"Testing Local AI Agents in LMStudio for Computer Use and Code Execution Tasks" matching MCP servers:

MCP server that analyzes codebases with tree-sitter and generates AGENTS.md files for AI agents.

Enables converting a public release-note URL into ordered upgrade tasks with source excerpts, anchors, confidence, and uncertainty, without executing release text or project code.

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

An MCP server that converts Cursor agent plans into structured markdown task lists and organizes them in your repository, helping you track AI-generated plans and recommendations as actionable specifications.

Enables AI agents to search and browse a curated catalog of 330+ third-party APIs and MCP servers using tools like search_apis, get_api, get_reviews, and list_categories, with no API key required.

Enables local document search and reading across formats like docx, pdf, md, and more, providing tools for listing, searching, and reading documents.

Searches Claude Code documentation via BM25 indexing, returning ranked snippets with category filtering. Enables fast, local search over official docs without full-document scans.

Built in rust, feature complete MCP server for self-hosted Docmost (Community Edition) — read & write your wiki from Claude, Cursor & VS

Automatically crawls documentation websites, converts them to organized markdown files, and generates condensed cheat sheets. Intelligently categorizes content into tools/APIs and provides local-first access to downloaded documentation.

Provides MCP tools to list and search OpenAI Agents SDK documentation, enabling LLMs to retrieve documentation topics and content via natural language queries.

An MCP server that provides static validation and documentation lookup for quantum computing libraries, currently supporting PennyLane. It allows users to verify quantum code syntax and method usage against official library documentation to ensure correct implementation.

Enables LLM clients to query local markdown engineering documentation by indexing files into ChromaDB with Ollama embeddings and exposing a search_internal_docs tool over stdio, all offline and privacy-first.

Provides AI agents with a governed, three-layer project memory (guide, code facts, and knowledge) through namespaced MCP tools for code search, context compilation, impact analysis, and proposal-driven documentation updates.

Local MCP server that provides verified answers about Jimmer and internal libraries using a SQLite FTS5 knowledge base.

Allows LLM tools like Claude Desktop and Cursor AI to access and summarize code files through a Model Context Protocol server, providing structured access to codebase content without manual copying.

Provides a compressed knowledge graph of the NVIDIA AI developer stack for deterministic traversal, enabling agents to answer questions about dependencies and prerequisites with minimal tokens.

High-performance code understanding toolkit that enables batch reading of multiple files with dependency context, structural outline extraction with Java annotation awareness, and precise location of classes/methods across large codebases.

Provides AI assistants with specialized tools to interact with NIST's Open Security Controls Assessment Language (OSCAL) framework. It enables agents to retrieve schemas, explore models, and generate valid OSCAL documentation for security compliance automation.

Connects to vibe-code-best-practices.vercel.app to index 817 tools across 185 sections and 10 domains, routes the right tool/Skill for your project need, and can recommend a full stack.

Facilitates searching and accessing programming resources across platforms like Stack Overflow, MDN, GitHub, npm, and PyPI, aiding LLMs in finding code examples and documentation.