send_thought · MCP Contemplation MCP: Risk & Policy

WHAT IT DOES

What send_thought does on MCP Contemplation

AI agents use send_thought to create or update resources in MCP Contemplation — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP Contemplation environment.

WHY IT NEEDS A POLICY

Why send_thought needs a policy

The tool writes/stores a thought into a background processing system, which is a reversible data creation operation. It does not execute arbitrary code, delete data, move money, or retrieve existing data—it adds new content. Severity is medium because an agent could flood the system with thoughts or inject misleading content into the contemplation loop, but the effects are not financially damaging or irreversible.

From the tool's definition Tool name 'send_thought' and description 'Send a thought for background processing' indicate the tool creates or modifies data (storing a thought in a contemplation system) without irreversible deletion or code execution.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

send_thought Rate-limited

send_thought stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "send_thought": {
      "limits": [
        {
          "counter": "send_thought_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches MCP Contemplation, so you can run agents against it safely.

FAQ

Questions about send_thought

What does the send_thought tool do? +

Send a thought for background processing. It is categorised as a Write tool in the MCP Contemplation MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on send_thought? +

Register the MCP Contemplation MCP server in PolicyLayer and add a rule for send_thought: 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 Contemplation. Nothing to install.

What risk level is send_thought? +

send_thought is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit send_thought? +

Yes. Add a rate_limit block to the send_thought 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 send_thought completely? +

Set action: deny in the PolicyLayer policy for send_thought. 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 send_thought? +

send_thought is provided by the MCP Contemplation MCP server (mikeybeez/mcp-contemplation). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.