What can you do with this server?

The MCP Inspector server enables LLMs to inspect, test, and debug other MCP servers through both ephemeral and persistent connections with human-in-the-loop steering. Core Capabilities: * Inspect MCP Servers: List and explore tools, resources (including templates), and prompts from any target MCP server * Test MCP Servers: Call tools and read resources with full parameter support * Multi-Transport Support: Connect via stdio (local commands), SSE, or HTTP transports with auto-detection * Persistent Session Management: Create, monitor, and close persistent connections with automatic garbage collection (30-minute TTL) * Event Monitoring: Capture and read buffered traffic, notifications, and errors for debugging * Human-in-the-Loop Workflows: Inject steering messages via CLI (mcp-steer), HTTP API (port 9847), or MCP tools to guide LLM testing * Stateful Testing: Maintain server state across operations using session IDs for debugging stateful behavior Use Cases: * Debug and develop MCP servers iteratively within an LLM conversation * Test MCP server functionality without external tools * Discover capabilities of unknown MCP servers * Validate tool inputs/outputs and resource structures

How do I use MCP Inspector as MCP Server?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@MCP Inspector as MCP Server list tools from my local weather server" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

MCP Inspector as MCP Server

A lean MCP server that enables LLMs to inspect and test other MCP servers. This is a self-contained implementation that uses the MCP SDK directly, without shelling out to external CLIs.

Features

Direct SDK integration: Uses @modelcontextprotocol/sdk directly for both server and client operations
All transport types: Supports stdio, SSE, and HTTP (streamable) transports
Minimal footprint: Single dependency (@modelcontextprotocol/sdk)
Full MCP inspection: List tools, call tools, list resources, read resources, list prompts, get prompts
Session management: Persistent connections with automatic garbage collection
Event buffering: Capture notifications, traffic, and errors for debugging

Installation

npm install npm run build

Usage

As an MCP Server

Add to your MCP config. While there are slight variances between different harnesses, the general format is the same:

{ "mcpServers": { "mcp-inspector": { "command": "node", "args": ["/path/to/mcp-inspector-as-mcp-server/dist/server.js"] } } }

Available Tools

Session Management (NEW in v2.0)

Tool	Description
`insp_connect`	Establish a persistent connection to an MCP server. Returns a `session_id`.
`insp_disconnect`	Close a persistent session and release resources.
`insp_list_sessions`	List all active sessions with their status and idle time.
`insp_read_events`	Read buffered events (notifications, traffic, errors) from a session.
`insp_inject_steering`	Inject a human steering message into a session's queue.

Inspection Tools

Tool	Description
`insp_tools_list`	List all tools exposed by an MCP server
`insp_tools_call`	Call a tool on an MCP server
`insp_resources_list`	List all resources exposed by an MCP server
`insp_resources_read`	Read a specific resource
`insp_resources_templates`	List resource templates
`insp_prompts_list`	List all prompts
`insp_prompts_get`	Get a specific prompt

Connection Parameters

All tools accept the following connection parameters:

For stdio transport (local commands):

command: Command to run (e.g., "node", "python")
args: Array of arguments (e.g., ["path/to/server.js"])

For SSE/HTTP transport (remote servers):

url: Server URL (e.g., "http://localhost:3000/sse")
headers: Optional HTTP headers object

Common:

transport: Force transport type ("stdio", "sse", or "http"). Auto-detected if not specified.
session_id: (Optional) Use an existing persistent session instead of creating an ephemeral connection.

Session Workflow

For debugging stateful server behavior, use persistent sessions:

1. insp_connect → returns session_id 2. insp_tools_list (with session_id) → uses persistent connection 3. insp_tools_call (with session_id) → state is preserved 4. insp_read_events (with session_id) → see notifications 5. insp_disconnect (with session_id) → cleanup

Sessions auto-close after 30 minutes of inactivity.

Human Steering & Observability

The inspector enables human-in-the-loop workflows where you can observe and guide LLM-driven MCP testing in real-time.

How It Works

┌─────────────┐ MCP calls ┌─────────────────┐ forwards ┌─────────────┐ │ LLM Agent │ ◄────────────────► │ MCP Inspector │ ◄──────────────► │ Target MCP │ │ (Antigravity) │ (v2.0) │ │ Server │ └─────────────┘ └────────┬────────┘ └─────────────┘ │ Events logged to session EventBuffer │ ┌───────────────────────┼───────────────────────┐ │ │ │ ▼ ▼ ▼ insp_read_events HTTP :9847/api mcp-steer CLI (LLM reads events) (external access) (human injection)

Viewing Activity

Via LLM: The agent can call insp_read_events to see what's happening:

{ "session_id": "sess_abc123", "types": ["traffic_in", "traffic_out"], "limit": 20 }

Via HTTP: Query the steering API directly:

curl http://127.0.0.1:9847/api/sessions

Steering the Agent

Inject guidance messages that appear in the LLM's next tool response.

Using the CLI:

./bin/mcp-steer.mjs "Focus on testing the error handling paths" ./bin/mcp-steer.mjs --session sess_abc123 "Try calling with invalid params"

Using HTTP:

curl -X POST http://127.0.0.1:9847/api/steer \ -H "Content-Type: application/json" \ -d '{"message": "Check the authentication flow next"}'

Using the MCP tool:

{ "tool": "insp_inject_steering", "arguments": { "session_id": "sess_abc123", "message": "Great progress! Now test edge cases." } }

Event Types

Type	Description
`traffic_out`	Messages sent TO the target server
`traffic_in`	Messages received FROM the target server
`notification`	MCP notifications from the target server
`error`	Errors encountered during communication
`steering`	Human steering messages injected into the session

Typical Workflow

LLM creates session: insp_connect → gets sess_abc123
LLM starts testing: insp_tools_call with session_id
Human observes: curl http://127.0.0.1:9847/api/sessions
Human steers: ./bin/mcp-steer.mjs "Also test the batch endpoint"
LLM receives steering: Next tool response includes ⚡ STEERING from human: ...
LLM adapts: Takes the human guidance into account

Examples

List tools from a local MCP server (ephemeral):

{ "command": "node", "args": ["/path/to/some-mcp-server/dist/server.js"] }

Create a persistent session:

{ "command": "node", "args": ["/path/to/some-mcp-server/dist/server.js"] } // Returns: { "session_id": "sess_abc123", "server_info": {...} }

Call a tool using a session:

{ "session_id": "sess_abc123", "tool_name": "search", "tool_args": {"query": "hello"} }

Architecture

├── src/ │ ├── server.ts # MCP server exposing inspector tools │ ├── client.ts # Client wrapper (hybrid stateless/session mode) │ ├── transport.ts # Transport factory (stdio, SSE, HTTP) + TracingWrapper │ ├── session.ts # SessionRegistry with GC (30-min TTL) │ └── events.ts # EventBuffer (ring buffer for notifications) ├── bin/ │ └── mcp-steer.mjs # CLI tool for human steering └── tests/ # Ad-hoc test scripts (run with npx tsx)

Why This Exists

The original MCP Inspector is a web-based UI + CLI combo spread across multiple projects. This consolidates the core functionality into a single, lean MCP server that an LLM can use to:

Develop and debug MCP servers iteratively
Test MCP server functionality without leaving the conversation
Explore what tools/resources/prompts an MCP server exposes
Debug stateful behavior with persistent sessions

Changelog

v2.1.0

Added human steering (insp_inject_steering) for human-in-the-loop workflows
Added HTTP API on port 9847 for external steering/observability
Added mcp-steer.mjs CLI tool for easy human interaction
Fixed critical bug in TracingTransportWrapper where handler capture timing caused message loss

v2.0.0

Added session management (insp_connect, insp_disconnect, insp_list_sessions)
Added event buffering (insp_read_events)
All inspection tools now support optional session_id for persistent connections
Added automatic garbage collection (30-minute TTL for idle sessions)
Backward compatible: omit session_id for original ephemeral behavior

v1.0.0

Initial release with ephemeral connections

License

MIT

MCP Inspector as MCP Server

MCP Inspector as MCP Server

Features

Installation

Usage

As an MCP Server

Available Tools

Session Management (NEW in v2.0)

Inspection Tools

Connection Parameters

Session Workflow

Human Steering & Observability

How It Works

Viewing Activity

Steering the Agent

Event Types

Typical Workflow

Examples

Architecture

Why This Exists

Changelog

v2.1.0

v2.0.0

v1.0.0

License

Resources

Tools

New MCP Servers

Latest Blog Posts

MCP directory API