Skip to content
mcpfy
Start deploying

inspector

See exactly what the model saw

An open-source debugger for MCP servers: invoke tools, read raw JSON-RPC, browse resources, test prompts and preview widgets. Run it hosted, local, or self-hosted with Docker.

Open the InspectorRun it locally

Our open source tools are used by developers at top companies

NorthwindApertureCogentLumenBrightpathSundialMeridianIroncladBlue HarborKestrel

How it runs

A real debugger for a real protocol

  1. 1

    Connect

    Point it at any MCP endpoint.

  2. 2

    Call

    Invoke tools with real arguments.

  3. 3

    Read

    Every frame, in and out.

  4. 4

    Fix

    Replay the call after each change.

Protocol-level logging

Timestamped JSON-RPC frames you can expand, copy and diff between runs.

Cloud Inspectorsession #4f2a

San Francisco, CA

72°F

Partly cloudy · H 74° L 58°

now72°
2pm74°
3pm73°
4pm70°
5pm66°
6pm63°

→ tools/call

{
  "name": "display_weather",
  "arguments": { "city": "San Francisco" }
}

← result20041ms

{ "content": [{ "type": "resource" }] }

GPT-5.2

18/18

Claude

18/18

Gemini

17/18

Widget preview

Render interactive views exactly as the host client will, with host APIs emulated.

acme-mcp · zsh

➜ npx create-mcpfy-app

✓ tools/chart-sales.ts

✓ widgets/Chart.tsx

✓ mcpfy.config.ts

➜ mcpfy dev

ready on :4141 · 6 tools registered

tools/chart-sales.ts

export const chartSales = tool({
  name: "chart_sales",
  input: z.object({ period: z.string() }),
});

Runs anywhere

Use it hosted, from the CLI against localhost, or self-hosted behind your own network.

Deploymentsauto · on push
  • mainProduction12s
  • feat/chartsPreview9s
  • fix/authPreview11s

➜ npx mcpfy deploy

✓ live → my-server.mcpfy.ai/mcp

In the box

Everything you need to debug MCP

1

Tool testing

Arbitrary arguments, instant results.

2

Resource browsing

Inspect what you actually expose.

3

Prompt testing

Exercise prompts in isolation.

4

Open source

MIT licensed and self-hostable.

Debug your MCP server properly

Start deployingBook a call

Explore the rest of the platform

MCP Hosting

GitHub-native builds, preview URLs per branch, production endpoints with TLS and custom domains, and instant rollback, purpose-built for MCP traffic and the clients that connect to it.

Learn more

Cross-client testing

Your server behaves differently in ChatGPT than it does in Claude or Cursor.

Learn more

Publishing checks

Six categories of checks mapped to marketplace requirements, each failure with fix guidance and an autofix flow, plus live end-to-end runs inside the real clients.

Learn more

Cloud Inspector

Fire tool calls at your deployed server, read raw JSON-RPC frames, browse resources and preview widgets, against real clients, with no local setup.

Learn more

Public chat

Every deployment gets a shareable chat surface you can embed anywhere you already have an audience: no client install, no configuration.

Learn more

Analytics

Tool calls, sessions, error rates and latency percentiles broken down by client, client version, protocol version and country, with discovery traffic excluded by default.

Learn more

Everything on mcpfy Cloud shares one pipeline.