@amp-labs
Basic information
Official AI SDK by Ampersand
No standard config provided
This server doesn't expose a parseable MCP config block in its README. See the repository for install instructions.
RepositoryTool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
This repo contains the official Ampersand AI SDK and the official MCP server for Ampersand. The AI SDK exposes tools for AI agents to manage and interact with integrations with customers' SaaS tools, while the MCP server exposes those tools via the Model Context Protocol.
Install the AI SDK with npm install @amp-labs/ai (or yarn/pnpm). Import modules such as createRecord and updateRecord from framework-specific paths (e.g., @amp-labs/ai/aisdk for Vercel AI SDK, @amp-labs/ai/mastra for Mastra). For the MCP server, configure it in mcp.json or claude_desktop_config.json using either SSE mode (with URL and headers/query param) or stdio mode (with npx command and env variables).
createRecord and updateRecord.checkConnection tool in AI workflows.The MCP server can be run via SSE (remote) or stdio (local). For stdio, you need Node.js and `npx`. Environment variables include `AMPERSAND_API_KEY`, `AMPERSAND_PROJECT_ID`, `AMPERSAND_GROUP_REF`, and optionally `AMPERSAND_INTEGRATION_NAME`.
Pass your Ampersand API key via the `x-api-key` header in SSE mode, or as a query parameter (`apiKey`) if headers are not supported. For stdio mode, set it in the `env` as `AMPERSAND_API_KEY`.
Ampersand manages integrations and connectors on its platform; the SDK and MCP server reference your project, integration, and group (identified by `projectId`, `integrationName`, and `groupRef`) to access the appropriate configuration.
The MCP server supports SSE (Server-Sent Events) for remote clients and stdio for local clients (e.g., via `npx`).
Open-source MCP to use Blender with any LLM
Connect your AI assistant to your own YOUB endurance training account. Read recorded activities with full analysis, planned sessions, race goals, wellness (HRV, sleep, resting HR) and your athletic profile. Create or mov
Handl speaks the Model Context Protocol. Your whole billing operation — projects, invoices, clients, reports, approvals — as tools any AI assistant can call, inside your autonomy rules.
PickFu MCP is a Model Context Protocol (MCP) server that connects AI assistants, developers, marketers, product managers, and AI agents to PickFu's consumer research platform. It enables users to create surveys, conduct
Painless E2E Automation for Mobile and Web
Comments