add_concept · Concept Tracker MCP: Risk & Policy

WHAT IT DOES

What add_concept does on Concept Tracker

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

WHY IT NEEDS A POLICY

Why add_concept needs a policy

This tool creates or modifies data (adds a new concept to the knowledge base) in a reversible manner. The operation is not destructive (no deletion), does not execute arbitrary code or external operations, and has no financial implications. The blast radius is low because adding a concept to a documentation/knowledge base has minimal downstream impact—it can be easily corrected via update_concept or delete_concept.

From the tool's definition Tool name 'add_concept' and description 'Manually add a new technical concept to the knowledge base' indicate creation of new data entries in a searchable knowledge base.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

add_concept Rate-limited

add_concept 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": {
    "add_concept": {
      "limits": [
        {
          "counter": "add_concept_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 Concept Tracker, so you can run agents against it safely.

FAQ

Questions about add_concept

What does the add_concept tool do? +

Manually add a new technical concept to the knowledge base. It is categorised as a Write tool in the Concept Tracker MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on add_concept? +

Register the Concept Tracker MCP server in PolicyLayer and add a rule for add_concept: 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 Concept Tracker. Nothing to install.

What risk level is add_concept? +

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

Can I rate-limit add_concept? +

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

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

add_concept is provided by the Concept Tracker MCP server (liwengggou/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.