"The most widely used models" matching MCP servers:

Index docs websites and local folders, then let Claude, Cursor, or any MCP client answer from the current docs, with a link to every section it used.

Enables read-only scanning and text extraction from PDF, DOCX, PPTX, SVG, and PNG files in a local folder, providing the raw text to AI models for summarization or analysis without an external LLM API.

Enables AI models to search, browse, and retrieve full content of OpenCode documentation pages.

Provides AI coding tools with queryable documentation for the AK (Active Kernel) event-driven MCU framework, including API signatures, guides, and guardrails.

Enables AI agents to search a local folder of Markdown, AsciiDoc, and text files through a SQLite FTS5 keyword index, returning the most relevant sections with file paths, line ranges, and heading breadcrumbs instead of grepping through a repo. It also exposes tools to list indexed documents and refresh the index incrementally, all offline with no dependencies, network calls, or embeddings.

Provides AI agents with access to a comprehensive database of 200+ Next.js documentation URLs for intelligent document selection and retrieval. Enables Claude and other AI assistants to analyze user queries and recommend the most relevant Next.js documentation pages.

Provides search and detail tools for YANG paths across network vendor models (Nokia, Cisco, Arista), enabling models to find correct gNMI paths without guessing. The server is offline and does not connect to any devices.

Enables AI models to search and retrieve offline security knowledge from over 20 curated sources including HackTricks, PayloadsAllTheThings, and OWASP guides, via the Model Context Protocol.

Provides a structured interface to the Japanese National Diet Library's parliamentary proceedings API, allowing AI models to search and retrieve Diet meeting records and speeches.

Enables AI assistants to fetch sourced, citable face measurement percentiles, face type definitions and threshold rules, methodology and citation details, and to classify a face shape from four distances using the site's seven rules in order. Read-only and takes no photo.

MCP server that recommends which npm/PyPI libraries to use or avoid, with concise verdicts, alternatives, and code snippets, keeping responses under 500 tokens.

Provides LLMs with real-time access to up-to-date documentation from PyPI, npm, crates.io, GoDocs, DockerHub, GitHub, and GCP, preventing outdated code generation and API hallucinations.

Converts Sphinx documentation (RST) to Markdown optimized for LLMs, enabling easy consumption of technical documentation by language models.

MCP server for the MST Chain ecosystem, enabling access to documentation, network info, smart contract guides, wallet balances, and transaction details via Web3.

It lets AI coding agents look up design tokens, component specifications, and prohibition rules on demand, then validate generated HTML or JSX with the same lint logic used by CI and editor hooks so violations are caught and corrected immediately. It also exposes the design constitution and rule sets as resources for reference during generation.

Automatically analyzes project dependencies to discover and download the most relevant documentation, enabling developers to quickly set up comprehensive project context.

Enables generating UI design rules, fetching color palettes, and retrieving brand design references from over 328 brands.

A Model Context Protocol Server that enables language models to access and manipulate Readwise documents and highlights programmatically.

A version-aware cache for web research that stores and serves documentation references, preventing models from re-researching the same topics across sessions.

Enables AI assistants to extract and document Mendix Studio Pro modules by interrogating local .mpr files. Generates comprehensive JSON documentation of domain models, pages, microflows, and enumerations without sending data to the cloud.