BuildPulse

BuildPulse MCP Server

Name: BuildPulse MCP Server
Author: BuildPulse

A hosted Model Context Protocol server that puts BuildPulse CI test analytics inside your AI agent. Nine read-only tools cover flaky-test inventory, recent CI failures, per-run test results, flakiness % and code-coverage % for every repository your token can see. Works with Claude, ChatGPT, Cursor, VS Code, Windsurf, Cline, and any MCP-aware client.

Endpoint: https://mcp.buildpulse.io/mcp

Connect

You need a BuildPulse API token (bp_…) from buildpulse.io → Organization Settings → API Tokens, or sign in with OAuth when your client offers it.

Claude Code

claude mcp add --transport http buildpulse https://mcp.buildpulse.io/mcp

Claude.ai and ChatGPT connectors

Add a custom connector and paste https://mcp.buildpulse.io/mcp. Both clients complete the OAuth sign-in for you.

Cursor (`.cursor/mcp.json`)

{
  "mcpServers": {
    "buildpulse": {
      "url": "https://mcp.buildpulse.io/mcp",
      "headers": { "Authorization": "Bearer bp_YOUR_TOKEN" }
    }
  }
}

VS Code (`.vscode/mcp.json`)

{
  "servers": {
    "buildpulse": {
      "type": "http",
      "url": "https://mcp.buildpulse.io/mcp",
      "headers": { "Authorization": "Bearer bp_YOUR_TOKEN" }
    }
  }
}

Local stdio (Claude Desktop, Windsurf, Cline, Continue, Zed)

{
  "mcpServers": {
    "buildpulse": {
      "command": "npx",
      "args": ["-y", "@buildpulse/mcp"],
      "env": { "BUILDPULSE_TOKEN": "bp_YOUR_TOKEN" }
    }
  }
}

Tools

list_my_organizations — every organization the token can access; returns the id to pass as organization_id.
list_repositories — repositories BuildPulse monitors for an organization.
find_flaky_tests — a repository's flaky-test inventory over the last 14 days, by disruptiveness or recency.
get_test_history — recent disruption events for one test, with build URL and commit SHA.
list_recent_submissions — the most recent CI runs that uploaded results for a repository.
get_submission_test_results — per-test results for one CI run; filter to failures.
get_recent_failures — every test that failed across the last N CI runs, aggregated by test identity.
get_repo_flakiness — current flakiness % for a repository (last 14 days).
get_repo_coverage — current code-coverage % from the latest report.

Sessions with access to more than one organization pass organization_id on every repo-scoped call; the server never guesses which tenant you meant. Four guided prompts ship alongside: triage_flaky_tests, ci_health_check, explain_test_failure, whats_red.

Try asking

“Why is CI red on web-client? Show me the failing tests from the last run.”
“Which tests in platform-api have been flakiest this week, and where do they fail?”
“How well tested is agents? Give me flakiness and coverage.”
“Which tests failed in more than one of the last 10 runs of test-reporter-lambdas?”