link_clawmarks · Clawmarks MCP: Risk & Policy

WHAT IT DOES

What link_clawmarks does on Clawmarks

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

WHY IT NEEDS A POLICY

Why link_clawmarks needs a policy

This tool creates connections (edges) in a knowledge graph stored in a local JSON file. While it modifies state, the operation is reversible (clawmarks can be unlinked via delete_clawmark or unlink_clawmarks, and the modification affects only metadata bookmarks and their relationships, not the underlying codebase or critical system data). The blast radius is confined to the local annotation/documentation system.

From the tool's definition Tool description states it 'Create[s] a reference from one clawmark to another', which modifies the knowledge graph by adding an edge. The verb 'create' and the action of establishing a link is a reversible data modification operation.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

link_clawmarks Rate-limited

link_clawmarks 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": {
    "link_clawmarks": {
      "limits": [
        {
          "counter": "link_clawmarks_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 Clawmarks, so you can run agents against it safely.

FAQ

Questions about link_clawmarks

What does the link_clawmarks tool do? +

Create a reference from one clawmark to another (knowledge graph edge). It is categorised as a Write tool in the Clawmarks MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on link_clawmarks? +

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

What risk level is link_clawmarks? +

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

Can I rate-limit link_clawmarks? +

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

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

link_clawmarks is provided by the Clawmarks MCP server (mrilikecoding/clawmarks). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.