Fetch onboarding + join manifests.
AI agents call chorus_join to retrieve information from Chorus field without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves onboarding and join manifests for agents registering with the chorus field server. It is a read-only operation that queries existing data without creating, modifying, deleting, or executing arbitrary operations. The blast radius of misuse is minimal—an agent could fetch manifests it shouldn't access, but no irreversible actions or financial impact is possible.
From the tool's definition Tool name 'chorus_join' with description 'Fetch onboarding + join manifests' performs a retrieval operation. The verb 'Fetch' and the context of reading manifests indicate a query/retrieval action with no side effects or data modification.
Attacks that exploit this kind of access
Fetch onboarding + join manifests. It is categorised as a Read tool in the Chorus field MCP Server, which means it retrieves data without modifying state.
Register the Chorus field MCP server in PolicyLayer and add a rule for chorus_join: 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 Chorus field. Nothing to install.
chorus_join 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 chorus_join 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 chorus_join. 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.
chorus_join is provided by the Chorus field MCP server (luisprimecore/chorus-field-mcp). 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 →