AI agents call load_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 to fetch or load specification data for the ProSuite quality verification system. With no evidence of side effects, modification, or execution capabilities, this is best classified as a Read operation. The empty description and context of sibling tools (which include 'describe_spec', 'list_conditions', 'run_verification') suggest load_spec retrieves specification objects for inspection.
From the tool's definition Tool name 'load_spec' suggests retrieving or loading a specification object. The empty description limits certainty, but 'load' typically indicates a read operation that retrieves data without modification.
Attacks that exploit this kind of access
load_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 load_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.
load_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 load_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 load_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.
load_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 →