// SCAN REPORT

Self-hosted MCP server for Claude

Q: How do I prevent bulk modifications through Self-hosted MCP server for Claude?

The Self-hosted MCP server for Claude server has 4 write tools including book_note, book_split, sftp_upload. 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 Self-hosted MCP server for Claude.

Q: How many tools does the Self-hosted MCP server for Claude MCP server expose?

12 tools across 3 categories: Execute, Read, Write. 4 are read-only. 8 can modify, create, or delete data.

Q: How do I enforce a policy on Self-hosted MCP server for Claude?

Register the Self-hosted MCP server for Claude 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.

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

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

Last updated: 30 Jun 2026

8 can modify or destroy data

4 read-only

12 tools total

Community server · catalogue entry verified 30/06/2026

How to control Self-hosted MCP server for Claude ↓

TOOL MAP

What Self-hosted MCP server for Claude exposes to your agents

Read (4) Write / Execute (8) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Self-hosted MCP server for Claude tools

Execute · Critical aws_cli This tool executes arbitrary AWS CLI commands with effects determined entirely by user input. Execute · High local_exec This tool triggers arbitrary shell command execution (via cmd.exe on Windows or /bin/sh on Linux/Mac) whose effects are entirely argument-dependent. Execute · Critical ssh_exec This tool enables execution of arbitrary shell commands on remote servers via SSH. Execute · Critical postgres_query This tool executes arbitrary SQL queries against a PostgreSQL database over SSH.

8 of Self-hosted MCP server for Claude's 12 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Self-hosted MCP server for Claude

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

Rate limit write operations

{
  "book_note": {
    "limits": [
      {
        "counter": "book_note_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "book_chunk": {
    "limits": [
      {
        "counter": "book_chunk_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 Self-hosted MCP server for Claude — 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 SELF-HOSTED MCP SERVER FOR CLAUDE →

Instant setup, no code required.

FULL CATALOGUE

All 12 Self-hosted MCP server for Claude tools

EXECUTE 4 tools

Execute aws_cli Run an AWS CLI command using the locally configured AWS profile. Pass arguments as an array of strings (no Execute local_exec Run a shell command on the local machine where this MCP server is running. On Windows the command goes to cmd. Execute postgres_query Run a SQL query on a PostgreSQL database over SSH on a remote host from hosts.json. Uses psql via Execute ssh_exec Run a shell command on a remote host over SSH. Two ways to specify the target:\n\n(A) PREFERRED: pass host=<na

WRITE 4 tools

Write book_note Read/write structured notes for a long document in a JSON file (_notes.json in book_dir). Useful for tracking Write book_split Split a large text file into chunks of ~N words each (default 3000). Saves chunks and a _meta.json index to th Write sftp_upload Upload a local file to a remote host (over SFTP, reusing the persistent SSH pool). Streams the transfer. Use w Write write_file Write text content to a file on the local machine. Creates parent directories if needed. Overwrites existing f

READ 4 tools

Read book_chunk Read one chunk of a large text file (e.g. a book) that was pre-split into ~3000-word chunks by book_split. Use Read github_api Make a request to the GitHub REST API using the configured Personal Access Token. Use endpoint paths like Read pm2_status Show PM2 status (process list and optionally recent logs) on a remote host. Quick diagnostics: Read sftp_download Download a file from a remote host (over SFTP, reusing the persistent SSH pool) to the local filesystem where

EXPLORE

Related servers

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

FAQ

Questions about Self-hosted MCP server for Claude

How do I prevent bulk modifications through Self-hosted MCP server for Claude? +

The Self-hosted MCP server for Claude server has 4 write tools including book_note, book_split, sftp_upload. 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 Self-hosted MCP server for Claude.

How many tools does the Self-hosted MCP server for Claude MCP server expose? +

12 tools across 3 categories: Execute, Read, Write. 4 are read-only. 8 can modify, create, or delete data.

How do I enforce a policy on Self-hosted MCP server for Claude? +

Register the Self-hosted MCP server for Claude 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 Self-hosted MCP server for Claude tool call.

Deterministic rules across all 12 Self-hosted MCP server for Claude tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON SELF-HOSTED MCP SERVER FOR CLAUDE →

Instant setup, no code required.

12 Self-hosted MCP server for Claude tools catalogued and risk-classified — across an index of 43,000+ MCP servers.