MCP

Connect your AI to AudioMap

In 3 steps, your favorite AI can search, read and summarize your transcribed voice notes. Works in Claude, ChatGPT, Claude Code, Cursor, and any MCP-compatible tool.

Go to MCP dashboardSee per-platform guides

Connect your AI

Pick where you work and paste what we give you. It takes under a minute.

  1. Open claude.ai and go to Settings, Connectors.
  2. Click Add custom connector.
  3. Paste the URL below and click Add.
  4. Authorize with your AudioMap account on the screen that appears.
Server URL
https://mcp.audiomap.ai
Read the docs

One-click install

The editor adds the server and asks you to sign in to AudioMap the first time. No keys to copy.

Add to CursorAdd to VS Code

Ask your AI

Paste this into your assistant (Claude, ChatGPT, Gemini…): it reads the address and walks you through your client.

https://mcp.audiomap.ai Install this as an MCP connector and tell me the exact steps for my AI client.

Three ways to use it

From trying it without signing up to full access with your personal library.

No signup

Public demo

Try AudioMap MCP without an account. Demo dataset, rate-limited.

  • ✓No signup, no token
  • ✓10 requests per IP every 10 min
  • ✓Limited read tools
  • ✓Ideal to evaluate before signing up
https://mcp.audiomap.ai/demo
€0 · Free

Free account

Your own notes library. Full read, write within plan credits.

  • ✓300 transcription minutes / month
  • ✓Full read tools (free)
  • ✓Write tools using your credits
  • ✓50 write credits per month
  • ✓3 active MCP connections
Create free account →
From €19/mo

Pro / Power

Generous credits, REST API and processing priority.

  • ✓3,600 minutes / month (Pro)
  • ✓REST API access (Pro+)
  • ✓No overage: 402 when exhausted
  • ✓Priority support
  • ✓Up to 10 MCP connections at once (20 on Power)
See plans →

Quick start, 3 steps

1

Create a persistent API key at /dashboard/api-keys (recommended) or a session token at /dashboard/mcp.

2

Copy the generated "connection prompt" for your AI. Works in Claude, ChatGPT, Claude Code and more.

3

Paste it into your AI. It configures itself and shows you what to ask.

Generate my connection prompt

Per-platform guides

Specific instructions for each AI

🤖Claude.aiEasy+
  1. 1Open Claude.ai and go to Settings
  2. 2Click "Connectors"
  3. 3Click "Add custom connector"
  4. 4Paste the URL: https://mcp.audiomap.ai
  5. 5Enter your am_live_* Bearer token when prompted
  6. 6Save, done!
💬ChatGPTPaid plans only+
Requires ChatGPT Plus, Pro, Team, or Enterprise. The free plan does not support MCP servers.
  1. 1Open ChatGPT and go to Settings (gear icon)
  2. 2Go to Apps & Connectors
  3. 3Enable "Developer Mode"
  4. 4Click "Create connector"
  5. 5Name it "AudioMap"
  6. 6Paste the server URL: https://mcp.audiomap.ai
  7. 7Select Bearer token authentication and paste your am_live_* token
⌨️Claude CodeCLI+
Claude Code does NOT read mcpServers from settings.json. Use the claude mcp add command (recommended) or create .mcp.json at the project root.
  1. 1Open your terminal in any project where you use Claude Code
  2. 2Run: claude mcp add --transport http -s user audiomap <URL> --header "Authorization: Bearer <TOKEN>"
  3. 3Replace <URL> and <TOKEN> with values from your dashboard
  4. 4Restart the Claude Code session
  5. 5Ask: "list my latest audiomap notes"

Recommended command (whole machine)

claude mcp add --transport http -s user audiomap https://mcp.audiomap.ai --header "Authorization: Bearer <YOUR_TOKEN>"

Alternative: .mcp.json in the project

{
  "mcpServers": {
    "audiomap": {
      "type": "http",
      "url": "https://mcp.audiomap.ai",
      "headers": {
        "Authorization": "Bearer <YOUR_TOKEN>"
      }
    }
  }
}
🛠️Claude Desktop, Cursor, VS CodeAdvanced+
These tools use a JSON configuration file. Paste the mcpServers block in the corresponding path.

Paths:

  • Claude Desktop: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Cursor: .cursor/mcp.json
  • VS Code: .vscode/mcp.json
  • Claude Code: .mcp.json (or use claude mcp add)
{
  "mcpServers": {
    "audiomap": {
      "type": "http",
      "url": "https://mcp.audiomap.ai",
      "headers": {
        "Authorization": "Bearer <YOUR_TOKEN>"
      }
    }
  }
}
✨GeminiNot supported+
Gemini web/app does not support connecting custom MCP servers. If you use Gemini CLI you can do it programmatically; see its documentation.

Connect your local AI

Claude Desktop, Cursor, LM Studio and Open WebUI (Ollama) talk to AudioMap through the same MCP server.

With this your AI can ask AudioMap to import a YouTube video or a podcast and analyze it: the import_from_url tool (replaces upload_audio_url) accepts YouTube, podcast RSS, Apple Podcasts and direct audio or video URLs.

Replace <YOUR_TOKEN> with your persistent API key (am_live_...) from /dashboard/api-keys. It travels in the Authorization header as Bearer.
🖥️Claude Desktop~/Library/Application Support/Claude/claude_desktop_config.json+

Open Claude Desktop, Settings, Developer, Edit Config, and paste the block. Claude Desktop launches servers by command, so the mcp-remote bridge translates to HTTP (requires Node.js). Restart Claude Desktop.

{
  "mcpServers": {
    "audiomap": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://mcp.audiomap.ai",
        "--header",
        "Authorization: Bearer <YOUR_TOKEN>"
      ]
    }
  }
}
⌨️Cursor.cursor/mcp.json+

Create .cursor/mcp.json in your project (or ~/.cursor/mcp.json for all projects) with this content. In Cursor, Settings, MCP, the audiomap server shows up green.

{
  "mcpServers": {
    "audiomap": {
      "type": "http",
      "url": "https://mcp.audiomap.ai",
      "headers": {
        "Authorization": "Bearer <YOUR_TOKEN>"
      }
    }
  }
}
🧪LM Studiomcp.json+

In LM Studio open the Program tab (plug icon), click Install, Edit mcp.json and paste the block. Use a model with tool calling (Qwen, Llama 3.1 or similar) so it can call the tools.

{
  "mcpServers": {
    "audiomap": {
      "type": "http",
      "url": "https://mcp.audiomap.ai",
      "headers": {
        "Authorization": "Bearer <YOUR_TOKEN>"
      }
    }
  }
}
🦙Open WebUI (Ollama)+

In Open WebUI go to Admin Panel, Settings, External Tools, Add; choose the MCP (Streamable HTTP) type, paste the server URL and under Auth pick Bearer with your API key. Ollama provides the model; enable the tool in the chat.

URL: https://mcp.audiomap.ai
Auth: Bearer
Header: Authorization: Bearer <YOUR_TOKEN>

Example: import and analyze from your AI

Import https://www.youtube.com/watch?v=... with import_from_url, wait until it finishes and give me a summary with the decisions and the tasks.

Available tools

14 tools total. Read tools are free; write tools consume credits.

search_notes

Search notes by text (title, description, transcript).

list_recent_notes

Last N notes with metadata.

get_note

Full note: transcript + AI summary + highlights.

get_transcript_segments

Segments with timestamps and speakers.

get_transcript_translation

Transcript translated into another language, per segment and cached.

list_folders

Folders with note count.

list_highlights

Highlighted fragments of a note.

get_outline

Auto-generated chapters with timestamps.

import_from_url

Import from a link: YouTube, podcast RSS, Apple Podcasts or direct URL. 50 credits/min.

wait_for_transcription

Polling with timeout until status ready.

generate_ai_notes

Templates: meeting, sales, legal, medical… 100 cred.

generate_outline

Outline/chapters with AI. 50 cred.

replace_in_transcript

Literal search & replace over the transcript. Free.

suggest_speaker_names

Suggests the real name of each speaker from what is said, the title and the channel. Free.

rename_speaker

Names a speaker or confirms the suggested name. Free.

list_voice_profiles

Lists your voice profiles and whether voice recognition is on. Read-only. Free.

founder_status

Describes whether your account is a founder one and how its commitment is going. Read-only. Free.

ask_note

Ask about a note (RAG + timestamps). 10 cred.

extract_clip

Extract MP3 clip from a range. 1h presigned URL. 5 cred.

Full descriptions and annotations: https://mcp.audiomap.ai/mcp/info

Ready to connect your AI?

Generate your personalized connection prompt in one click. Your AI does the rest.

Go to MCP dashboardCreate persistent API key
Connect your AI to AudioMap | MCP setup guide