About Trunk Flaky Tests
Trunk Flaky Tests is an MCP server for development teams investigating flaky tests. It provides root-cause analysis and fix suggestions, and can generate plans for uploading test results to Trunk.
Key features
- 01Flaky-test root-cause analysis
- 02Suggested fixes for flaky tests
- 03Test-result upload setup plans
- 04OAuth 2.0 and OpenID Connect authorization
Use cases
- 01Investigate intermittent test failures
- 02Get suggestions for addressing flaky tests
- 03Plan test-result uploads to Trunk
MCP support
Provides the `fix-flaky-test` and `setup-trunk-uploads` tools through the hosted MCP endpoint at `https://mcp.trunk.io/mcp`. It supports OAuth 2.0 and OpenID Connect authorization.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://mcp.trunk.io/mcpclaude mcp add --transport http io-trunk https://mcp.trunk.io/mcp{"mcpServers":{"io-trunk":{"type":"http","url":"https://mcp.trunk.io/mcp"}}}Open in Cursor{"servers":{"io-trunk":{"type":"http","url":"https://mcp.trunk.io/mcp"}}}Open in VS Code{"mcpServers":{"io-trunk":{"type":"http","url":"https://mcp.trunk.io/mcp"}}}{"mcpServers":{"io-trunk":{"serverUrl":"https://mcp.trunk.io/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
Details
From the project READMETrunk.io MCP Server
Leverage the power of Trunk Flaky Tests from your IDE, or the AI application of your choosing.
Use MCP Server
Trunk Flaky Tests comes with a Model Context Protocol (MCP) server. AI applications like Claude Code or Cursor can use MCP servers to connect to data sources, tools, and workflows — enabling them to access key information and perform tasks.
Supported AI Applications
| Application | Supported | Guide | Plugin |
|---|---|---|---|
| Cursor | Yes | Setup guide | Cursor plugin |
| Claude Code | Yes | Setup guide | Claude Code plugin |
| GitHub Copilot | Yes | Setup guide | |
| Gemini CLI | Yes | Setup guide |
Note
Gemini Code Assist and Windsurf are not supported due to their limited support for MCP servers.
Quick Start
Cursor
Add to .cursor/mcp.json:
{
"mcpServers": {
"trunk": {
"url": "https://mcp.trunk.io/mcp"
}
}
}
Claude Code
claude mcp add trunk --transport streamable-http https://mcp.trunk.io/mcp
GitHub Copilot
Add to .vscode/mcp.json:
{
"servers": {
"trunk": {
"type": "http",
"url": "https://mcp.trunk.io/mcp"
}
}
}
Gemini CLI
Add to ~/.gemini/settings.json:
{
"mcpServers": {
"trunk": {
"httpUrl": "https://mcp.trunk.io/mcp"
}
}
}
API
The MCP server is available at https://mcp.trunk.io/mcp and exposes the following tools:
| Tool | Description |
|---|---|
fix-flaky-test | Retrieve root cause analysis and fix suggestions for flaky tests |
setup-trunk-uploads | Generate a setup plan to upload test results to Trunk |
Authorization
The Trunk MCP server supports the OAuth 2.0 + OpenID Connect standard for MCP authorization. When connecting from a supported client, you will be prompted to authenticate via your Trunk account.
Made with love by the Trunk.io team
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.