"npm" matching MCP servers:

MCP server for the StitchAPI docs: search_docs (hybrid BM25+vector) + get_doc. Local/offline npm package (@stitchapi/docs-mcp, docs bundled, no per-query network) and a hosted Streamable-HTTP server (stitchapi.dev/api/mcp).

Provides intelligent, version-aware access to npm library documentation. Supports semantic search, API validation, and version comparison to assist developers in using libraries correctly.

An MCP server that enables coding agents to safely verify npm/PyPI packages, retrieve cited briefs, discover GitHub repos, and fetch canonical docs, with fail-closed OSV vulnerability checks and injection-hardened output.

Provides comprehensive management of OpenAI Vector Stores, allowing AI assistants to upload files, manage vector databases, and handle batch operations via the OpenAI API. It supports multiple deployment methods, including Cloudflare Workers and local NPM installation, for seamless integration with MCP-compatible clients.

Enables MCP clients to leverage the Intel Arrow Lake NPU for local speech transcription, screenshot OCR, private semantic search, and hardware diagnostics, all processed locally.

A powerful MCP server for fetching and transforming web content into various formats (HTML, JSON, Markdown, Plain Text) with ease.

Enables AI agents to consume 50+ NVIDIA NIM models including LLMs, image generation, and vision through 10 MCP tools with rich metadata and advanced filtering.

A codemode MCP server for fetching and querying dependency source code from npm, PyPI, crates.io, and GitHub. It allows agents to execute server-side JavaScript for context-efficient searching and browsing of large codebases without overwhelming the LLM's context window.

Enables AI agents to access 140+ NVIDIA NIM models for chat, embeddings, reranking, vision, image generation, OCR, and content safety via stdio.

A multi-agent product-management copilot that automates morning briefings, metrics answers, knowledge lookups over an Obsidian vault, and PRD/ticket drafting.