• We’re releasingSlither-MCP, a new tool that augments LLMs with Slither’s unmatched static analysis engine. • Slither-MCP benefits virtually every use case for LLMs by exposing Slither’s static analysis API via tools, allowing LLMs to find critical code faster, navigate codebases more efficiently, and ultimately improve smart contract authoring and auditing performance. • How Slither-MCP works Slither-MCP is an MCP server that wraps Slither’s static analysis functionality, making it accessible through the Model Context Protocol. • It can analyze Solidity projects (Foundry, Hardhat, etc.) and generate comprehensive metadata about contracts, functions, inheritance hierarchies, and more. • When an LLM uses Slither-MCP, it no longer has to rely on rudimentary tools like grep andread_fileto identify where certain functions are implemented, who a function’s callers are, and other complex, error-prone tasks. • Because LLMs are probabilistic systems, in most cases they are only probabilistically correct.

Article Summaries:

  • Slither‑MCP Launches to Enhance Solidity LLM Workflows

The Slither team has released Slither‑MCP, a Model Context Protocol (MCP) server that exposes Slither’s static‑analysis engine to large language models (LLMs). By wrapping Slither’s API, the tool lets LLMs quickly locate contract code, identify callers and callees, and run Slither’s detector suite without relying on generic file‑search or grep calls. In a typical audit scenario, an LLM can simply request get_function_source to retrieve the exact implementation of a function such as ERC20.transfer(). The server supports Foundry, Hardhat, and other Solidity projects, and can be added to Claude Code or Cursor with minimal configuration. Slither‑MCP is AGPL‑v3 licensed, but dual licensing is now available for commercial use.

Sources: