Testmode AI
Write, run and check natural-language browser tests of your web app from an AI assistant
- Pricing
- Freemium
- Platforms
- Web, API
- Runs
- Remotely
- Version
- 1.8.0
- Listing updated
- 2 days ago
About Testmode AI
Testmode AI is a freemium MCP server for developer tools. It runs as a hosted remote server, so there is nothing to install locally.
Testmode runs browser tests described in plain language, and its MCP server is one of three ways in, alongside a GitHub Action and a REST API that share one API. With a project API key or by signing in, an agent can list projects, environments, test plans, test cases and runs, start runs by plan, by test case id or by tag, and read results.
Guardrails are specific. Callers cannot read credentials or variable values, edit the test suite or create API keys. Runs they start show the key's name or the agent as the trigger and use credits like any other run, and a failing CI run is investigated by Testmode's Self-driving feature. A key stops working when its creator leaves or becomes a viewer.
The free plan gives 100 credits a month, about 10 test runs. Pro is 99 USD a month with a 7-day trial and 10,000 credits plus Self-driving, and Startup is 299 USD with 40,000 credits. The docs say API access comes with every paid plan.
Install
Run in a terminal
claude mcp add --transport http testmode https://api.testmode.ai/mcpAdd to Settings → Connectors → Add custom connector
https://api.testmode.ai/mcpAdd to ~/.cursor/mcp.json
{
"mcpServers": {
"testmode": {
"url": "https://api.testmode.ai/mcp"
}
}
}Add to .vscode/mcp.json
{
"servers": {
"testmode": {
"type": "http",
"url": "https://api.testmode.ai/mcp"
}
}
}Add to ~/.codeium/windsurf/mcp_config.json
{
"mcpServers": {
"testmode": {
"serverUrl": "https://api.testmode.ai/mcp"
}
}
}Add to your client's MCP settings (most use this shape)
{
"mcpServers": {
"testmode": {
"type": "http",
"url": "https://api.testmode.ai/mcp"
}
}
}What it does
- Start runs from agents
- Run a plan, specific cases or cases by tag on any environment.
- Read results
- List environments, plans, cases and run outcomes.
- Restricted access
- Cannot read secrets, edit tests or create keys.
- CI integrations
- Also available via GitHub Actions and a REST API.
- Self-driving follow-up
- Investigates failed CI runs.
Good for
- Have a coding agent run the tests for the feature it just changed
- Fail a deploy pipeline when a smoke test fails
- Check the latest run results from chat
- Run all tests with a given tag after a release
Pricing
Freemium, from $99 a month
Free 100 credits/mo; Pro 99 USD/mo with 7-day trial; API on paid plans
Prices change. Check testmode.ai before you buy.
Testmode AI FAQ
Can an agent edit my tests?
No. It can list and start runs but cannot edit the suite.
How does it sign in?
With a project API key or by signing in as yourself.
What do runs cost?
Each action a test runs uses one credit, the same as in the app.
Is there a free plan?
Yes, 100 credits a month; paid plans start at 99 USD.
Is Testmode AI free?
Testmode AI has a free plan, with paid plans for more usage or features. Paid plans start at $99 a month.
How do I add Testmode AI to Claude Code?
Run this command in your terminal: claude mcp add --transport http testmode https://api.testmode.ai/mcp
What are the best alternatives to Testmode AI?
The closest alternatives to Testmode AI are REA, Codebase Memory, GitHub, Serena MCP: the IDE for your agent and XERJ.
Alternatives to Testmode AI

REA
MCP serverCLI and MCP server that lets coding agents reverse engineer apps and binaries
Runs locally- Open source
- 464K GitHub stars
- Developer tools

Codebase Memory
MCP serverLocal MCP server that builds a code knowledge graph for AI coding agents
Runs locally- Open source
- 48.7K GitHub stars
- Knowledge and memory

GitHub
MCP serverOfficial MCP server connecting AI assistants to GitHub repos, issues and workflows
Not checked yet- Remote
- Open source
- 34.5K GitHub stars
- Developer tools

Serena MCP: the IDE for your agent
MCP serverMCP toolkit giving coding agents symbol-level code retrieval and editing
Runs locally- Open source
- 31.5K GitHub stars
- Developer tools

XERJ
MCP serverLocal search engine for AI agents with cited answers over your code and docs
Runs locally- Open source
- 19.2K GitHub stars
- Knowledge and memory

Ouroboros
MCP serverSpec-first layer that pins requirements and verifies results of AI coding agent work
Runs locally- Open source
- 6.4K GitHub stars
- Developer tools