// SCAN REPORT

Open Context

6 tools. 1 can modify or destroy data without limits.

1 write tool that can modify data. Rate limits recommended.

Last updated: 2 Jul 2026

1 can modify or destroy data

5 read-only

6 tools total

Community server · catalogue entry verified 02/07/2026

How to control Open Context ↓

TOOL MAP

What Open Context exposes to your agents

Read (5) Write / Execute (1) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Open Context tools

Write · Medium update_module_context This tool creates or modifies data reversibly—it updates module documentation/context within a codebase.

1 of Open Context's 6 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Open Context

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

Rate limit write operations

{
  "update_module_context": {
    "limits": [
      {
        "counter": "update_module_context_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "get_module_context": {
    "limits": [
      {
        "counter": "get_module_context_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 Open Context — 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 OPEN CONTEXT →

Instant setup, no code required.

FULL CATALOGUE

All 6 Open Context tools

WRITE 1 tools

Write update_module_context Update a module

READ 5 tools

Read get_module_context Get detailed context for a specific module by ID or file path. Use list_modules first to see available modules Read get_project_context Get the full context document (llms.txt format) for a project. This includes project description, architecture Read list_modules List all modules in a project with their types, paths, and context status. Read resolve_project Find a project by working directory path or name. Pass cwd for auto-detection from your current directory, or Read search_context Search across all project contexts for a keyword or phrase. Returns matching projects and modules with relevan

FAQ

Questions about Open Context

How do I prevent bulk modifications through Open Context? +

The Open Context server has 1 write tools including update_module_context. 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 Open Context.

How many tools does the Open Context MCP server expose? +

6 tools across 2 categories: Read, Write. 5 are read-only. 1 can modify, create, or delete data.

How do I enforce a policy on Open Context? +

Register the Open Context 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 Open Context tool call.

Deterministic rules across all 6 Open Context tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON OPEN CONTEXT →

Instant setup, no code required.

6 Open Context tools catalogued and risk-classified — across an index of 43,000+ MCP servers.