ingest_perf_results · Orihime MCP: Risk & Policy

WHAT IT DOES

What ingest_perf_results does on Orihime

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

WHY IT NEEDS A POLICY

Why ingest_perf_results needs a policy

The name 'ingest_perf_results' implies writing or importing performance result data into the knowledge graph or database. 'Ingest' is a write operation. However, since the description is empty, confidence is low. It could also be an Execute if it triggers analysis pipelines. Given the context of a code knowledge graph server, the most likely interpretation is writing performance data into the embedded KuzuDB store.

From the tool's definition Tool name 'ingest_perf_results' suggests ingesting (writing/importing) performance results into the system. Description is empty and uninformative.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

ingest_perf_results Rate-limited

ingest_perf_results 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": {
    "ingest_perf_results": {
      "limits": [
        {
          "counter": "ingest_perf_results_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 Orihime, so you can run agents against it safely.

FAQ

Questions about ingest_perf_results

What does the ingest_perf_results tool do? +

ingest_perf_results. It is categorised as a Write tool in the Orihime MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on ingest_perf_results? +

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

What risk level is ingest_perf_results? +

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

Can I rate-limit ingest_perf_results? +

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

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

ingest_perf_results is provided by the Orihime MCP server (srinivasan-sundaresan95/orihime). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.