"Exploring Cursor Tools for Interfacing with Local LLMs" matching MCP servers:

A MCP server to allow the LLM in Cursor to access Rust Analyzer, Crate Docs and Cargo Commands.

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 web search, content extraction, question answering, and RAG context generation using Tavily API with Cursor-compatible underscore-named tools.

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.

MCP server providing filesystem allowlist and pack-aware Qdrant RAG search. Enables reading files, listing directories, and performing filtered RAG searches with case and pack IDs.

A plugin that allows Dify to connect to multiple MCP (Model Control Protocol) servers using HTTP with Server-Sent Events transport, supporting custom configurations for URLs, headers, and timeouts.

Enables searching through vectorized Cursor IDE chat history via a FastAPI service powered by LanceDB and Ollama.

A local-first document retrieval MCP server that enables AI coding tools like Codex to search private local documents via semantic search and keyword boost, supporting ingestion of PDF, DOCX, TXT, Markdown, and HTML files.

Privacy-first local document search using semantic search. Runs entirely on your machine with no cloud services, supporting PDF, DOCX, TXT, and Markdown files.

Enables developers to index and search their own local PDF, DOCX, Markdown, and text documents from an MCP client or terminal, combining semantic similarity with keyword matching for exact technical terms. Everything runs on the user's machine with no API key, Docker, or external database, so private documents stay private and work offline after the initial model download.

A fully local RAG MCP server for semantic code search and code intelligence, using AST-level chunking and hybrid search to pinpoint functions, classes, and APIs. No cloud, no API keys, zero setup.

Generates DeepWiki-style documentation for private code repositories with RAG-based Q\&A capabilities, semantic code search, and multi-language AST parsing. Supports local LLMs (Ollama) or cloud providers for privacy-focused codebase analysis.

A local MCP server that indexes codebases using Tree-sitter AST parsing and LanceDB, enabling AI models to search across repositories with sub-second latency.

A local-first MCP server for PageIndex — the vectorless, reasoning-based RAG framework. It lets local AI agents index and query local PDF and Markdown documents through a self-hosted PageIndex installation, without requiring any PageIndex cloud API key.

Local-first temporal knowledge graph with six read-only MCP retrieval tools. Supports Ollama and embedded LadybugDB; additions use a separate CLI proposal queue with human approval and explicit application.

Enables MCP clients to administer a local LM Studio instance: loading, estimating, downloading, configuring and unloading models, running chat and embedding inference, diagnosing the server, engines and hardware, and managing MCP connectors with conflict-safe configuration. It also builds a local document index supporting citation-checked search and answers grounded in TXT, Markdown, PDF and DOCX files.

Enables cost-effective repository analysis, code search, file editing, and task planning by wrapping the cursor-agent CLI through focused tools. Reduces token usage by offloading heavy thinking tasks from Claude to specialized operations with configurable output formats.

MCP server for compressing AI embeddings by 5-7x using TurboQuant (PolarQuant + QJL), with tools to compress, decompress, estimate savings, and embed+compress vectors.