record_run_observation · Blop MCP: Risk & Policy

WHAT IT DOES

What record_run_observation does on Blop

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

WHY IT NEEDS A POLICY

Why record_run_observation needs a policy

The tool writes (records) an observation tied to a run ID and observation key. Being idempotent means it creates or updates a record but does not irreversibly delete or execute code. It fits Write as it creates/modifies audit or QA data. Severity is medium because misuse could corrupt release confidence decisions, but the idempotent nature limits blast radius.

From the tool's definition 'Idempotent agent observation keyed by (run_id, observation_key)' — records/writes an observation entry associated with a run

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

record_run_observation Rate-limited

record_run_observation 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": {
    "record_run_observation": {
      "limits": [
        {
          "counter": "record_run_observation_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 Blop, so you can run agents against it safely.

FAQ

Questions about record_run_observation

What does the record_run_observation tool do? +

Idempotent agent observation keyed by (run_id, observation_key). It is categorised as a Write tool in the Blop MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on record_run_observation? +

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

What risk level is record_run_observation? +

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

Can I rate-limit record_run_observation? +

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

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

record_run_observation is provided by the Blop MCP server (n2400813g/blop-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.