mcpField
M
mcp-telemetry-server

mcp-telemetry-server

Local
github.com/arnavranjan005Developer Tools2Updated 17w ago
Repository

About mcp-telemetry-server

mcp-telemetry-server collects progress from tools instrumented with mcp-telemetry-sdk and makes it available to MCP clients. It is intended for monitoring running jobs and their outcomes.

Key features

  1. 01Stream live job progress
  2. 02List jobs with status and cost
  3. 03Inspect steps and failure reasons

Use cases

  1. 01Monitor an instrumented tool while it runs
  2. 02Review job cost and completion status

MCP support

An MCP server that exposes tools for subscribing to job progress and querying job lists and status.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "arnavranjan005-mcp-telemetry-server": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-telemetry-server"
      ]
    }
  }
}
Run commandnpx -y mcp-telemetry-server

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npmmcp-telemetry-server0.1.3

Tools

3

Saved tool list · updated 2w ago

This tool takes no parameters.

Details

From the project README

mcp-telemetry-server

The collector half of mcp-telemetry. Register it as an MCP server to watch live progress from any tool instrumented with mcp-telemetry-sdk.

Install

npm install -g mcp-telemetry-server

Register it

{
  "mcpServers": {
    "telemetry": { "command": "npx", "args": ["-y", "mcp-telemetry-server"] }
  }
}

Tools it exposes

ToolBehavior
telemetry_subscribe({ jobId?, timeoutMs? })Blocks and streams live progress for a job until it finishes.
telemetry_jobs()Lists all known jobs with status and cost.
telemetry_job_status({ jobId })Full state of one job — steps, cost, failure reason.

See the main README for a full worked example.

License

MIT

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.