contribute_knowledge · WAKE Protocol MCP: Risk & Policy

WHAT IT DOES

What contribute_knowledge does on WAKE Protocol

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

WHY IT NEEDS A POLICY

Why contribute_knowledge needs a policy

An AI agent can call contribute_knowledge faster than any human can review — one bad instruction and it creates or modifies resources in WAKE Protocol by the hundred, each call as confident as the last.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

contribute_knowledge Rate-limited

contribute_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": {
    "contribute_knowledge": {
      "limits": [
        {
          "counter": "contribute_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 WAKE Protocol, so you can run agents against it safely.

FAQ

Questions about contribute_knowledge

What does the contribute_knowledge tool do? +

Add a knowledge entry to the Black Box. Requires master token. Only in ACTIVE phase. Categories: finances, contacts, accounts, documents, decisions, commitments, medical, other. It is categorised as a Write tool in the WAKE Protocol MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on contribute_knowledge? +

Register the WAKE Protocol MCP server in PolicyLayer and add a rule for contribute_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 WAKE Protocol. Nothing to install.

What risk level is contribute_knowledge? +

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

Can I rate-limit contribute_knowledge? +

Yes. Add a rate_limit block to the contribute_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 contribute_knowledge completely? +

Set action: deny in the PolicyLayer policy for contribute_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 contribute_knowledge? +

contribute_knowledge is provided by the WAKE Protocol MCP server (wake-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.