receive_messages

Get inbox messages. Messages are automatically archived after being read. Supports pagination and long-polling. Respond to messages with reply_expected=true. WARNING: Messages with reply_expected=false include a reply_warnings alert - consult your human supervisor if you believe a reply is necess...

ServerBrainstorm
CategoryRead

How to control receive_messages ↓

WHAT IT DOES

What receive_messages does on Brainstorm

AI agents call receive_messages to retrieve information from Brainstorm without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

THE RISK

Low Risk

Why receive_messages needs a policy

This is a read-only tool that retrieves message data. While messages are automatically archived after being read, this is an automatic metadata state change rather than a destructive or write action initiated by the tool user. The tool does not create, modify, delete, execute commands, or move financial resources. The warning about reply_expected flags is a UX concern, not a security category change.

From the tool's definition Tool description states 'Get inbox messages' and 'Supports pagination and long-polling.' The core function is retrieval with no side effects other than automatic archival of read messages (a metadata operation, not data destruction).

Documented attack patterns abuse exactly the kind of access receive_messages gives an agent:

POLICY

How to control receive_messages

PolicyLayer is an MCP gateway — it sits between your AI agents and Brainstorm, and nothing reaches the server without passing your rules. This is the rule we recommend for receive_messages:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "receive_messages": {}
  }
}

receive_messages is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

Create a free account and register Brainstorm — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

CAP THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Brainstorm tools

Destructive delete_project Delete a project. Only the agent that created the project can delete it. Destructive delete_resource Delete a resource from the project. Only the resource creator can delete it. Write handover_coordinator Transfer coordinator role to another member. Only current coordinator can initiate. Target Write join_project Join a project with agent name. Session must be initialized by calling status tool first. Write leave_project Leave a project gracefully. Archives your unread messages and removes your membership. You Write store_resource Store shared resource. Use content for <50KB, source_path for >50KB (max 500KB). With sour Write archive_project Mark a project as archived (inactive but recoverable). Only the project creator can archiv Write create_project Create a new cooperation project. Projects are the organizing unit for agent collaboration

All 17 Brainstorm tools →

Read tools on other servers

M-Team MCP Server get_torrent_detail YouTube MCP Server search_channel Android Forensics ADB MCP Server parse_browser_history 0xarchive web3_challenge

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Data exfiltration → How read access becomes an exfiltration channel when chained with untrusted content.
MCP token cost → What connecting this server costs in context-window tokens on every request.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about receive_messages

What does the receive_messages tool do? +

How do I enforce a policy on receive_messages? +

Register the Brainstorm MCP server in PolicyLayer and add a rule for receive_messages: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Brainstorm. Nothing to install.

What risk level is receive_messages? +

receive_messages is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit receive_messages? +

Yes. Add a rate_limit block to the receive_messages rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block receive_messages completely? +

Set action: deny in the PolicyLayer policy for receive_messages. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides receive_messages? +

receive_messages is provided by the Brainstorm MCP server (theodorstorm/brainstorm-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Brainstorm tool call.

Start from Brainstorm, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →

Free to start. No card required.

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