Engineering Leadership Toolkit
About
Free remote MCP server giving AI assistants direct access to data from a mentoring practice: 3,400+ paid 1:1 sessions with 300+ engineering leaders since 2019.
Details
- Author
- Unknown
- Categories
- Productivity, Other
Jump to
Free remote MCP server giving AI assistants direct access to data from a mentoring practice: 3,400+ paid 1:1 sessions with 300+ engineering leaders since 2019.
Free AI coaching tools. Every one ends with a verdict.
Nine tools, built from 3,400+ mentoring sessions with 300+ engineering leaders across 17 countries. Eight open in the browser. All nine your agent can call over MCP. Four ship as Claude skills. No login, no email gate. What you get back is a number you can use, not a reading list.
Browser, agent, or both. Start with the readiness test if you don't know which one you need.
Point Claude, Cursor, or any MCP client at one endpoint and your agent gets 9 tools: salary math, readiness verdicts, benchmark data from 3,400+ sessions. No key, no signup, MIT-licensed,source on GitHub.
claude mcp add --transport http eng-leadership-toolkit https://www.marian.coach/mcp
{ "mcpServers": { "eng-leadership-toolkit": { "url": "https://www.marian.coach/mcp" } } }
Settings → Connectors → Add custom connector, pastehttps://www.marian.coach/mcp. No JSON, no restart.
git clone https://github.com/marian-kamenistak/<skill> ~/.claude/skills/<skill>
MCP:coach.marian/eng-leadership-toolkitin theofficial MCP registry, endpointwww.marian.coach/mcp(streamable HTTP, works as a plain JSON-RPC API too). Skills install from GitHub, MIT. The benchmarks dataset is CC BY 4.0: cite it, build on it.
Yes. No login, no email gate, no trial that expires. All nine also run inside your agent over MCP without an API key, and the source is MIT on GitHub, so you can read exactly what they do before you run them.
They are estimates, not offers. The 2026 numbers come from Western-Europe market data weighted by the level the calculator scores you at. Use the range as a negotiation anchor, not a promise. Country and company stage move a real offer more than the calculator can see.
What is the MCP server, and why use it instead of the web page?
MCP (Model Context Protocol) lets an AI agent call a tool directly. Point Claude, Cursor, or any MCP client athttps://www.marian.coach/mcpand your agent gets 9 tools it can run mid-conversation: salary math, readiness verdicts, benchmark data from 3,400+ sessions. No key, no signup. Worth it when you want the answer inside the doc you're already writing.
Yes. The Engineering Leadership Benchmarks dataset is CC BY 4.0: cite it and build on it. It comes from 3,400+ mentoring sessions with 300+ engineering leaders across 17 countries, which is first-party data you won't find in a vendor report.
Nothing automatic. No drip sequence, no sales call booked on your behalf. If a result surprised you, or confirmed something you have been circling for months, book the free intro call and we talk about that.
The tools give you a verdict in three minutes. What they can't tell you is whether to take the role, how to run the conversation with your VP, or which of your two gaps to close first. That's the part I do, with 300+ engineering leaders across 17 countries so far.
Book the free intro call →Free. No pitch deck. If it's not a fit, I say so.
Fitimio helps your AI assistant track your meals, calories, workouts, goals, body metrics, and health notes so it can give answers based on your real progress.
AI workout coach MCP server. Access training data, workout history, personal records, and body progress through Claude Desktop.
MCP server for Oura Ring data with smart analysis tools
Access the Whoop API to query cycles, recovery, strain, and workout data.
Local MCP server that exposes Whoop recovery, sleep, and strain data to AI agents
Read-only access to your Alma nutrition data, meals, goals, scores, workouts, weight history, pantry, and grocery list.
AI-powered cycling training coach: personalized training plans, daily workouts, nutrition, strength training, fitness metrics (FTP, VO2Max), and Strava, Garmin, Wahoo, MyWhoosh, and Rouvy integrations.
Access your Fitbit health and fitness data for personalized insights.
Access Garmin Connect running data and training plan information.
Local-first Garmin data warehouse: sync once into SQLite you own, then analyze trends, correlations, baselines and anomalies offline, even when Garmin's API breaks.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
