The shortlist
Models train on a snapshot; your dependencies don't stop moving. Two MCP servers fix the two halves of this — current library docs, and real web search — and a third lets you self-host the search side entirely.
61k stars · Open source · TypeScript
Feeds MCP clients current, version-correct library documentation — the highest-adopted docs server in the index, and the difference between the agent guessing an API and reading it.
— Your stack is niche enough that its docs are not covered.
4.9k stars · Open source · TypeScript
Search built for AI consumption, exposed over MCP — one config entry gives your agent a real search tool instead of stale training data.
1.2k stars · Open source · TypeScript
MCP bridge to SearXNG, the self-hosted meta-search engine — web search for your agent with no third-party API and no query logs leaving your infrastructure.
Every retrieval tool you add widens what the agent reads — and web content is untrusted input. Prefer read-only search/docs servers, and treat 'the agent found it online' with the same skepticism you'd give any unverified source.
