// SCAN REPORT

Project Context Map

10 tools. 2 can modify or destroy data without limits.

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

Last updated: 2 Jul 2026

2 can modify or destroy data

8 read-only

10 tools total

Community server · catalogue entry verified 02/07/2026

How to control Project Context Map ↓

TOOL MAP

What Project Context Map exposes to your agents

Read (8) Write / Execute (2) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Project Context Map tools

Write · Medium write_and_log This tool creates or modifies file content and log entries, which are reversible operations. Write · Medium refresh_project_map This tool overwrites two specific files (.project-map.json and .project-map.md) with freshly generated content.

2 of Project Context Map's 10 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Project Context Map

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

Rate limit write operations

{
  "refresh_project_map": {
    "limits": [
      {
        "counter": "refresh_project_map_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "explain_file_role": {
    "limits": [
      {
        "counter": "explain_file_role_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 Project Context Map — 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 PROJECT CONTEXT MAP →

Instant setup, no code required.

FULL CATALOGUE

All 10 Project Context Map tools

WRITE 2 tools

Write refresh_project_map Regenerate .project-map.json and .project-map.md for the current repository. Write write_and_log Writes file content and appends an entry to the .project.md Change Log.

READ 8 tools

Read explain_file_role Explain why a file exists, which module it belongs to, and whether it changed recently. Read find_relevant_files Rank the most relevant files for a natural-language task so the coding agent can open only a small subset. Read get_module_context Return context for a module or feature area, including module summary, files, recent commits, and likely impac Read get_project_summary Load the current project context map and return the project summary, modules, stack, and hotspots. Read get_recent_git_changes Summarize git commits and hotspots from the last N days. Default is 5 days. Read query_topology Takes a natural language query and returns matched file paths from the query index, along with import/dependen Read read_files_sparse Read only a small set of indexed files. Rejects paths that are outside the project root or missing from the pr Read read_project_context Returns the generated .project.md content for the repository.

FAQ

Questions about Project Context Map

How do I prevent bulk modifications through Project Context Map? +

The Project Context Map server has 2 write tools including refresh_project_map, write_and_log. 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 Project Context Map.

How many tools does the Project Context Map MCP server expose? +

10 tools across 2 categories: Read, Write. 8 are read-only. 2 can modify, create, or delete data.

How do I enforce a policy on Project Context Map? +

Register the Project Context Map 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 Project Context Map tool call.

Deterministic rules across all 10 Project Context Map tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON PROJECT CONTEXT MAP →

Instant setup, no code required.

10 Project Context Map tools catalogued and risk-classified — across an index of 43,000+ MCP servers.