Warpmetrics

io.github.warpmetricsPublished by GitHub account warpmetricsv0.1.0Updated Oct 24, 2026

Connect AI assistants to Warpmetrics — query runs, calls, costs, and outcomes.

VerifiedSTDIODesktop onlySecurity & MonitoringData & Analytics

Overview

AI-generated overview

A local MCP server that connects AI assistants to Warpmetrics AI agent telemetry, letting them query runs, calls, costs and outcomes.

What you can do
Query runs and calls, including recent failed runs and details for a specific run ID, and list the most expensive calls. Review costs and performance, such as total LLM spend, average latency per agent and cost trends over a period. Check outcomes and success rates, including outcome statistics and outcome classifications. Tools are loaded dynamically from the Warpmetrics API and stay in sync automatically.
When to use it
Useful when you already track AI agent activity in Warpmetrics and want to ask about run history, LLM spend, latency or success rates in plain language instead of browsing the dashboard.
Requirements
Runs as a local process installed from the npm package @warpmetrics/mcp, so Node.js is needed. Requires a Warpmetrics account and an API key supplied through the WARPMETRICS_API_KEY environment variable; WARPMETRICS_API_URL is optional and defaults to the hosted API. Network access to the Warpmetrics API is required. Desktop client only.
Before you install
The server needs a Warpmetrics API key (WARPMETRICS_API_KEY), which is stored in the client configuration file; treat it as a secret and avoid sharing that file. Queries and results are sent to the Warpmetrics API over the network. The listed tools appear read-only, but the tool set is loaded dynamically from the API, so check what is actually exposed before use.

Installation

In SourceWeft

  1. Open Warpmetrics 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

Warpmetrics MCP Server

Connect AI assistants to your Warpmetrics AI agent telemetry via the Model Context Protocol.

[MCP Registry] [npm]

Installation

bash
npm install -g @warpmetrics/mcp

Setup

1. Get your API key

Create an API key at warpmetrics.com/app/api-keys

2. Configure Claude Desktop

Add to your ~/.claude/claude_desktop_config.json:

json
{  "mcpServers": {    "warpmetrics": {      "command": "warpmetrics-mcp",      "env": {        "WARPMETRICS_API_KEY": "wm_live_your_api_key_here"      }    }  }}

3. Restart Claude Desktop

The Warpmetrics tools will now be available.

Available Tools

Tools are loaded dynamically from the Warpmetrics API and stay automatically in sync.

View all available tools:

Example Prompts

Runs & Calls

  • "How many runs did I have today?"
  • "Show me the most expensive calls"
  • "List recent failed runs"
  • "Show details for run wm_run_01abc123"

Costs & Performance

  • "What's my total LLM spend this week?"
  • "What's the average latency for my code-review agent?"
  • "Show me cost trends for the last 7 days"

Outcomes & Success Rates

  • "What's the success rate for my code-review agent?"
  • "Show me outcome statistics"
  • "List all outcome classifications"

Environment Variables

VariableRequiredDescription
WARPMETRICS_API_KEYYesYour Warpmetrics API key
WARPMETRICS_API_URLNoAPI URL (default: https://api.warpmetrics.com)

Development

bash
git clone https://github.com/warpmetrics/mcp.gitcd mcpnpm install
# Run locallyWARPMETRICS_API_KEY=wm_live_... node src/index.js

License

MIT

Source: README.md at commit 0afd403

Tools

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

Version history

1
  1. v0.1.0LatestSep 16, 2026

Score

40% 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
  • License10 pts

    Declare a license in the repository or the registry entry.