post_knowledge · AT MCP: Risk & Policy

WHAT IT DOES

What post_knowledge does on ATMcp

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

WHY IT NEEDS A POLICY

Why post_knowledge needs a policy

This tool creates/writes data (knowledge entries) in a multi-agent shared system with potential side effects: it populates a knowledge base that other agents can access and act upon. The severity is medium because while it modifies data reversibly (entries could theoretically be deleted/updated), in a distributed multi-agent system, unvetted or malicious knowledge could influence agent behavior across the network.

From the tool's definition Tool description states 'Share a finding' which creates new knowledge entries in a shared system. The deduplication logic ('Identical content...is auto-deduped') indicates persistent storage of posted content.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

post_knowledge Rate-limited

post_knowledge 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": {
    "post_knowledge": {
      "limits": [
        {
          "counter": "post_knowledge_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 ATMcp, so you can run agents against it safely.

FAQ

Questions about post_knowledge

What does the post_knowledge tool do? +

Share a finding. Identical content (same title/body/tags) is auto-deduped;. It is categorised as a Write tool in the ATMcp MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on post_knowledge? +

Register the AT MCP server in PolicyLayer and add a rule for post_knowledge: 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 ATMcp. Nothing to install.

What risk level is post_knowledge? +

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

Can I rate-limit post_knowledge? +

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

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

post_knowledge is provided by the AT MCP server (midcheck/atmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.