Skip to content
MCP server

TestChimp

QA coverage, in-repo test plans and release checks for coding agents

Install
Pricing
Free trial
Platforms
CLI, API, Web
Runs
Locally or Remotely
Version
0.1.93
Listing updated
2 days ago

About TestChimp

TestChimp is an MCP server for developer tools. It can run locally on your machine or as a hosted remote server.

TestChimp treats test planning as files in your repository: stories and scenarios live as Markdown where agents can read them and people can review them. Through the CLI and MCP server an agent can query requirement coverage for a branch, create user stories, manage releases and test runs, record issues, and compare performance runs against a baseline. The compare command exits nonzero when a regression is flagged, so it can gate a pipeline.

The wider platform measures QA posture in three ways: semantic coverage of requirements, API schema coverage from the payloads tests produce, and TrueCoverage against how real users behave. Its release command ranks gaps by risk and hands them to agents to close, then runs the suite, performance and security checks and UX walks in one view. The site also describes MeetBots, which transcribe meetings, and AgentWatch, which picks up requirement changes from coding-agent sessions.

The package runs as a stdio server through npx, or you can use the hosted endpoint at mcp.testchimp.io. A project API key is required. Plans start at $42 a month billed annually, with a 14-day trial.

Install

Run in a terminal

claude mcp add --transport http qa https://mcp.testchimp.io/mcp

Add to Settings → Connectors → Add custom connector

https://mcp.testchimp.io/mcp
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "qa": {
      "url": "https://mcp.testchimp.io/mcp"
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "qa": {
      "type": "http",
      "url": "https://mcp.testchimp.io/mcp"
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "qa": {
      "serverUrl": "https://mcp.testchimp.io/mcp"
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "qa": {
      "type": "http",
      "url": "https://mcp.testchimp.io/mcp"
    }
  }
}

Configuration

  • TESTCHIMP_API_KEYTestChimp project API key (Project Settings in TestChimp)Required
  • TESTCHIMP_BACKEND_URLOptional backend URL override for enterprise or self-hosted TestChimp

Tools this server provides (10)

Taken from the project documentation; the running server may differ.

get-requirement-coverage
Returns requirement coverage for a branch.
create-user-story
Creates a user story file in the plans folder.
compare-perf-to-baseline
Compares a performance run to a baseline and exits nonzero on regression.
promote-perf-baseline
Promotes a performance run to the baseline for an environment class.
list-meetings
Lists team meetings captured by Meeting Bots with filters.
get-meeting-transcript
Fetches a meeting transcript or summary.
upsert-issue
Creates or updates an issue.
get-release
Returns a release record.
manage-test-run
Manages a test run for a release.
ephemeral-environment
Provisions or deploys an ephemeral environment for a branch.

What it does

Requirement coverage
Measures how well tests cover the requirements for a branch.
Plans in the repo
Keeps stories and scenarios as reviewable Markdown files.
Release governance
Creates releases, ranks gaps by risk and shows QA posture with test verification status.
Performance gates
Promotes baselines and fails when a run regresses against one.
Meeting transcripts
Lists meetings and fetches transcripts captured by its bots.
Ephemeral environments
Provisions environments for a branch and reports scan findings.

Good for

  • Check which requirements on a branch lack tests
  • Ask an agent to close the highest-risk QA gaps before a release
  • Fail a build when p95 latency regresses past a threshold
  • Track issues and test runs for a release
  • Pull a customer meeting transcript into a story

Pricing

Free trial, from $42 a month

14-day trial; Indie $42/mo, Team $420/mo, Growth $667/mo (billed annually)

Prices change. Check testchimp.io before you buy.

TestChimp FAQ

What does it need to run?

A TestChimp project API key in TESTCHIMP_API_KEY, or an OAuth token.

How do I start it?

Run npx -y @testchimp/cli@latest mcp, or connect to the hosted endpoint at mcp.testchimp.io/mcp.

What does it cost?

Indie is $42 a month billed annually, Team $420 and Growth $667, with custom Enterprise pricing and a 14-day trial without a card.

Can it run self-hosted?

The Enterprise plan lists VPC or on-prem deployment, and a backend URL override exists for enterprise or self-hosted setups.

Is TestChimp free?

TestChimp is a paid product with a free trial. Paid plans start at $42 a month.

How do I add TestChimp to Claude Code?

Run this command in your terminal: claude mcp add --transport http qa https://mcp.testchimp.io/mcp

What are the best alternatives to TestChimp?

The closest alternatives to TestChimp are REA, Codebase Memory, GitHub, Serena MCP: the IDE for your agent and XERJ.

Alternatives to TestChimp

  1. REA

    MCP server

    CLI and MCP server that lets coding agents reverse engineer apps and binaries

    Runs locally
    • Open source
    • 464K GitHub stars
    • Developer tools
  2. Codebase Memory

    MCP server

    Local MCP server that builds a code knowledge graph for AI coding agents

    Runs locally
    • Open source
    • 48.7K GitHub stars
    • Knowledge and memory
  3. GitHub

    MCP server

    Official MCP server connecting AI assistants to GitHub repos, issues and workflows

    Not checked yet
    • Remote
    • Open source
    • 34.5K GitHub stars
    • Developer tools
  4. MCP toolkit giving coding agents symbol-level code retrieval and editing

    Runs locally
    • Open source
    • 31.5K GitHub stars
    • Developer tools
  5. XERJ

    MCP server

    Local search engine for AI agents with cited answers over your code and docs

    Runs locally
    • Open source
    • 19.2K GitHub stars
    • Knowledge and memory
  6. Ouroboros

    MCP server

    Spec-first layer that pins requirements and verifies results of AI coding agent work

    Runs locally
    • Open source
    • 6.4K GitHub stars
    • Developer tools