or CSV Read memory_export_advanced Advanced memory export with multiple formats and options

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Documcp

Can an AI agent delete data through the Docu MCP server? +

Yes. The Documcp server exposes 3 destructive tools including cleanup_agent_artifacts, memory_cleanup, memory_pruning. 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 Documcp? +

The Documcp server has 16 write tools including optimize_readme, populate_diataxis_content, record_drift_outcome. 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 Documcp.

How many tools does the Docu MCP server expose? +

52 tools across 3 categories: Execute, Read, Write. 28 are read-only. 24 can modify, create, or delete data.

How do I enforce a policy on Documcp? +

Register the Docu 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.

Enforce policy on every Documcp tool call.

Deterministic rules across all 52 Documcp tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON DOCUMCP →

Free to start. No card required.

52 Documcp tools catalogued and risk-classified — across an index of 43,000+ MCP servers.