Search for proofs in the library. Full-text search with filtering by system, tags, author, and success rate. Supports multiple sorting options for optimal retrieval. Features: - Full-text search across names, descriptions, premises, and conclusions - Filter by logical system, tags, author - Sort ...
AI agents call logic-proof-search to retrieve information from Logic-Thinking MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves existing proofs from a library without creating, modifying, deleting, or executing any logic systems. It is a pure read operation with no side effects. The blast radius of misuse is minimal—an agent could access unwanted proof metadata but cannot alter logical reasoning, financial systems, or external state.
From the tool's definition Tool performs "Full-text search" and "retrieval" with "filtering" and "sorting" capabilities. Description explicitly states search, filter, and retrieval operations with no mutation, deletion, or execution of proofs.
Attacks that exploit this kind of access
Search for proofs in the library. Full-text search with filtering by system, tags, author, and success rate. Supports multiple sorting options for optimal retrieval. Features: - Full-text search across names, descriptions, premises, and conclusions - Filter by logical system, tags, author - Sort by relevance, usage, date, or success rate - Pagination support. It is categorised as a Read tool in the Logic-Thinking MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Logic-Thinking MCP Server MCP server in PolicyLayer and add a rule for logic-proof-search: 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 Logic-Thinking MCP Server. Nothing to install.
logic-proof-search 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 logic-proof-search 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 logic-proof-search. 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.
logic-proof-search is provided by the Logic-Thinking MCP Server MCP server (quanticsoul4772/logic-thinking). 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 →