Claude Writer's Aid MCP

34 tools. 5 can modify or destroy data without limits.

5 write tools that can modify data. Rate limits recommended.

Last updated:

5 can modify or destroy data
29 read-only
34 tools total

Community server · catalogue entry verified 12/06/2026

How to control Claude Writer's Aid MCP ↓

What Claude Writer's Aid MCP exposes to your agents

Read (29) Write / Execute (5) Destructive / Financial (0)
High Risk

The most dangerous Claude Writer's Aid MCP tools

5 of Claude Writer's Aid MCP's 34 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

How to control Claude Writer's Aid MCP

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

Rate limit write operations
{
  "add_style_decision": {
    "limits": [
      {
        "counter": "add_style_decision_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations
{
  "analyze_link_graph": {
    "limits": [
      {
        "counter": "analyze_link_graph_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

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

  1. Create a free account and register Claude Writer's Aid MCP — nothing to install.
  2. Add these rules — paste them, or build them visually. Tune the limits to your setup.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
ENFORCE POLICY ON CLAUDE WRITER'S AID →

Free to start. No card required.

All 34 Claude Writer's Aid MCP tools

READ 29 tools
Read analyze_link_graph Visualize connections between documents Read check_before_edit Check context before editing a file - get warnings about past mistakes, decisions, and requirements to maintai Read check_readability Analyze readability metrics Read check_terminology Find inconsistent term usage Read extract_themes Cluster content into main themes/topics Read find_broken_links Detect broken internal and external links Read find_concept_contradictions Detect contradictions in concept definitions across versions Read find_duplicates Find near-duplicate content Read find_gaps Find terms mentioned but not explained Read find_orphaned_sections Find sections with no incoming links Read find_related_sections Find content semantically similar to given text Read find_todos Extract all TODO/FIXME/DRAFT markers Read get_file_context Get all context for a file (sessions, decisions, mistakes, commits) Read get_requirements Get all requirements or filter by type Read get_session_context Get detailed context for a specific file or concept from past sessions Read get_writing_stats Overall project statistics Read holistic_search Unified search across all memory layers (content, decisions, mistakes, concepts, sessions, commits) Read link_commits_to_sessions Link git commits to writing sessions for context Read list_writing_decisions List writing decisions by file, type, or date range Read recall_writing_session Search writing session history by date range or query Read search_content Semantic search across all manuscript content Read search_similar_mistakes Search for similar mistakes to avoid repeating them Read suggest_reorganization Suggest better content organization Read trace_reference_chain Follow concept through linked documents Read track_changes Show what changed since timestamp Read track_concept_evolution Show how concept is discussed across documents Read track_file_evolution Show how a file evolved through git commits with rationale Read validate_structure Check heading hierarchy and section balance Read generate_progress_report Create progress dashboard

Questions about Claude Writer's Aid MCP

How do I prevent bulk modifications through Claude Writer's Aid MCP? +

The Claude Writer's Aid MCP server has 5 write tools including add_style_decision, generate_outline, mark_mistake. 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 Claude Writer's Aid MCP.

How many tools does the Claude Writer's Aid MCP server expose? +

34 tools across 2 categories: Read, Write. 29 are read-only. 5 can modify, create, or delete data.

How do I enforce a policy on Claude Writer's Aid MCP? +

Register the Claude Writer's Aid 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 Claude Writer's Aid MCP tool call.

Deterministic rules across all 34 Claude Writer's Aid MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

34 Claude Writer's Aid MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.