AI agents call search_spec to retrieve information from Prosuite without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears designed to search or retrieve specification information from the ProSuite quality verification system. Given the absence of explicit side effects in the name, the context of a verification/quality-checking tool, and the read-only nature of sibling tools like 'load_spec' and 'describe_spec', this is classified as a Read operation with low severity.
From the tool's definition Tool name 'search_spec' suggests searching/querying specification data. Context shows this MCP server performs quality verification checks on geospatial datasets.
Attacks that exploit this kind of access
search_spec. It is categorised as a Read tool in the Prosuite MCP Server, which means it retrieves data without modifying state.
Register the Prosuite MCP server in PolicyLayer and add a rule for search_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 Prosuite. Nothing to install.
search_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 search_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 search_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.
search_spec is provided by the Prosuite MCP server (prosuite/prosuite-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 →