Deep MCP Server

Async deep research MCP server for AI agents and MCP clients with Brave, GitHub, Context7, and SQLite-backed local storage.

Local serverstdio

What is the Deep MCP server?

Async deep research MCP server for AI agents and MCP clients with Brave, GitHub, Context7, and SQLite-backed local storage. That is what the deep mcp server brings to an AI assistant: the same capability, reachable through the Model Context Protocol rather than a separate app or dashboard.

The short version

Async deep research MCP server for AI agents and MCP clients. It starts long-running research jobs, searches Brave/GitHub/Context7, fetches and cleans sources, stores chunks in local SQLite, and lets clients retrieve reports or targeted evidence without dumping every page into context.

The tools it exposes

The server publishes 5 tools. What each one is for:

  • research_start — research_status
  • research_report — research_sources
  • research_search — research_get_source
  • research_get_chunks — research_active_jobs
  • research_due_jobs — research_cancel

What it needs from you

Configuration is passed through the environment: BRAVE_API_KEY, GITHUB_TOKEN, CONTEXT7_API_KEY. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

Getting it running

Setup follows the usual MCP pattern — install or clone the server, register it in your client's configuration file, restart the client.

How it compares

Among the database access options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Deep's toolset — research_start, research_report, research_search and 2 more — is a fair guide to whether it matches your workflow. It is maintained by menesekinci; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against Deep's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.

Things to watch

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Available tools

ToolWhat it does
research_startresearch_status
research_reportresearch_sources
research_searchresearch_get_source
research_get_chunksresearch_active_jobs
research_due_jobsresearch_cancel

Configuration

VariableDescriptionRequired
BRAVE_API_KEYCredential the server authenticates with.Yes
GITHUB_TOKENCredential the server authenticates with.Yes
CONTEXT7_API_KEYCredential the server authenticates with.Yes

Example prompts to try

  • Use Deep to research start.
  • Use Deep to research report.
  • Use Deep to research search.

Frequently asked questions

It connects Deep to MCP-compatible AI assistants such as Claude and Cursor, exposing 5 tools (research_start, research_report, research_search, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Deep directly.