Keploy

MCP serverDev tools

Add this and your AI can take over end-to-end API testing for you. It generates tests from what you already have, such as an OpenAPI spec, curl commands, Postman collections, or real user traffic, and then runs them. That means working API checks without writing each test by hand.

Use Keploy in Claude, ChatGPT or Ahel Desktop

Free. Sign in, add Keploy and connect your AI. About a minute.

Also: Claude Code · Cursor · Codex

Then ask your AI: use the devloop begin oauth install tool from Keploy

Details

Available today. Use it from your connected AI after setup.

After adding it, give your AI an OpenAPI spec, a curl command, a Postman collection, or real traffic to work from, and it will generate and run the tests for you.

What your AI can do with it

  • Generate API tests from an OpenAPI spec
  • Create tests from curl commands
  • Build tests from Postman collections
  • Capture tests from real user traffic
  • Run end-to-end API tests and report results

Install Keploy

The server’s own address, for the clients that take one directly. Or connect Ahel once and every client you use reads it from one address, with the account kept on Ahel rather than in each client’s config.

  • Claude Code

    claude mcp add --transport http --scope user keploy 'https://api.keploy.io/client/v1/mcp'

    Run it once in your project, then open /mcp to approve any sign-in the server asks for.

  • Claude Desktop

    https://api.keploy.io/client/v1/mcp

    Add a custom connector in Settings, paste this address, and approve the sign-in.

  • Cursor

    cursor://anysphere.cursor-deeplink/mcp/install?name=keploy&config=eyJ1cmwiOiJodHRwczovL2FwaS5rZXBsb3kuaW8vY2xpZW50L3YxL21jcCJ9

    Open the link and Cursor adds the server at that address.

  • ChatGPT

    https://api.keploy.io/client/v1/mcp

    In Settings, enable Developer mode, create an MCP app, and paste this address. Your plan and workspace must allow custom apps.

  • Codex

    codex mcp add keploy --url 'https://api.keploy.io/client/v1/mcp'

    Run it once, then sign in with codex mcp login keploy if the server asks for an account.

From the project's README

As published by keploy/keploy in README.md.


Keploy is a developer‑centric API and integration testing tool that auto‑generates tests and data‑mocks faster than unit tests.

It records API calls, database queries, and streaming events — then replays them as tests. Under the hood, Keploy uses eBPF to capture traffic at the network layer, but for you it’s completely code‑less and language‑agnostic.

🐰 Fun fact: Keploy uses itself for testing! Check out our swanky coverage badge:  


Key Highlights

🎯 No code changes

Just run your app with keploy record. Real API + integration flows are automatically captured as tests and mocks. (Keploy uses eBPF under the hood to capture traffic, so you don’t need to add any SDKs or modify code.)

📹 Record and Replay complex Flows

Keploy can record and replay complex, distributed API flows as mocks and stubs. It's like having a very light-weight time machine for your tests—saving you tons of time!

👉 Read the docs on record-replay

🐇 Complete Infra‑Virtualization (beyond HTTP mocks)

Unlike tools that only mock HTTP endpoints, Keploy records databases (Postgres, MySQL, MongoDB), streaming/queues (Kafka, RabbitMQ), external APIs, and more.

It replays them deterministically so you can run tests without re‑provisioning infra.

👉 Read the docs on infra virtualisation

🧪 Combined Test Coverage

If you’re a developer, you probably care about statement and branch coverage — Keploy calculates that for you.

If you’re a QA, you focus more on API schema and business use‑case coverage — Keploy calculates that too. This way coverage isn’t subjective anymore.

👉 Read the docs on coverage

🤖 Expand API Coverage using AI

Keploy uses existing recordings, Swagger/OpenAPI Schema to find: boundary values, missing/extra fields, wrong types, out‑of‑order sequences, retries/timeouts.

This helps expand API Schema, Statement, and Branch Coverage.

👉 Read the docs on coverage

Other Capabilities

  • 🌐 CI/CD Integration: Run tests with mocks anywhere you like—locally on the CLI, in your CI pipeline (Jenkins, Github Actions..) , or even across a Kubernetes cluster. Read more

  • 🎭 Multi-Purpose Mocks: You can also use Keploy-generated Mocks, as server Tests!

  • 📊 Reporting: Unified reports for API, integration, unit, and e2e coverage with insights directly in your CI or PRs.

  • 🖥️ Console: A developer-friendly console to view, manage, and debug recorded tests and mocks.

  • ⏱️ Time Freezing: Deterministically replay tests by freezing system time during execution. Read more

  • 📚 Mock Registry: Centralized registry to manage, reuse, and version mocks across teams and environments. Read more


Quick Start

1. Install Keploy Agent

curl --silent -O -L https://keploy.io/install.sh && source install.sh

2. Record Test Cases

Start your app under Keploy to convert real API calls into tests and mocks.

keploy record -c "CMD_TO_RUN_APP"

Example for Python:

keploy record -c "python main.py"

3. Run Tests

Run tests offline without external dependencies.

keploy test -c "CMD_TO_RUN_APP" --delay 10

Resources

- 📘 Installation

- 🏁 QuickStarts


Languages & Frameworks (Any stack)

Because Keploy intercepts at the network layer (eBPF), it works with any language, framework, or runtime—no SDK required.

Note: Some of the dependencies are not open-source by nature because their protocols and parsings are not open-sourced. It's not supported in Keploy enterprise.


Questions?

Book a Live Demo / Enterprise Support

Want a guided walkthrough, dedicated support, or help planning enterprise rollout?

Prefer a calendar invite? Mention your availability in the email—we’ll send a calendar invite right away.


Documentation & Community


Contribute & Collaborate

Whether you're new or experienced, your input matters. Help us improve Keploy by contributing code, reporting issues, or sharing feedback.

Together, let's build better testing tools for modern applications.

Tools it offers (7)

What this server listed when Ahel dialed its public endpoint in Oct 2026, with no key and no account of yours. The names are the server’s own.

  • devloop_begin_oauth_install
  • devloop_setup_instructions
  • get_auth_status
  • get_setup_instructions
  • get_tool_schema
  • invoke_tool
  • search_tools

Signals

GitHub stars
19k
Forks
2k
Last commit
Oct 2026
Advanced
Delivery
Keploy MCP server → your Ahel connector (mcp.ahel.ai) → your AI.
Item type
mcp-server
Key
io-github-keploy-mcp
Source
github.com/keploy/keploy
Hosted endpoint
https://api.keploy.io/client/v1/mcp