// SCAN REPORT

Grimoire

3 tools. 0 can modify or destroy data without limits.

Read-only server. Low risk, but rate limits prevent runaway API costs.

Last updated: 30 Jun 2026

0 can modify or destroy data

3 read-only

3 tools total

Community server · catalogue entry verified 30/06/2026

How to control Grimoire ↓

TOOL MAP

What Grimoire exposes to your agents

Read (3) Write / Execute (0) Destructive / Financial (0)

Running more than one server? Check your whole stack →

THE RISK

What can go wrong

Even read-only tools carry cost. An agent in a retry loop can make thousands of API calls per minute, exhausting rate limits and running up bills.

POLICY

How to control Grimoire

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

Cap read operations

{
  "grimoire_index_status": {
    "limits": [
      {
        "counter": "grimoire_index_status_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 Grimoire — 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 GRIMOIRE →

Instant setup, no code required.

FULL CATALOGUE

All 3 Grimoire tools

READ 3 tools

Read grimoire_index_status Show Grimoire index statistics: document count, embedding coverage, data sources, last update times. Read grimoire_quality Run a quality and health check on the Grimoire knowledge base. Reports integrity issues, FTS sync status, and Read grimoire_search Search the Grimoire security knowledge base. Supports keyword (FTS5), semantic (embedding), and hybrid search

EXPLORE

Related servers

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

FAQ

Questions about Grimoire

Is the Grimoire MCP server safe to use without restrictions? +

The Grimoire server is primarily read-only with 3 read tools. While it cannot modify data, an agent in a retry loop can make thousands of API calls per minute, exhausting rate limits and running up costs. Rate limiting is still recommended.

How many tools does the Grimoire MCP server expose? +

3 tools across 2 categories: Execute, Read. 3 are read-only. 0 can modify, create, or delete data.

How do I enforce a policy on Grimoire? +

Register the Grimoire 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 Grimoire tool call.

Deterministic rules across all 3 Grimoire tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON GRIMOIRE →

Instant setup, no code required.

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