run_tests

11 registry entries were observed exposing a tool named run_tests — none of them flagged as a privileged capability.

Every row is point-in-time scan output, dated below. Forge has an observed tool surface for 12,342 of 40,590 scannable entries (30%) — an entry that has not been scanned cannot appear here, so absence from this list is not evidence that an entry does not expose this tool.

  1. gdharnessMCPattestedtrust 85/100 · A
    v1.1.62
    ↓ 6k/wk
    ★ 2

    A harness for driving a Godot 4 project from an agent: addons, runtime bridge, MCP server, CLI.

    ClaudeCursorCopilotGemini
    io.github.AurelioloMIT3d agonpmGitHubobserved · static extraction
    mcp
  2. playwright-report-mcpMCPattestedtrust 85/100 · A
    v3.4.0
    ↓ 239/wk

    MCP server for running Playwright tests and reading structured results — designed for AI agents doing test failure analysis

    ClaudeCursorCopilotGemini
    io.github.hubertgajewskiMIT17d agonpmGitHubobserved · static extraction
    playwrightmcpmodel-context-protocoltestingtest-resultsai
  3. io.github.programinglive/dev-workflow-mcp-serverMCPattestedtrust 85/100 · A
    v1.4.6
    ★ 1

    MCP server to enforce development workflow discipline

    ClaudeCursorCopilotGemini
    io.github.programingliveUnknown10mo agonpmGitHubobserved · static extraction
    mcp
  4. io.github.hubertgajewski/playwright-report-mcpMCPattestedtrust 85/100 · A
    v3.2.2

    Run Playwright tests and surface structured results for AI agents doing test failure analysis.

    ClaudeCursorCopilotGemini
    io.github.hubertgajewskiUnknown4mo agonpmGitHubobserved · static extraction
    mcp
  5. forkmindMCPcommunitytrust 60/100 · B
    v0.9.0
    ↓ 640/wk

    Local-first LLM state branching, debugging & context offloading. Treat AI context windows like a Git repo — capture, branch, and archive context as encrypted DAG capsules.

    ClaudeCursorCopilotGemini
    Medhovarsh BayyapureddiMIT2mo agonpmGitHubobserved · static extraction
    llmopenaianthropicollamadebuggingproxy
  6. smolanalyticsMCPcommunitytrust 60/100 · B
    v0.21.0
    ↓ 84/wk
    ★ 3

    End-to-end tests without test code. Write one sentence, an agent drives a real browser and returns a verdict, and a passing run is recorded so the next one calls no model. Runs on any URL with no account.

    ClaudeCursorCopilotGemini
    Arjun VarmaSEE LICENSE IN LICENSE1mo agonpmGitHubobserved · static extraction
    e2e-testingend-to-end-testingtestingtest-automationplaywrightqa
  7. io.github.jdhart81/verdigraph-mcpMCPcommunitylivetrust 60/100 · B
    v0.2.0
    ★ 1

    Paid hosted MCP for agent-to-agent compute routing. 25% of net revenue funds conservation.

    ClaudeCursorCopilotChatGPTGemini
    io.github.jdhart81Unknown4mo agoGitHubobserved · static extraction
    mcp
  8. ai.gatetest.www/gatetestMCPcommunitytrust 60/100 · B
    v1.56.4

    120-module QA gate. Give Claude eyes (screenshots), ears (Sentry errors), and hands (verify fixes).

    ai.gatetest.wwwUnknown3mo agoGitHubobserved · static extraction
    mcp
  9. com.floot/flootMCPcommunitylivetrust 60/100 · B
    v1.0.0

    Build and publish full-stack web and mobile apps on Floot from any MCP client. Building is free.

    ClaudeCursorCopilotChatGPTGemini
    com.flootUnknown3mo agoobserved · live tools/list
    mcp
  10. io.github.fasteningcode/claudetestMCPcommunitytrust 60/100 · B
    v0.0.3

    Playwright & Appium test automation for Claude. Generate tests, diagnose failures, open fix PRs.

    ClaudeCursorCopilotGemini
    io.github.fasteningcodeUnknown5mo agonpmobserved · static extraction
    mcp
  11. obra-ctoMCPcommunitytrust 60/100 · B
    v0.3.0

    Obra CTO: a local-first MCP that scores a codebase's Build Readiness. Your code never leaves your machine; your own Claude reads it and runs your tests. The free preview of Obra's role lineup.

    ClaudeCursorCopilotGemini
    ObraApache-2.03mo agonpmGitHubobserved · static extraction
    mcpclaudecode-reviewbuild-readinesstechnical-due-diligenceinvestor-readiness

All indexed toolsSearch the registry for run_tests