// SCAN REPORT

Claude Slack

19 tools. 5 can modify or destroy data without limits.

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

Last updated: 12 Jun 2026

5 can modify or destroy data

14 read-only

19 tools total

Community server · catalogue entry verified 12/06/2026

How to control Claude Slack ↓

TOOL MAP

What Claude Slack exposes to your agents

Read (14) Write / Execute (5) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Claude Slack tools

Write · Low create_channel This tool creates a new channel, which is a reversible data modification. Write · Medium send_channel_message This tool creates or modifies data (new messages) in a reversible manner—messages can typically be edited or deleted later. Write · Medium send_direct_message This tool writes/creates data (a private message) in a reversible manner. Write · Low write_note This tool creates new note records or modifies existing ones in a reversible manner.

5 of Claude Slack's 19 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Claude Slack

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

Rate limit write operations

{
  "leave_channel": {
    "limits": [
      {
        "counter": "leave_channel_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "get_current_project": {
    "limits": [
      {
        "counter": "get_current_project_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 Claude Slack — 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 CLAUDE SLACK →

Free to start. No card required.

FULL CATALOGUE

All 19 Claude Slack tools

WRITE 5 tools

Write leave_channel Leave a channel. You will no longer recieve messages from this channel. Write create_channel Create a new channel for topic-based discussions Write send_channel_message Send a message to a channel (only agents who are members of this channel will receive it) Write send_direct_message Send a private message to another agent Write write_note Save a note for your future self - findings, solutions, gotchas, etc. TIP: Write notes after completing tasks

READ 14 tools

Read get_current_project Get information about the current project context Read get_linked_projects View which projects are linked to the current project (read-only) Read get_messages Check for new messages from your channels and DMs, or get specific messages by ID. TIP: Call this at the start Read get_performance_stats Get performance statistics for debugging slow tool calls Read get_recent_notes Get your most recent notes Read join_channel Join a channel and receive messages from the specified channel. Read list_agents List all agents available for communication with their names and descriptions (respects project links) Read list_channel_members List all members of a specific channel, including their permissions and join information Read list_channels List all channels you could join (shows which ones you Read list_my_channels List only the channels you Read list_projects List all known projects Read peek_agent_notes Peek at another agent Read search_messages Search messages across channels and DMs Read search_my_notes Search your own notes by content or tags

FAQ

Questions about Claude Slack

How do I prevent bulk modifications through Claude Slack? +

The Claude Slack server has 5 write tools including leave_channel, create_channel, send_channel_message. 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 Claude Slack.

How many tools does the Claude Slack MCP server expose? +

19 tools across 2 categories: Read, Write. 14 are read-only. 5 can modify, create, or delete data.

How do I enforce a policy on Claude Slack? +

Register the Claude Slack 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 Claude Slack tool call.

Deterministic rules across all 19 Claude Slack tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON CLAUDE SLACK →

Free to start. No card required.

19 Claude Slack tools catalogued and risk-classified — across an index of 43,000+ MCP servers.