An MCP server that answers questions about TypeScript APIs using TypeDoc JSON documentation
An MCP server that answers questions about TypeScript APIs using TypeDoc JSON documentation
Large Language Models (LLMs) have made incredible strides in code generation and developer productivity. However, they face a key limitation: they can only reliably use APIs and libraries they’ve seen during training. This creates a bottleneck for adopting new tools, SDKs, or internal APIs — LLMs simply don’t know how to use them effectively.
Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.
{
"mcpServers": {
"typescribe": {
"command": "npx",
"args": [
"-y",
"mcp-typescribe@latest",
"run-server",
"<PATH_TO_API_DOT_JSON>"
],
"env": {}
}
}
}Configuration as documented by the project. Restart the client after saving.
Store entities, relations and observations in a local knowledge graph with the reference Memory MCP server.
A structured scratchpad for hard problems — stepwise reasoning with revisions, branches and visible logic.
Read Caper's wiki and DAO on-chain data; launch a DAO, trade, and propose on Radix testnet.
Disease Twin — Brazil's rare-disease knowledge graph (10,468) over MCP. Source-grounded, PT-BR.
Adaptive memory system for AI applications. Multi-strategy retrieval, cognitive scoring, knowledge graph, and self-improving ML. Connects via MCP or
Search 250M+ research papers, citations and author profiles. Free OpenAlex account; OAuth sign-in.