Mcp Server Agent Analytics

io.github.joepangalloPublished by GitHub account joepangallov1.1.1Updated Oct 24, 2026

Track AI agent fleet performance, costs, anomalies, and trends.

VerifiedSTDIODesktop onlyData & AnalyticsAI & ML

Overview

AI-generated overview

Lets an assistant track AI agent fleet performance, costs, anomalies, and trends from a local process.

What you can do
This MCP server exposes analytics for a fleet of AI agents, covering performance, cost, anomaly detection, and trend reporting. It runs locally over stdio, so the assistant can query these metrics as tools during a session. The registry lists no individual tools, so the exact operations are not documented here.
When to use it
Worth considering when you run multiple AI agents and want an assistant to help review their performance, spending, and unusual behavior. It is a desktop-only local server, so it suits individual workstations rather than shared or hosted environments.
Requirements
Runs as a local process on the user's machine, installed from the npm package mcp-server-agent-analytics over stdio. Desktop only; no web execution. No authentication, environment variables, or headers are declared.
Before you install
The registry description is the only documentation available, and no tools are listed, so what data it reads and where that data comes from is unclear. Review the package before installing, especially if agent cost or performance data is sensitive.

Installation

In SourceWeft

  1. Open Mcp Server Agent Analytics in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

This repository has no README.

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v1.1.1LatestSep 16, 2026

Score

25% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts

    Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.

  • License10 pts

    Declare a license in the repository or the registry entry.