🚀 Quick start

<div align="center">

<h1>MCPJam</h1>

<img alt="MCPJam — the testing and evaluations platform for MCP server developers" src="./docs/images/readme-banner.png">

<p>
  <a href="https://app.mcpjam.com"><b>Hosted app</b></a> &nbsp;·&nbsp;
  <a href="https://docs.mcpjam.com"><b>Docs</b></a> &nbsp;·&nbsp;
  <a href="https://www.mcpjam.com"><b>Website</b></a>
</p>

[![npm version](https://img.shields.io/npm/v/@mcpjam/inspector?style=for-the-badge&color=blue)](https://www.npmjs.com/package/@mcpjam/inspector)
[![License: Apache 2.0](https://img.shields.io/badge/License-Apache%202.0-blue.svg?style=for-the-badge)](https://opensource.org/licenses/Apache-2.0)
[![Discord](https://img.shields.io/badge/Discord-Join%20Server-5865F2.svg?style=for-the-badge&logo=discord&logoColor=white)](https://discord.gg/JEnDtz8X6z)

</div>

**MCPJam** is the open-source **testing & evaluations platform for MCP server developers** who ship. Interactively test tools, prompts, resources, and authorization across 16 client configurations and 170+ models. Run evals on test cases, get insights on what's breaking, and gate regressions to secure every deployment.

# 🚀 Quick start

Open the hosted app. No install needed.

👉 **[app.mcpjam.com](https://app.mcpjam.com)**

... or run MCPJam locally for HTTP/S and local STDIO servers:

```bash
npx @mcpjam/inspector@latest
```

# 👋🏽 Why MCPJam

Clients like ChatGPT, Claude, and Cursor all read your server differently. MCPJam catches those differences, shows where your server breaks, and tells you how to fix it:

- **Inspect & debug**: Explore your server's tools, resources, and prompts in one place. Test prompts from real LLMs, with full visibility & traces on every JSON-RPC message and OAuth exchange.
- **Cross-client evals**: Score agent behavior across 16 client configurations — ChatGPT, Claude, Cursor, Copilot, and more — to understand how your MCP integrations perform across all users. Track accuracy, latency, and tool-call performance over time.
- **Security & reliability**: Automate conformance & behavior checks in CI/CD to catch regressions before they reach production.

<img alt="MCPJam Playground trace view: every tool call, agent step, and JSON-RPC message in one timeline" src="./docs/images/readme-playground.png">

<div align="center">

_Trace view: every tool call, agent step, and JSON-RPC message in one timeline._

</div>

# 🔨 Features

| Capability           | What it does                                                                                                                                                                                                        |
| -------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| **Playground**       | Cross-client chat interface that emulates UIs, tool calls, and skills (with full traces). OpenAI Apps SDK and MCP app UIs, text tools, and a Chrome DevTools-style widget emulator. [Read more](https://docs.mcpjam.com/inspector/playground) |
| **OAuth Debugger**   | Visualize your OAuth & EMA requests step-by-step to find the source of errors. Guided MCP OAuth conformance checks across protocol versions 03-26, 06-18, 11-25, and 2026-07-28; DCR, client pre-registration, and CIMD. [Read more](https://docs.mcpjam.com/inspector/guided-oauth) |
| **Server Debugging** | Manually run tools, resources, templates, prompts, and elicitation flows with full JSON-RPC logs.                                                                                                                  |
| **Skills**           | Extend models with reusable behaviors in Playground. Local skills are read from your filesystem and never leave your machine; a project can also carry hosted skills, available on accounts where that is enabled. [Read more](https://docs.mcpjam.com/inspector/skills) |
| **Workspaces**       | Shared server groups with real-time team sync, so everyone tests the same config. [Read more](https://docs.mcpjam.com/inspector/workspaces)                                                                         |
| **Evals**            | Test cases with expected tool calls, run across LLMs, with accuracy metrics over time. [Read more](https://docs.mcpjam.com/inspector/test-cases)                                                                    |
| **CLI**              | Probe servers, run doctor checks, exercise OAuth, and list tools/resources/prompts from your terminal. [Read more](https://docs.mcpjam.com/cli/overview)                                                            |
| **SDK**              | Programmatically drive inspections, snapshot capabilities, and assert on tool/resource shapes from your own tests. [Read more](https://docs.mcpjam.com/sdk)                                                         |
| **CI/CD**            | Run conformance, E2E tests, evals, and O

... (truncated)