coach.marian/eng-leadership-toolkit
Engineering leadership benchmarks, 1:1 playbooks, developer value calculator. 3,662 sessions.
Install
Add this to your client's MCP configuration (Claude Desktop: claude_desktop_config.json; Cursor: .cursor/mcp.json; VS Code and others use the same "mcpServers" shape).
claude mcp add --transport http eng-leadership-toolkit 'https://www.marian.coach/mcp'{
"mcpServers": {
"eng-leadership-toolkit": {
"type": "http",
"url": "https://www.marian.coach/mcp"
}
}
}Documentation
From the project's README on GitHub, refreshed weekly. Links open on GitHub.
ai-engineering-leader-toolkit
"I just became an engineering manager. What should I focus on?" "What's a healthy sprint completion rate?" "Do I need a mentor or a coach?" "What is this developer worth on the market?" "Should I become a team lead, or stay IC?"
Your AI already gets asked these. Now it can answer with first-party data from 3,662 paid 1:1 mentoring sessions with 300+ engineering leaders in 17+ countries, instead of guessing.
This is a remote MCP server. No install, no API key. One URL:
https://www.marian.coach/mcpTools
| Tool | The question it answers |
|---|---|
calculate_developer_value | What is this developer worth? Scores 15 skills across 5 pillars, returns level + 2026 Western-Europe salary estimate |
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 |
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 |
get_engineering_leadership_benchmarks | What's healthy? Sprint completion, roadmap %, manager time per report, mentee mix, 2025 topic demand. CC BY 4.0, citable |
choose_mentor_coach_or_advisor | Mentor, coach, or advisor? All three compared + a three-question self-test |
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 |
get_first_time_manager_guidance | I'm a new EM, now what? The responsibility triangle, six failure modes, readiness self-check |
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 |
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 |
The 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.
Connect
Claude Code
claude mcp add -t http eng-leadership-toolkit https://www.marian.coach/mcpClaude.ai / Claude Desktop
Settings > Connectors > Add custom connector > https://www.marian.coach/mcp
Cursor (.cursor/mcp.json)
{
"mcpServers": {
"eng-leadership-toolkit": {
"url": "https://www.marian.coach/mcp"
}
}
}ChatGPT
Settings > Connectors > Developer mode > Add server > https://www.marian.coach/mcp
Human-readable docs live at the same URL: open www.marian.coach/mcp in a browser.
Where the data comes from
Every response is grounded in Marian Kamenistak's mentoring practice, not model guesses:
- The calculators mirror the live developer value calculator and engineering manager salary calculator
- The readiness test mirrors the live team lead readiness test
- Benchmarks come from the published engineering leadership statistics, licensed CC BY 4.0
- Playbooks are the actual session templates used across 3,662 sessions
Nothing is synthetic. Thin topics were cut rather than padded.
Stack
Cloudflare Workers + Durable Objects, McpAgent from the agents SDK, streamable HTTP, authless. GET /mcp with an HTML accept header serves the docs page; MCP clients hit the same URL.
npm install
npx wrangler dev # local
npx wrangler deploy # ship itAuthor
Marian 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 in CEE.
Found it useful? A star helps other engineering leaders' AIs find it too.
License
MIT
Frequently asked questions
What is coach.marian/eng-leadership-toolkit?
Engineering leadership benchmarks, 1:1 playbooks, developer value calculator. 3,662 sessions.
How do I install coach.marian/eng-leadership-toolkit?
It runs as a remote server. In Claude Code: claude mcp add --transport http eng-leadership-toolkit 'https://www.marian.coach/mcp'. For other clients, paste the JSON configuration from this page into their MCP settings.
Does coach.marian/eng-leadership-toolkit need an API key?
Its registry entry lists no required key or secret. Some features may still need an account with the service it connects to.
Is coach.marian/eng-leadership-toolkit open source?
Yes. Its code is on GitHub under the MIT license.
Who maintains coach.marian/eng-leadership-toolkit?
It is published by marian-kamenistak. AI.tn lists it but does not maintain or endorse it.
From the official MCP Registry. Listing is not an endorsement: review a server's code and permissions before giving it access to your data.