AI agents call harness_describe to retrieve information from Loom without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns information about the current harness state without modifying any data. It is purely informational/diagnostic in nature, similar to introspection or status-checking commands. The 'write its manifest' phrasing refers to outputting the manifest description, not persisting changes. No data is created, modified, deleted, or irreversibly altered.
From the tool's definition The tool 'harness_describe' performs a self-description operation that 'write[s] its manifest' from the currently connected harness.
Attacks that exploit this kind of access
Self-describe the CURRENTLY CONNECTED harness: write its manifest at. It is categorised as a Read tool in the Loom MCP Server, which means it retrieves data without modifying state.
Register the Loom MCP server in PolicyLayer and add a rule for harness_describe: 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 Loom. Nothing to install.
harness_describe is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the harness_describe 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.
Set action: deny in the PolicyLayer policy for harness_describe. 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.
harness_describe is provided by the Loom MCP server (jbarket/loom). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →