"File system augmented tools for deep research" matching MCP servers:

An open-source deep research MCP server that provides multi-source web search and synthesis with citations, enabling agents to perform citation-backed research using Qwen3-30B-A3B-Thinking and other models.

A deep-research MCP server exposing a single task-augmented tool that runs GPT-Researcher with Tavily search, Anthropic Claude, and OpenAI embeddings, streaming progress via MCP tasks and Upjack entity stream.

A read-only FastMCP server for academic research that lets agents search papers, inspect metadata, follow citation graphs, generate BibTeX, and read full texts of open-access PDFs via semantic scholar, OpenAlex, arXiv, DBLP, and Crossref.

45-tool MCP server for video analysis, deep research, content extraction, web search, and Weaviate knowledge storage. Powered by Gemini 3.1 Pro.

Local-first filesystem MCP bridge with ripgrep search, atomic writes, multiple transports

Enables fast file search on macOS using the native mdfind (Spotlight) command, with support for filtering, regex, sorting, and limiting results.

AI-operable research workspace integrating Zotero, Obsidian, and NotebookLM. Search papers (arXiv/Semantic Scholar/PubMed/CrossRef), ingest into Zotero, sync per-paper notes to Obsidian, verify NotebookLM briefs. All three external tools optional.

Enables natural-language search over locally indexed files such as markdown, text, images, videos, and PDFs, and retrieves indexed text or media metadata by path. It lets Cursor query a local embedding index built with Gemini and SQLite.

An MCP server that enables saving, retrieving, and managing research content using ChromaDB vector storage and semantic search.

Enables AI agents to search videos, retrieve metadata and transcripts, pinpoint exact moments via hybrid semantic search, and conduct multi-video research with timestamp deep links—all without YouTube API keys.

MCP server for AI-powered research using Gemini. Provides fast grounded web search, deep autonomous research, URL extraction, and session management.

Enables declarative FDTD validation, guarded cloud-task workflows, and normalization of Tidy3D simulation results into metadata and bounded CSV observables, while keeping credentials and cloud-execution privileges isolated.

MCP server that searches 9 sources, scrapes full content, reranks results, and synthesizes cited answers with free LLMs.

Unifies YouTube transcripts, YouTube search, and Google NotebookLM into a research pipeline for Claude Desktop and MCP clients.

Domain-Driven MCP server for ed-tech workflows, exposing validated MCP tools backed by LangGraph agents, Supabase document retrieval, web search, and YouTube video discovery.

Enables AI assistants to research YouTube videos by collecting captions, comments, and channel information for analysis and comparison.

A lightweight MCP server providing common utility tools such as unit conversion, password generation, date calculation, hashing, Base64 encoding/decoding, UUID generation, text case conversion, and text statistics, with no external dependencies.

Enables inspecting local OpenAPI specification files by listing and retrieving spec details with filters and $ref resolution.

Search and resolve MCP server packages on the mpak registry, enabling agents to discover servers, inspect tools, and check credential requirements before installation.

Enables natural-language interaction with Ladybug Tools for building performance simulation, 3D modeling, and data visualization, allowing agents to perform complex environmental analysis tasks without CAD software.