Retrieve a published spec/contract by name.
AI agents call get_spec to retrieve information from Interagent without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool simply retrieves or queries existing specification/contract data by name. It does not create, modify, delete, execute commands, or trigger external operations. The action is purely informational with no side effects, placing it firmly in the Read category. Severity is low as misuse would only expose information already published in the system.
From the tool's definition Tool description states 'Retrieve a published spec/contract by name' — a retrieval operation with no side effects. The verb 'Retrieve' and the read-only nature of fetching an existing spec confirm this is a data query.
Attacks that exploit this kind of access
Retrieve a published spec/contract by name. It is categorised as a Read tool in the Interagent MCP Server, which means it retrieves data without modifying state.
Register the Interagent MCP server in PolicyLayer and add a rule for get_spec: 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 Interagent. Nothing to install.
get_spec 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 get_spec 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 get_spec. 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.
get_spec is provided by the Interagent MCP server (signalclaude/interagent). 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 →