# MCPJam MCP server

> Lets AI clients chat with, inspect, and debug MCP servers, tools, prompts, and OAuth flows with full JSON-RPC traces.

- Repository: https://github.com/MCPJam/inspector
- Page: https://hostedmcp.org/servers/mcpjam/inspector
- Transport: stdio
- Stars: 2318

## Install

### Claude Code

```sh
claude mcp add inspector -- npx -y @mcpjam/cli
```

### Cursor (`~/.cursor/mcp.json`)

```json
{
  "mcpServers": {
    "inspector": {
      "command": "npx",
      "args": [
        "-y",
        "@mcpjam/cli"
      ]
    }
  }
}
```

### VS Code (`.vscode/mcp.json`)

```json
{
  "servers": {
    "inspector": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@mcpjam/cli"
      ]
    }
  }
}
```

### VS Code CLI

```sh
code --add-mcp '{"name":"inspector","type":"stdio","command":"npx","args":["-y","@mcpjam/cli"]}'
```

### Claude Desktop (`claude_desktop_config.json`)

```json
{
  "mcpServers": {
    "inspector": {
      "command": "npx",
      "args": [
        "-y",
        "@mcpjam/cli"
      ]
    }
  }
}
```

### Codex

```sh
codex mcp add inspector -- npx -y @mcpjam/cli
```

### Codex config.toml (`~/.codex/config.toml`)

```toml
[mcp_servers.inspector]
command = "npx"
args = ["-y", "@mcpjam/cli"]
```

### Gemini CLI

```sh
gemini mcp add -s user inspector npx -- -y @mcpjam/cli
```

### Gemini settings.json (`~/.gemini/settings.json`)

```json
{
  "mcpServers": {
    "inspector": {
      "command": "npx",
      "args": [
        "-y",
        "@mcpjam/cli"
      ]
    }
  }
}
```

## Tools (17)

- `connect_server`: Open a persistent connection to an MCP server under test, over HTTP (url) or stdio (command). The connection stays open across tool calls so session state and notifications can be observed. Returns the negotiated initialization info.
- `disconnect_server`: Close an open connection created by connect_server and discard its buffered notifications.
- `list_servers`: List the MCP server connections opened with connect_server, with status and a redacted target summary. (read-only)
- `server_info`: Get the negotiated initialization info for a connected server: protocol version, transport, server info/version, capabilities, and instructions. (read-only)
- `ping_server`: Send an MCP ping over an open connection and report the round-trip latency. (read-only)
- `list_tools`: List tools exposed by a connected server, including pagination cursor and per-tool metadata. (read-only)
- `call_tool`: Invoke a tool on a connected server and return the target's raw CallToolResult. A tool-level failure is reported inside the payload via its "isError" field; this call only errors when the request itself fails.
- `list_resources`: List resources exposed by a connected server. Set templates=true to list resource templates instead. (read-only)
- `read_resource`: Read a resource from a connected server by URI. (read-only)
- `list_skills`: List the Agent Skills a connected server serves over the skills extension (SEP-2640), including ones it advertises that cannot be verified, each with the reason. (read-only)
- `get_skill`: Fetch one skill by uri and verify it before returning content: the SKILL.md digest against the manifest, the fetched frontmatter against what the listing advertised, and the name against the uri. Answers with the skill, or with a refusal naming the check that failed. (read-only)
- `read_skill_file`: Read one supporting file of a skill served by a connected server, checked against that skill's own manifest for byte length and digest. (read-only)
- `list_prompts`: List prompts exposed by a connected server. (read-only)
- `get_prompt`: Fetch a named prompt from a connected server, optionally with string arguments. (read-only)
- `get_notifications`: Return notifications received from connected servers since connect (log messages, progress, tools/resources/prompts list_changed, resource updates). Use after call_tool or a server-side change to verify the target emitted the expected notifications.
- `server_doctor`: Run a stateless diagnostic sweep against an MCP server (HTTP url or stdio command) without keeping a connection open: reachability, initialize, capability checks, and tool/resource/prompt counts. Equivalent to `mcpjam server doctor`. (read-only)
- `probe_server`: Probe an HTTP MCP server without the full client connect flow: transport selection, auth requirements, and OAuth metadata discovery. Equivalent to `mcpjam server probe`. (read-only)

## FAQ

### How do I run MCPJam locally?

Run npx @mcpjam/inspector@latest in your terminal; it supports HTTP/S and local STDIO servers and prints a localhost URL to open.

### Can I test MCP servers across different AI clients?

Yes, MCPJam scores agent behavior across 16 client configurations including ChatGPT, Claude, Cursor, and Copilot.

### Does MCPJam help debug OAuth flows?

Yes, its OAuth Debugger visualizes OAuth requests step by step and runs guided conformance checks across multiple protocol versions.

### Can MCPJam run evals in CI/CD?

Yes, you can wire MCPJam into GitHub Actions, GitLab CI, or any CI system to run conformance, E2E tests, and evals on every pull request.

### Is MCPJam free and open source?

The project is open source and licensed under the Apache License 2.0.
