Speak AI
Search recordings, summarize meetings, create clips, and automate workflows from your AI assistant.
Search recordings, summarize meetings, create clips, and automate workflows from your AI assistant.
Use this profile to copy client config, check auth requirements, review tools and resources, and compare related MCP servers before adding it to an AI client.
https://api.speakai.co/v1/mcpnpx -y @speakai/mcp-server{
"SPEAK_API_KEY": "YOUR_SECRET_VALUE",
"SPEAK_BASE_URL": "https://api.speakai.co"
}Add this server entry to the mcpServers object in your Claude Desktop config, then restart the app.
{
"mcpServers": {
"io-github-speakai-mcp-server": {
"command": "npx",
"args": [
"-y",
"@speakai/mcp-server"
],
"env": {
"SPEAK_API_KEY": "YOUR_SECRET_VALUE",
"SPEAK_BASE_URL": "https://api.speakai.co"
}
}
}
}~/Library/Application Support/Claude/claude_desktop_config.json%APPDATA%\Claude\claude_desktop_config.jsonNo remote HTTP endpoint is advertised. Use the package or stdio setup shown in Install.
Speak AI is an MCP server for Search recordings, summarize meetings, create clips, and automate workflows from your AI assistant.. It supports STDIO, HTTP transport.
Use the generated config in Install. This server runs with npx -y @speakai/mcp-server; add any required environment variables before starting your client.
Choose the Claude Desktop tab in Install, copy the config, and add it to Claude Desktop's MCP server settings. Endpoint: https://api.speakai.co/v1/mcp.
Choose the Claude Code tab in Install, copy the config, and add it to Claude Code's MCP server settings. Endpoint: https://api.speakai.co/v1/mcp.
Choose the Codex tab in Install, copy the config, and add it to Codex's MCP server settings. Endpoint: https://api.speakai.co/v1/mcp.
Choose the Cursor or VS Code tab in Install, copy the config, and add it to Cursor or VS Code's MCP server settings. Endpoint: https://api.speakai.co/v1/mcp.
Speak AI uses STDIO, HTTP transport. Endpoint: https://api.speakai.co/v1/mcp.
Speak AI inventory is listed when the MCP endpoint exposes tools, resources, or prompts. Some servers require auth first.
Speak AI is marked with Auth required by registry metadata auth. You may need provider login, an API key, a bearer token, or a session header.
| Package | Registry | Version | Inputs |
|---|---|---|---|
@speakai/mcp-serverstdio | npm | 1.9.0 | Env: SPEAK_API_KEY required secret Env: SPEAK_BASE_URL |