write_research · Pelaris MCP: Risk & Policy

WHAT IT DOES

What write_research does on Pelaris

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

WHY IT NEEDS A POLICY

Why write_research needs a policy

This tool creates or modifies research cache entries within the Pelaris fitness coaching system. While the operations are reversible (can be updated again or deleted via sibling tools like delete_session), they modify user data. The blast radius is medium because corrupted or malicious research cache entries could mislead fitness coaching outputs, but the data itself is not financial and can be corrected.

From the tool's definition Tool description states 'Write or update a research cache entry. Creates a new document or updates an existing one by ID.' The verbs 'write,' 'update,' and 'creates' indicate reversible modification operations.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

write_research Rate-limited

write_research 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": {
    "write_research": {
      "limits": [
        {
          "counter": "write_research_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 Pelaris, so you can run agents against it safely.

FAQ

Questions about write_research

What does the write_research tool do? +

Write or update a research cache entry. Creates a new document or updates an existing one by ID. It is categorised as a Write tool in the Pelaris MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on write_research? +

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

What risk level is write_research? +

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

Can I rate-limit write_research? +

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

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

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