curate_context

THE RISK

Low Risk

Why curate_context needs a policy

With no description available, I can only infer from the tool name. 'Curate context' suggests gathering or organizing contextual information (likely codebase context) to pass to the AI model. This is most likely a Read operation, but given the server's purpose of connecting Gemini to Claude Code for generating plans and feedback, 'curate' could involve some selection/filtering.

From the tool's definition Tool name is 'curate_context' and description is empty or uninformative.

Documented attack patterns abuse exactly the kind of access curate_context gives an agent:

POLICY

How to control curate_context

PolicyLayer is an MCP gateway — it sits between your AI agents and Yellhorn MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for curate_context:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "curate_context": {
      "limits": [
        {
          "counter": "curate_context_rate",
          "window": "minute",
          "max": 60,
          "scope": "grant"
        }
      ]
    }
  }
}

curate_context gets a rate cap, and everything else on the server is denied unless you say otherwise.

Create a free account and register Yellhorn MCP — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

SET A RULE FOR THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Yellhorn MCP tools

Write create_workplan create_workplan Write revise_workplan revise_workplan Read get_workplan Retrieves the workplan content (GitHub issue body) for a specified issue number. Other judge_workplan judge_workplan

All 5 Yellhorn MCP tools →

Other tools on other servers

Android Forensics ADB MCP Server generate_app_analysis_report Ethereum Tools add Math MCP Server complex_analysis_suite Crypto_MCP aes_encrypt

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Tool risk categories → How PolicyLayer classifies MCP tools by what they can do.
MCP tool → What an MCP tool is and how clients discover and call it.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about curate_context

What does the curate_context tool do? +

curate_context. It is categorised as a Other tool in the Yellhorn MCP MCP Server, which means it performs auxiliary operations.

How do I enforce a policy on curate_context? +

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

What risk level is curate_context? +

curate_context is a Other tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit curate_context? +

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

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

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

Enforce policy on every Yellhorn MCP tool call.

Start from Yellhorn MCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →