mcp-telemetry provides a telemetry SDK for MCP server authors to emit job, step, log, cost, and completion events over a local socket, and an MCP server that lets agents subscribe to and query that live job state. It is designed to show long-running tool progress without polling, including from a different client session.
From the registry: Streams live progress from mcp-telemetry-sdk-instrumented tools to any connected MCP client.

$ npm install -g mcp-telemetry-serverPlease install the `mcp-telemetry-server` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Install Node.js and npm** — Node.js and npm are required to run the MCP server via npx/npm. (https://nodejs.org/.)
Optional prerequisites:
- Install the mcp-telemetry server package globally — The README quickstart installs the MCP server package globally before registering it with an MCP client. Run: `npm install -g mcp-telemetry-server`
Canonical MCP server config (stdio transport):
- command: `npx`
- args: ["-y","mcp-telemetry-server"]
Note: The README shows this server being registered alongside another instrumented MCP server. No environment variables are documented for mcp-telemetry-server. The server exposes MCP tools including telemetry_subscribe, telemetry_jobs, and telemetry_job_status.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.Meta Ads MCP (Facebook + Instagram) - analyze performance, manage budgets, pause campaigns.