"Automating Testing and Debugging for LLMs in Production" matching MCP servers:

An MCP server that exposes the llms.txt file and its referenced local or external resources from a project root to provide context for AI models. It automatically parses documentation links and URLs to make them accessible as additional MCP resources.

Enables agents to discover the llms.txt index covering any site, fetch its linked documentation pages as markdown, and search across parsed indexes by section heading, link title, and notes.

Enables fast, token-efficient access to large documentation files in llms.txt format through semantic search. Solves token limit issues by searching first and retrieving only relevant sections instead of dumping entire documentation.

Enables Codex to rank available tools and skills, rerank code and documentation search results, and triage saved output artifacts using Jev-based relevance scoring while leaving final decisions to Codex.

A Model Context Protocol server that enables LLMs to interact directly with MongoDB databases, allowing users to query collections, inspect schemas, and manage data through natural language.

Serves plain-text notes that an Obsidian user has explicitly published for AI over streamable HTTP, with full-text and embedding-based search. MCP clients can read and search those notes and queue suggested edits that the user's own client applies only if the AI rules allow it.

A Model Context Protocol server that enables large language models to interact directly with Couchbase databases through natural language, supporting operations like querying buckets, performing CRUD operations, and executing N1QL queries.

All In One Model Context Protocol: qdrant, google suite (gmail, calendar, ...), jira, gitlab, CLI, ...

Enables any MCP-compatible AI assistant to search, filter, and retrieve information from a local document collection using a hybrid search pipeline with vector, BM25, reranking, and LLM enrichment.

An Operit-compatible adapter of the Exa MCP server, enabling web search, code search, and company research capabilities in AI assistants. It fixes MCP handshake compatibility issues, allowing tools like web_search_exa and web_fetch_exa to load and run reliably.

MCP for Azure DevOps Boards is a MCP server that lets your favourite AI browse, query and update Azure DevOps work items as if it were a project manager. Written in Rust and optimized for tokens usagem, It runs via stdio or HTTP mode and uses standard Azure authentication with az login.

Enables agents to optimize context-window attention by reordering retrieved documents so critical evidence lands at prompt boundaries, mitigating lost-in-the-middle degradation. It combines BM25 lexical scoring, dense vector similarity, reciprocal rank fusion, knowledge-graph expansion, and recency-decay memory caching, exposed as a zero-dependency MCP stdio server.

A proof of concept MCP server for Apache OFBiz

Enables agents to run hybrid retrieval, reciprocal rank fusion, knowledge graph expansion, semantic caching, and context reordering so critical evidence is placed at prompt boundaries to reduce lost-in-the-middle degradation.

WordPress plugin that runs an MCP server on your own site: search and read published posts and pages, look up WooCommerce products, describe the site as schema.org types and query site figures, with drafts only when the site enables them. Signed-in access by default; anonymous access and OAuth are optional and off.

An MCP server that enables users to fetch and audit documentation from user-defined llms.txt index files. It provides tools to list documentation sources and retrieve content from specific URLs with built-in domain access controls for secure context retrieval.

Enables asking questions and performing semantic searches against an Inkeep knowledge base. Deployable to Vercel with Next.js.

A production-grade MCP server and client implementation with comprehensive features including structured logging, health checks, metrics, authentication, and RAG capabilities with PostgreSQL vector search. Supports both stdio and SSE transports with containerization and security features for enterprise deployment.

Enables MCP host applications to retrieve and process structured documentation from user-defined llms.txt files. It provides tools to fetch specific URLs and audit the documentation context returned to the LLM.

A read-only MCP server providing curated Qdrant documentation for LLMs, enabling retrieval of the latest and most accurate documentation.

This MCP server provides a cost-optimized personal-knowledge brain, enabling AI agents to query imported documents via hybrid search and synthesis at minimal monthly spend.

An open-source MCP server that provides applications like Cursor, Windsurf, and Claude with access to llms.txt documentation files, allowing users to control and audit context retrieval.

Turns any static website into an MCP-searchable knowledge base by deploying a Cloudflare Worker that provides full-text search tools, enabling AI assistants to search and retrieve content from your site.

Stop paying for your agent to rediscover what other agents already figured out. Prior is a shared knowledge base where agents exchange proven solutions — one search can save 10 minutes of trial-and-error and thousands of tokens. Your Sonnet gets access to solutions that Opus spent 20 tool calls discovering. Search is free with feedback, and contributing earns credits.

Hebbian learning MCP server with neural memory graphs, eligibility traces, and three-factor reward signals. Associative memory that strengthens through use.

A TypeScript-based server to interact with ArangoDB using the Model Context Protocol, enabling database operations and integration with tools like Claude and VSCode extensions for streamlined data management.

An MCP server that exposes unified tools for HTTP requests, web search and fetching, weather/time/currency, file and SQLite sandboxes, GitHub, email, calendars, and a self-learning SQLite FTS5 knowledge base. It supports stdio, SSE, and streamable-HTTP transports with Bearer-token auth and SSRF protection so AstrBot agents can call these capabilities directly.

A workspace of six MCP servers—grounded-cv (hybrid RAG with citations), repo-intel (GitHub repo intelligence), web-research (safe web search/extraction), ats-jobs (unified ATS job boards), outcome-ledger (durable task ledger), and coding-workflows (code review & planning)—purpose-built for agentic hiring evaluations.

A custom MCP tool that integrates Perplexity AI's API with Claude Desktop, allowing Claude to perform web-based research and provide answers with citations.

A Python server implementing the Model Context Protocol to provide customizable prompt templates, resources, and tools that enhance LLM interactions in the continue.dev environment.

Enables AI agents to query Microsoft Entra data using natural language, converting requests into Microsoft Graph API calls for read-only enterprise IT scenarios.

Search a folder of documents and check answers against them. Offline: no API key or database.

A Model Context Protocol server that connects AI agents to Apache Jena, enabling them to execute SPARQL queries and updates against RDF data stored in Jena Fuseki.

Natural Language Analytics MCP server for Apache Druid. With this enterprise ready server in Java, one can query Apache Druid by natural language queries. Furthermore, the complete management like data loading of the Time Series Database Druid can be done with natural language commands.

Provides semantic search and complete document retrieval by ID through OpenAI's Vector Store API, letting deep research agents access company-specific knowledge and tools.

Enables users to ingest documents into a PostgreSQL/pgvector knowledge base, run semantic search over them, and get grounded answers through a retrieval-augmented generation pipeline backed by a free LLM. It also lets clients spin up specialized AI agents on demand and exposes knowledge-base stats and configuration as resources for tutoring workflows.

A Node In Layers package that simplifies creation of MCP (Model-Control-Protocol) servers with tools for defining models, adding CRUD operations, and interacting with clients.

Provides a standardized protocol for tool invocation, enabling an AI system to search the web, retrieve information, and provide relevant answers through integration with LangChain, RAG, and Ollama.

A local-first Graph-RAG system combining ChromaDB with metadata-based graph relationships and Gemini 2.5 Flash for intelligent Q&A over Obsidian vaults, supporting MCP clients like Claude Desktop, Cursor, and Raycast.

Enables accessing and managing personal/team internal knowledge repository with tools for semantic search, smart search, document listing, and saving information for future recall.