Execute a proof using the current session
AI agents invoke prove_session to trigger actions in FOL Prover MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool executes external prover processes whose behavior depends on the formulas and premises in the current session. While theorem proving itself is deterministic and non-destructive, the 'Execute' category applies because the tool runs code/external operations whose effects depend on arguments (the session's formulas and premises).
From the tool's definition Tool name 'prove_session' and description 'Execute a proof using the current session' directly indicate code execution.
Attacks that exploit this kind of access
Execute a proof using the current session. It is categorised as a Execute tool in the FOL Prover MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the FOL Prover MCP Server MCP server in PolicyLayer and add a rule for prove_session: 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 FOL Prover MCP Server. Nothing to install.
prove_session is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the prove_session 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 prove_session. 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.
prove_session is provided by the FOL Prover MCP Server MCP server (newjerseystyle/folprover-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 →