Manual setup required. We don't have a verified install command for this server. Follow the maintainer README and use the raw config below as a starting point.
1
Prepare the server locally
Run this once before adding it to Claude Code.
npm install
npm run build2
Add it to Claude Code
Paste the maintainer's config below, then edit any placeholder values.
{
"projectRoot": ".",
"storage": {
"databasePath": ".autodev/logs/autodev.db",
"screenshotsDir": ".autodev/logs/screenshots"
},
"commands": {
"test": "npm test"
},
"browser": {
"headless": true,
"timeoutMs": 15000
},
"pipeline": {
"maxIterations": 3
}
}See the autocoding-mcp README for full setup instructions.
3
Make your agent remember this setup
autodev-mcp's config, env vars, and the gotchas you hit — recalled in every future Claude Code, Cursor, and Codex session.
npx conare@latestFree · one command · indexes the sessions already on disk. Set up in the browser instead →
What it does
- Dual-track testing combining CLI execution and Playwright browser automation.
- Persistent logging of sessions, console output, network requests, and errors to SQLite.
- Automated requirement and optimization generation based on test evidence.
- Integrated Git workflow with automatic commits and sensitive file protection.
- Context management with compacting suggestions to optimize LLM token usage.
Tools 9
run_testsExecutes the original CLI test flow.browser_openOpens a browser session at a specified URL.browser_interactPerforms interactions within the browser session.browser_assertPerforms assertions on the current browser state.browser_screenshotCaptures a screenshot of the current browser page.run_pipelineExecutes a combined CLI and browser test pipeline.propose_requirementsGenerates 10 requirement or optimization directions based on test logs.git_commit_featureCommits changes to the git repository after a feature is complete.test_get_session_logsRetrieves logs, summaries, and screenshot paths for a session.Try it
→Run the full test pipeline and generate optimization suggestions for my current project.
→Open the browser to my local development server and perform an assertion on the login button.
→Capture a screenshot of the current browser state and retrieve the latest session logs.
→Check the current git status and commit the recent changes if the tests passed.
→Compare the logs of my last two test sessions to identify regressions.
Original README from rookiejefren/autocoding-mcp
AutoDev MCP (Dual-Track Testing)
AutoDev MCP is a TypeScript MCP server that keeps your original CLI testing and adds an extra Chrome Dev (browser) testing track with persistent logs.
What it does
- Keeps original test flow via CLI (
run_tests) - not replaced - Adds browser test flow (
browser_*tools) via Playwright + CDP events - Persists everything to SQLite:
- sessions
- logs (cli/browser/console/error/network/assertion)
- screenshots
- Supports combined execution via
run_pipeline - After pipeline completion, automatically provides 10 requirement/optimization directions (中文输出)
Install
npm install
npm run build
Run MCP server (stdio)
npm run start
For local development:
npm run dev
Optional config: `autodev.config.json`
{
"projectRoot": ".",
"storage": {
"databasePath": ".autodev/logs/autodev.db",
"screenshotsDir": ".autodev/logs/screenshots"
},
"commands": {
"test": "npm test"
},
"browser": {
"headless": true,
"timeoutMs": 15000
},
"pipeline": {
"maxIterations": 3
},
"compact": {
"enabled": true,
"warningThreshold": 0.8,
"compactThreshold": 1.0,
"estimatedMaxChars": 120000
},
"git": {
"enabled": true,
"autoCommitOnFeatureComplete": true,
"defaultCommitPrefix": "feat",
"protectSensitiveFiles": true,
"sensitiveFilePatterns": [
"(^|/)\\.env(\\..*)?$",
"(^|/)credentials\\.json$",
"(^|/)secret(s)?(\\.|$)",
"(^|/).+\\.pem$",
"(^|/).+\\.key$"
]
}
}
Tool overview
CLI track (original)
run_testsgenerate_tests(stub)fix_failures(stub)
Browser track (new, additional)
browser_openbrowser_navigatebrowser_interactbrowser_assertbrowser_screenshotbrowser_get_consolebrowser_get_errorsbrowser_get_networkbrowser_close
Orchestration/query
run_pipeline(CLI first, browser optional)propose_requirements(always outputs 10 directions)check_compact(检查上下文占用并给出 none/warn/compact 建议)git_commit_feature（小功能完成后按策略提交 git）git_status_summary（查看当前仓库改动状态）test_get_session_logstest_compare_sessions
Example workflow
- Run original tests:
- call
run_tests
- call
- Start browser session:
- call
browser_openwith URL
- call
- Interact and assert:
browser_interactbrowser_assert
- Capture screenshot if needed:
browser_screenshot
- Close and finalize summary:
browser_close
- Query persisted logs:
test_get_session_logs
- Generate next-cycle demand directions:
propose_requirements
run_pipeline also includes suggestedRequirements in the final output so you can directly pick your next approved requirement.
run_pipeline now also returns compactSuggestion:
none: 上下文充足，继续执行warn: 上下文超过预警阈值（默认 80%），建议当前小任务结束后 compactcompact: 上下文达到 compact 阈值（默认 100%），建议立即 compact
run_pipeline 现在也会在测试通过后尝试执行 gitCommit：
- 若目录是 git 仓库且存在可提交改动，会自动提交
- 若不是 git 仓库，自动跳过并给出原因
- 默认会拦截疑似敏感文件（如
.env、*.pem、*.key）
测试日志与截图位置
- SQLite 数据库：
.autodev/logs/autodev.db - 截图目录：
.autodev/logs/screenshots
你可以通过 MCP 工具查看：
test_get_session_logs：按 sessionId 拉取日志、摘要、截图路径test_compare_sessions：对比两次测试结果
评分标准（需求方向）
每条方向的评分由以下字段组成：
impact：影响面（1-10）confidence：把握度（1-10）effort：工作量映射分值（S=2, M=5, L=8）
公式：
priorityScore = (impact × confidence) / effort
分数越高，优先级越高。
Notes
- Browser track is explicitly additive and independent from original CLI tests.
generate_testsandfix_failuresare stubs in this version and intentionally logged for future extension.- Requirement generation is evidence-based (sessions/logs/assertions/errors) and returns exactly 10 scored directions each cycle (中文输出).