watch_messages

Block and wait for a message to arrive for this terminal. Returns as soon as a message is received or timeout is reached.

Server Mcp Terminal Share wu-yu-pei/mcp-terminal-share
Category Read
Risk class Low
Parameters 00 required

What watch_messages does on Mcp Terminal Share

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

Why watch_messages needs a policy

This tool is purely passive observation of inter-process messages on the local filesystem. It does not create, modify, delete, or execute anything; it only waits for and retrieves data that another terminal has sent. This is functionally equivalent to a polling/subscription read operation.

From the tool's definition Tool description states it 'Block and wait for a message to arrive' and 'Returns as soon as a message is received' — it passively retrieves/reads messages from a queue without modifying, deleting, or executing code.

Questions about watch_messages

What does the watch_messages tool do? +

Block and wait for a message to arrive for this terminal. Returns as soon as a message is received or timeout is reached. It is categorised as a Read tool in the Mcp Terminal Share MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on watch_messages? +

Register the Mcp Terminal Share MCP server in PolicyLayer and add a rule for watch_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 Mcp Terminal Share. Nothing to install.

What risk level is watch_messages? +

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

Can I rate-limit watch_messages? +

Yes. Add a rate_limit block to the watch_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 watch_messages completely? +

Set action: deny in the PolicyLayer policy for watch_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 watch_messages? +

watch_messages is provided by the Mcp Terminal Share MCP server (wu-yu-pei/mcp-terminal-share). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

// LOOK UP ANOTHER SERVER

Every MCP server has a record like this.

Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.

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

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.