cognify · cognee MCP server MCP: Risk & Policy

WHAT IT DOES

What cognify does on cognee MCP server

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

WHY IT NEEDS A POLICY

Why cognify needs a policy

This tool creates a new knowledge graph structure from provided text, which is a data creation/modification operation. It does not delete data, execute arbitrary code, or involve financial transactions. It is reversible in the sense that the sibling 'prune' tool likely removes the knowledge graph.

From the tool's definition "Build knowledge graph from the input text"

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

cognify Rate-limited

cognify 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": {
    "cognify": {
      "limits": [
        {
          "counter": "cognify_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 cognee MCP server, so you can run agents against it safely.

FAQ

Questions about cognify

What does the cognify tool do? +

Build knowledge graph from the input text. It is categorised as a Write tool in the cognee MCP server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on cognify? +

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

What risk level is cognify? +

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

Can I rate-limit cognify? +

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

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

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