// SCAN REPORT

RepoMemory

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

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

Last updated: 30 Jun 2026

2 can modify or destroy data

6 read-only

8 tools total

Community server · catalogue entry verified 30/06/2026

How to control RepoMemory ↓

TOOL MAP

What RepoMemory exposes to your agents

Read (6) Write / Execute (2) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous RepoMemory tools

Write · High apply_pack apply_pack creates or modifies files in a repository. Write · Medium generate_pack This tool creates or modifies repository configuration and metadata files (CLAUDE.md, .claudeignore, hooks).

2 of RepoMemory's 8 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control RepoMemory

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

Rate limit write operations

{
  "apply_pack": {
    "limits": [
      {
        "counter": "apply_pack_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "check_drift": {
    "limits": [
      {
        "counter": "check_drift_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 RepoMemory — 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 REPOMEMORY →

Instant setup, no code required.

FULL CATALOGUE

All 8 RepoMemory tools

WRITE 2 tools

Write apply_pack Generate AI context files AND write them directly to the repository. Use with care - this modifies files in th Write generate_pack Generate AI context files (CLAUDE.md, .claudeignore, slash commands, pre-commit hook) for a repository. Requir

READ 6 tools

Read check_drift Compare current repository state against the last scan snapshot. Detects changed, added, or deleted files - es Read explain_codebase Provides a comprehensive explanation of a repository Read explain_repo Returns a structured explanation of the repository Read repo_health Returns a comprehensive health score for a repository Read scan_repo Scan a local repository folder and audit its AI context quality. Returns a score (0-100) across 7 dimensions: Read suggest_context_updates Analyzes a repository for changes that may require AI context file updates. Returns a list of specific recomme

FAQ

Questions about RepoMemory

How do I prevent bulk modifications through RepoMemory? +

The RepoMemory server has 2 write tools including apply_pack, generate_pack. 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 RepoMemory.

How many tools does the RepoMemory MCP server expose? +

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

How do I enforce a policy on RepoMemory? +

Register the RepoMemory 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 RepoMemory tool call.

Deterministic rules across all 8 RepoMemory tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON REPOMEMORY →

Instant setup, no code required.

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