add_entity_observation · Sourcesage MCP: Risk & Policy

WHAT IT DOES

What add_entity_observation does on Sourcesage

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

WHY IT NEEDS A POLICY

Why add_entity_observation needs a policy

This tool creates or modifies observational data associated with a codebase entity within SourceSage's memory system. It is reversible (observations can be updated or removed via other tools like clear_knowledge), so it falls under Write rather than Destructive.

From the tool's definition Tool name contains 'add' and description states 'Add an observation to an entity', indicating creation or modification of data within the knowledge base.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

add_entity_observation Rate-limited

add_entity_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": {
    "add_entity_observation": {
      "limits": [
        {
          "counter": "add_entity_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 Sourcesage, so you can run agents against it safely.

FAQ

Questions about add_entity_observation

What does the add_entity_observation tool do? +

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

How do I enforce a policy on add_entity_observation? +

Register the Sourcesage MCP server in PolicyLayer and add a rule for add_entity_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 Sourcesage. Nothing to install.

What risk level is add_entity_observation? +

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

Can I rate-limit add_entity_observation? +

Yes. Add a rate_limit block to the add_entity_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 add_entity_observation completely? +

Set action: deny in the PolicyLayer policy for add_entity_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 add_entity_observation? +

add_entity_observation is provided by the Sourcesage MCP server (mcpflow/sourcesage). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.