Docsearch MCP Server

MCP server and CLI tool for local document search with hybrid semantic+keyword search across PDFs, files, and Confluence

Local serverstdioTypeScript

What is the Docsearch MCP server?

MCP server and CLI tool for local document search with hybrid semantic+keyword search across PDFs, files, and Confluence. That is what the docsearch 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

A local-first document search and indexing system that provides hybrid semantic + keyword search across local files (including PDFs) and Confluence pages through the Model Context Protocol (MCP). Perfect for AI assistants like Claude Code/Desktop to access your documentation, codebase, and research materials.

The tools it exposes

The server publishes 2 tools. What each one is for:

  • source — Source to ingest: files, confluence, or all (default: all)
  • Flag — Environment Variable

Getting it running

The server ships on npm as npx, so your MCP client can launch it on demand — there is no separate build step. Add the server block to your client's configuration, restart it, and the tools register themselves.

What it needs from you

Configuration is passed through the environment: OPENAI_API_KEY, CONFLUENCE_BASE_URL, CONFLUENCE_API_TOKEN, ONLYOFFICE_URL, ONLYOFFICE_JWT_SECRET, DOCLING_URL, WHISPER_API_KEY, WHISPER_BASE_URL. 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.

How it compares

Among the developer tooling 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. Docsearch's toolset — source, Flag — is a fair guide to whether it matches your workflow. It is maintained by GitHub Actions; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against Docsearch'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
sourceSource to ingest: files, confluence, or all (default: all)
FlagEnvironment Variable

How to install the Docsearch MCP server

{
  "mcpServers": {
    "docsearch": {
      "command": "npx",
      "args": ["docsearch-mcp", "start"]
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

VariableDescriptionRequired
OPENAI_API_KEYCredential the server authenticates with.Yes
CONFLUENCE_BASE_URLEndpoint or connection string the server talks to.Yes
CONFLUENCE_API_TOKENCredential the server authenticates with.Yes
ONLYOFFICE_URLEndpoint or connection string the server talks to.Yes
ONLYOFFICE_JWT_SECRETCredential the server authenticates with.Yes
DOCLING_URLEndpoint or connection string the server talks to.Yes
WHISPER_API_KEYCredential the server authenticates with.Yes
WHISPER_BASE_URLEndpoint or connection string the server talks to.Yes

Example prompts to try

  • Use Docsearch to source.
  • Use Docsearch to Flag.

Frequently asked questions

It connects Docsearch to MCP-compatible AI assistants such as Claude and Cursor, exposing 2 tools (source, Flag) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Docsearch directly.