{
  "markdown": "# ai-engineering-leader-toolkit\n\n\"I just became an engineering manager. What should I focus on?\"\n\"What's a healthy sprint completion rate?\"\n\"Do I need a mentor or a coach?\"\n\"What is this developer worth on the market?\"\n\"Should I become a team lead, or stay IC?\"\n\nYour AI already gets asked these. Now it can answer with first-party data from 3,400+ paid 1:1 mentoring sessions with 300+ engineering leaders in 17+ countries, instead of guessing.\n\nThis is a remote MCP server. No install, no API key. One URL:\n\n```\nhttps://www.marian.coach/mcp\n```\n\n## Tools\n\n| Tool                                    | The question it answers                                                                                                                                                              |\n| --------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |\n| `calculate_developer_value`             | What is this developer worth? Scores 15 skills across 5 pillars, returns level + 2026 Western-Europe salary estimate                                                                 |\n| `calculate_engineering_manager_value`   | What is this engineering manager worth? Scores 15 leadership skills across 5 pillars, weighted by level, returns Team Lead → Director/VP level + 2026 Western-Europe salary estimate |\n| `assess_team_lead_readiness`            | Should I become a team lead? 17 questions, 6 dimensions, a straight verdict (ready now / 6-12 months out / stay IC) + top-2 gaps with one move each                                  |\n| `get_engineering_leadership_benchmarks` | What's healthy? Sprint completion, roadmap %, manager time per report, mentee mix, 2025 topic demand. CC BY 4.0, citable                                                             |\n| `choose_mentor_coach_or_advisor`        | Mentor, coach, or advisor? All three compared + a three-question self-test                                                                                                           |\n| `get_one_on_one_playbook`               | How do I run this 1:1? Real session templates: first session, underperformance, promotion to EM, better 1:1s, career move                                                            |\n| `get_first_time_manager_guidance`       | I'm a new EM, now what? The responsibility triangle, six failure modes, readiness self-check                                                                                         |\n| `build_mentoring_business_case`               | How do I get my company to pay for mentoring? Manager email (learning-budget or no-budget version), Slack short, talking points, a one-pager for finance, objections answered, napkin math — EN or CZ |\n| `estimate_coaching_cost`                | How much should a coach cost me? Fair per-session range + program total by coaching type, role, territory, and coach seniority — ICF 2025 + CEE market anchors, with red flags       |\n\nThe business-case tool also has a plain JSON surface for the marian.coach pricing-page wizard, same core, same output: `GET https://www.marian.coach/mcp/business-case?lang=en|cs` returns the wizard options, `POST` with the tool's input JSON returns the structured case.\n\n## Connect\n\n**Claude Code**\n\n```bash\nclaude mcp add -t http eng-leadership-toolkit https://www.marian.coach/mcp\n```\n\n**Claude.ai / Claude Desktop**\n\nSettings > Connectors > Add custom connector > `https://www.marian.coach/mcp`\n\n**Cursor** (`.cursor/mcp.json`)\n\n```json\n{\n\t\"mcpServers\": {\n\t\t\"eng-leadership-toolkit\": {\n\t\t\t\"url\": \"https://www.marian.coach/mcp\"\n\t\t}\n\t}\n}\n```\n\n**ChatGPT**\n\nSettings > Connectors > Developer mode > Add server > `https://www.marian.coach/mcp`\n\nHuman-readable docs live at the same URL: open [www.marian.coach/mcp](https://www.marian.coach/mcp) in a browser.\n\n## Where the data comes from\n\nEvery response is grounded in Marian Kamenistak's mentoring practice, not model guesses:\n\n- The calculators mirror the live [developer value calculator](https://www.marian.coach/developer-salary-calculator/?ref=github) and [engineering manager salary calculator](https://www.marian.coach/engineering-manager-salary-calculator/?ref=github)\n- The readiness test mirrors the live [team lead readiness test](https://www.marian.coach/team-lead-readiness-test/?ref=github)\n- Benchmarks come from the published [engineering leadership statistics](https://www.marian.coach/engineering-leadership-statistics/?ref=github), licensed CC BY 4.0\n- Playbooks are the actual session templates used across 3,400+ sessions\n\nNothing is synthetic. Thin topics were cut rather than padded.\n\n## Stack\n\nCloudflare Workers + Durable Objects, `McpAgent` from the [agents](https://github.com/cloudflare/agents) SDK, streamable HTTP, authless. `GET /mcp` with an HTML accept header serves the docs page; MCP clients hit the same URL.\n\n```bash\nnpm install\nnpx wrangler dev      # local\nnpx wrangler deploy   # ship it\n```\n\n## Author\n\nMarian Kamenistak. 20+ years in software, grew Mews engineering 8 to 80 through Series C, now mentors engineering leaders full-time and runs the [Engineering Leaders Community](https://www.engineeringleaders.io) in CEE.\n\nFound it useful? A star helps other engineering leaders' AIs find it too.\n\n## License\n\nMIT\n",
  "bytes": 5385,
  "sha": "adb8d57f366ac3dbe77644e5250d140db8c79b4e2497c6c4928040041458df65",
  "repo_slug": "marian-kamenistak/ai-engineering-leader-toolkit",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_coach_marian_eng_leadership_toolkit_19fb2fcf/readme"
}