// SCAN REPORT

Multi-MCPs

34 tools. 9 can modify or destroy data without limits.

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

Last updated: 4 Jul 2026

9 can modify or destroy data

25 read-only

34 tools total

Community server · catalogue entry verified 04/07/2026

How to control Multi-MCPs ↓

TOOL MAP

What Multi-MCPs exposes to your agents

Read (25) Write / Execute (9) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Multi-MCPs tools

Execute · High send_sms Sending an SMS is an external operation with real-world effects: it contacts third-party infrastructure (Twilio), delivers a message to a phone number, and may incur costs. Execute · High make_call This tool initiates an actual phone call to a real phone number via Twilio, which is an external side-effecting operation. Write · Medium add_tracks_to_playlist This tool creates or modifies data reversibly—it adds tracks to a playlist, which can be undone by removing those tracks later. Write · Medium create_card This tool creates new content (a Trello card) which is a reversible write operation.

9 of Multi-MCPs's 34 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Multi-MCPs

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

Rate limit write operations

{
  "add_tracks_to_playlist": {
    "limits": [
      {
        "counter": "add_tracks_to_playlist_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "geocode_address": {
    "limits": [
      {
        "counter": "geocode_address_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 Multi-MCPs — 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 MULTI-MCPS →

Instant setup, no code required.

FULL CATALOGUE

All 34 Multi-MCPs tools

EXECUTE 2 tools

Execute make_call Make a phone call via Twilio with a TwiML URL Execute send_sms Send an SMS via Twilio

WRITE 7 tools

Write add_tracks_to_playlist Add tracks to a playlist by URIs Write create_card Create a card in a Trello list Write create_issue Create an issue in a repository Write create_page Create a Notion page under a parent page or database Write create_playlist Create a new playlist for a user Write update_card Update a Trello card Write update_page Update a Notion page properties

READ 25 tools

Read geocode_address Geocode a human-readable address Read get_board_cards Get cards on a Trello board Read get_boards Get Trello boards for the authenticated user Read get_coin_price Get current price for a coin in a given currency Read get_current_weather Get current weather by city name Read get_directions Get directions between origin and destination Read get_market_data Get market data for a coin Read get_message_history List message history optionally since a date Read get_photo_details Get photo details by ID Read get_random_photo Get a random photo optionally filtered by category Read get_repository_info Get GitHub repository details Read get_sources List news sources Read get_top_headlines Get top headlines by country and category Read get_track_info Get Spotify track details Read get_trending_coins Get trending coins on CoinGecko Read get_weather_alerts Get weather alerts for a location (requires One Call support) Read get_weather_forecast Get 5-day/3-hour forecast by city name Read list_commits List recent commits for a repository Read query_database Query a Notion database with optional filter Read search_news Search news articles Read search_pages Search Notion pages by query string Read search_photos Search Unsplash photos Read search_places Search places via Google Places Text Search Read search_repositories Search GitHub repositories Read search_tracks Search tracks on Spotify

FAQ

Questions about Multi-MCPs

How do I prevent bulk modifications through Multi-MCPs? +

The Multi-MCPs server has 7 write tools including add_tracks_to_playlist, create_card, create_issue. 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 Multi-MCPs.

How many tools does the Multi-MCPs MCP server expose? +

34 tools across 2 categories: Read, Write. 25 are read-only. 9 can modify, create, or delete data.

How do I enforce a policy on Multi-MCPs? +

Register the Multi-MCPs 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 Multi-MCPs tool call.

Deterministic rules across all 34 Multi-MCPs tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON MULTI-MCPS →

Instant setup, no code required.

34 Multi-MCPs tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// WHERE THIS COMES FROM

These policies come from Multi-MCPs's registry record.

The record behind this page: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.

Teams ship this data inside their own products. See what a licence covers →