Plugins

The Captain MCP server exposes 19 tools to any Model Context Protocol client — Claude Code, Cursor, Windsurf, and others.

What you get

Search & collections: captain_search, captain_list_collections, captain_create_collection, captain_delete_collection, captain_list_documents, captain_delete_document, captain_wipe_documents

Indexing: captain_index_url, captain_index_youtube, captain_index_text, captain_index_file (local paths, multipart upload), captain_index_s3, captain_index_gcs, captain_index_azure, captain_index_r2

Jobs: captain_job_status, captain_cancel_job

Live project search:

• captain_save — save a short note (decision, gotcha, bug repro, design constraint) to a per-project collection with a timestamped filename. Auto-creates the collection on first use.
• captain_find — semantic search over saved notes; timestamps are surfaced so stale notes are obvious.

Credentials

Set these once in your shell (every client reads them the same way):

$
export CAPTAIN_API_KEY=cap_...
$
export CAPTAIN_ORGANIZATION_ID=019a...

Get an API key at runcaptain.com/studio.

Install — Claude Code

Add to ~/.claude.json (user scope) or a project .claude.json:

1
{
2
  "mcpServers": {
3
    "captain": {
4
      "command": "npx",
5
      "args": ["-y", "@captain-sdk/captain-mcp@latest"],
6
      "env": {
7
        "CAPTAIN_API_KEY": "${CAPTAIN_API_KEY}",
8
        "CAPTAIN_ORGANIZATION_ID": "${CAPTAIN_ORGANIZATION_ID}"
9
      }
10
    }
11
  }
12
}

Restart Claude Code. /mcp shows captain connected.

Install — Cursor

Add to .cursor/mcp.json (project) or ~/.cursor/mcp.json (global):

1
{
2
  "mcpServers": {
3
    "captain": {
4
      "command": "npx",
5
      "args": ["-y", "@captain-sdk/captain-mcp@latest"],
6
      "type": "stdio",
7
      "env": {
8
        "CAPTAIN_API_KEY": "${env:CAPTAIN_API_KEY}",
9
        "CAPTAIN_ORGANIZATION_ID": "${env:CAPTAIN_ORGANIZATION_ID}"
10
      }
11
    }
12
  }
13
}

Or use Settings → Tools & MCP → New MCP Server and paste the inner object.

Install — any other MCP client

1
{
2
  "mcpServers": {
3
    "captain": {
4
      "command": "npx",
5
      "args": ["-y", "@captain-sdk/captain-mcp@latest"],
6
      "env": {
7
        "CAPTAIN_API_KEY": "cap_...",
8
        "CAPTAIN_ORGANIZATION_ID": "019a..."
9
      }
10
    }
11
  }
12
}

Usage

> Search runcaptain-docs for how scientific/medical/ask streaming works
> Index c:\Users\me\reports\q4.pdf into finance-docs
> Index this YouTube video into training: https://youtube.com/watch?v=...
> Save this to runcaptain-notes: Decided Lambda over CF Worker — NCBI doesn't IP-rate-limit
> What did we decide about PubMed proxying?

Optional: agent guidance

Drop a rule file in your repo so the agent reaches for Captain automatically:

Cursor — .cursor/rules/captain.mdc:

1
---
2
description: Prefer Captain MCP tools — captain_search over grep/WebFetch for indexed material, captain_save/captain_find for cross-session notes.
3
alwaysApply: false
4
---
5
6
When searching docs or recalling past decisions, prefer captain_search, captain_save, and captain_find over grep/WebFetch. Use the repo basename as the collection; captain_save auto-creates it.

Claude Code — add the same text to CLAUDE.md in the repo root.

Links

• npm package
• Source on GitHub
• Model Context Protocol