Mcpspan

See the live demo, with sample data: nothing to install.

Features

• Every call, from every client. Tool calls, resource reads and prompt gets, with the client that made them: Claude, Claude Code, Cursor, VS Code, Codex, ChatGPT and the rest.
• Response times that mean something. Median and 95th percentile per tool, and the full distribution, so a cache hit and a slow path do not hide inside one average.
• Answer sizes. How large each tool's answers are, typical and largest: a tool that now and then returns megabytes fills the agent's context while looking fine on every latency chart.
• What agents are shown. Every session starts by reading the definitions of all your tools, called or not. See how many tokens that list costs, and which tools agents were shown in hundreds of sessions and never called.
• Failures, told apart. A handler that threw, a tool that answered with an error, arguments the server refused and which of them were wrong, and tools that agents asked for but your server does not have: which clients asked, the closest name you do have, and what the agent did next.
• Sessions. Each connection's calls, step by step, as the agent made them, with the calls an agent repeated with the same arguments marked: a loop that looks fine one call at a time. A tool's page says which call came right before it repeated or failed, by client.
• Releases. Every call carries the version of your server that answered it; the charts mark where each release began and compare it with the one before. A tool's own chart also marks where its description or input schema changed, since rewording a description can change how agents use a tool more than a change to its code.
• Alerts to Slack, Discord or any webhook, when errors climb or a server goes quiet, for a whole server or one tool.
• Your data, yours to take. CSV and NDJSON exports of anything you can see, and forwarding to OpenTelemetry for Grafana, Datadog, Honeycomb and the like.
• Private by design. Parameter values never leave your server's process, and nothing is sent anywhere you did not set up yourself. Error messages, which a tool that runs commands can fill with anything, can be turned off.

Ask your agent

Claude, Claude Code, Cursor, ChatGPT or any other MCP client can answer from your mcpspan numbers: which tools failed most this week, and why?, how does 1.4.1 compare with 1.4.0? The API is an MCP server itself: add http://localhost:6271/mcp to your agent, sign in when it asks, and allow it. It only reads. Other ways in are on the MCP server's page.

Badges

Show in your server's README how much it is used and how well it answers:

Calls, success rate and median response time over the last week, switched on per server in Settings. How they work.

Lint your tool definitions

Before you ship, check what makes a client refuse a tool or an agent pick the wrong one. No account needed:

npx mcpspan-lint -- node dist/server.js

What it checks.

Quick start

You need Docker.

git clone https://github.com/mcpspan/mcpspan.git
cd mcpspan
docker compose up -d

Open http://localhost:6270 and create your account. You get an API key for your first server, and the Settings page shows the line to add to it, in its language.

Connect your MCP server

TypeScript, on the official MCP SDK:

npm install mcpspan

import { instrument } from 'mcpspan';

instrument(server, {
  apiKey: process.env.MCPSPAN_API_KEY,
  endpoint: 'http://localhost:6271', // your mcpspan installation
});

Register your tools as you always have: every one is measured, and each returns and fails exactly as it did before.

Eight languages, the same features in each:

Every SDK behaves the same way, set out in one contract and checked by one test suite in every language.

Without changing your code

Any MCP server, in any language, can run behind the proxy instead. In your client's MCP settings, in front of the server's own command:

npx mcpspan-proxy -- node dist/server.js

Or in front of a server over HTTP, with clients pointed at the proxy:

docker run -p 6273:6273 -e MCPSPAN_API_KEY -e MCPSPAN_ENDPOINT ghcr.io/mcpspan/proxy http://flights:3000/mcp

It sees nearly all an SDK does; what it does not.

Running it

Settings are optional: copy .env.example to .env to change ports, how long data is kept, or the address your MCP servers reach the API at. docs/self-hosting.md covers the rest: the account and password reset, several servers, settings, exports, OpenTelemetry, and backups.

Contributing

See CONTRIBUTING.md.

Licence

MIT. See LICENSE.