Eng Leadership Toolkit

coach.marianPublished by marian.coachOfficial publisherv1.7.1Updated Oct 24, 2026

Engineering leadership benchmarks, 1:1 playbooks, developer value calculator. 3,662 sessions.

VerifiedStreamable HTTPWeb executableProductivity & WorkflowFinanceKnowledge & Memory

Overview

AI-generated overview

Remote MCP server giving assistants engineering-leadership benchmarks, 1:1 playbooks, readiness tests and developer/manager value calculators.

What you can do
  • Get a greeting and a menu of the questions the server answers, plus a check for further tools
  • Score a developer's or engineering manager's skills across five pillars and get a level and a 2026 Western-Europe salary estimate
  • Run a 17-question team lead readiness test with a verdict and top gaps
  • Retrieve engineering leadership benchmarks: sprint completion, roadmap share, manager time per report, topic demand
  • Get 1:1 session templates, first-time manager guidance, and a mentor-versus-coach-versus-advisor comparison
  • Estimate coaching market rates and build a business case for company-funded mentoring
When to use it
Useful when an assistant is asked about engineering management careers: whether to move from IC to lead, how to run a difficult 1:1, what healthy team metrics look like, what a developer or EM is worth, or how to justify mentoring spend to an employer.
Requirements
A remote streamable HTTP endpoint; no install, API key or account is required. Add the server URL as a custom connector in the client (Claude Code, Claude.ai/Desktop, Cursor, ChatGPT). Network access to the provider's domain is needed.
Before you install
The salary, level and coaching-cost outputs are estimates from one mentoring practice and published market anchors, not authoritative compensation data. The business-case tool drafts emails and documents aimed at an employer, so review before sending. Skill assessments are self-reported inputs sent to a third-party server.

Installation

In SourceWeft

  1. Open Eng Leadership Toolkit in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/coach.marian%2Feng-leadership-toolkit/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "eng-leadership-toolkit": {
      "type": "http",
      "url": "https://www.marian.coach/mcp"
    }
  }
}

README

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/mcp

Tools

ToolThe question it answers
calculate_developer_valueWhat is this developer worth? Scores 15 skills across 5 pillars, returns level + 2026 Western-Europe salary estimate
calculate_engineering_manager_valueWhat 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_readinessShould 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_benchmarksWhat's healthy? Sprint completion, roadmap %, manager time per report, mentee mix, 2025 topic demand. CC BY 4.0, citable
choose_mentor_coach_or_advisorMentor, coach, or advisor? All three compared + a three-question self-test
get_one_on_one_playbookHow do I run this 1:1? Real session templates: first session, underperformance, promotion to EM, better 1:1s, career move
get_first_time_manager_guidanceI'm a new EM, now what? The responsibility triangle, six failure modes, readiness self-check
build_mentoring_business_caseHow 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_costHow 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

bash
claude mcp add -t http eng-leadership-toolkit https://www.marian.coach/mcp

Claude.ai / Claude Desktop

Settings > Connectors > Add custom connector > https://www.marian.coach/mcp

Cursor (.cursor/mcp.json)

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:

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.

bash
npm installnpx wrangler dev      # localnpx wrangler deploy   # ship it

Author

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

Source: README.md at commit 21780b4

Tools

11

get_started

Start here — what can this MCP server do?

Call this for a greeting (hi, hello), a connectivity/liveness test, 'what can you do', or any message too general to match a specific tool below. Returns the full menu of real questions this server answers, each mapped to the tool name that answers it, so the next call can go straight to the right tool.

Parameterscontext

get_more_tools

More tools? Check here first — also answers a plain hello/liveness ping

Check for additional tools whenever your task might benefit from specialized capabilities, even if existing tools could work as a fallback. Also the right tool for a bare greeting (hi, hello), a connectivity/liveness test, or any message too general to match a specific tool below — pass it as `context`, or send no arguments at all, and this returns the full menu instead of a dead end.

Parameterscontext

calculate_developer_value

Developer value & salary calculator

Assess a software developer's market value: score 15 skills across 5 pillars (core craft, systems & judgment, impact & ownership, collaboration & influence, AI leverage), get a weighted total score, seniority level, and a 2026 Western-Europe gross salary estimate. Same logic as the live calculator at marian.coach. Unscored skills default to the level's baseline.

Parameterslevelscorescontext

calculate_engineering_manager_value

Engineering manager value & salary calculator

Assess an engineering leader's market value: score 15 leadership skills across 5 pillars (people & talent, delivery & execution, technical direction, stakeholder influence, AI leverage), weighted by current level, get a total score, a level from Team Lead to Director/VP of Engineering, and a 2026 Western-Europe gross salary estimate. Same logic as the live EM salary calculator at marian.coach. Unscored skills default to the level's baseline.

Parametersleveltrackscorescontext

assess_team_lead_readiness

Team lead readiness test — should this engineer become a team lead?

Answers "should I become a team lead?" with the same 17-question test as the live tool at marian.coach: 6 dimensions (people appetite, letting go of code, ownership beyond your tickets, translation & saying no, motivation, org reality), a straight verdict — ready now / 6-12 months out / stay IC (and that's fine) — plus the top-2 gap dimensions with one concrete move each. Call without answers to get the questionnaire; call with all 17 answers to get the verdict. Built from 3,662 mentoring sessions.

Parametersanswerscontext

get_engineering_leadership_benchmarks

Engineering leadership benchmarks & mentoring statistics

Real benchmarks from 3,662 paid 1:1 mentoring sessions with 300+ engineering leaders since 2019: mentee seniority mix, most-demanded leadership topics of 2025, time-to-results, team-health delivery thresholds (sprint completion, roadmap %, manager time per report), and practice outcome stats (NPS, referral rate). First-party data, CC BY 4.0 — citable.

Parameterstopiccontext

choose_mentor_coach_or_advisor

Mentor vs coach vs advisor — which one do you need?

Decide whether an engineering leader needs a mentor, a coach, or an advisor: what each brings, the typical question each answers, whether domain experience is required, time horizon, and a three-question self-test. Based on 3,662 mentoring sessions.

Parameterscontextsituation

get_one_on_one_playbook

1:1 playbooks for engineering managers

Situation-specific 1:1 scripts and templates from Marian Kamenistak's mentoring practice: first mentoring/direction-setting session, underperformance conversation, promoting a developer to manager, fixing status-update 1:1s, and the 10-question career-move checklist. These are the actual templates used across 3,662 sessions.

Parameterscontextsituation

get_first_time_manager_guidance

First-time engineering manager readiness & failure modes

Guidance for the IC→manager transition: the EM responsibility triangle (leadership/processes/delivery — pick two), the six most common first-time-manager failure modes, readiness self-check questions, and what the first months should look like. 52% of Marian's 300+ mentees arrive exactly at this transition.

Parameterscontext

estimate_coaching_cost

Coaching cost estimator — what should a coach cost?

Fair market rate for coaching or mentoring in 2026, by coaching type, client role, coach territory, coach seniority, and engagement length. Returns a per-session range, program total, and red flags (too cheap / brand margin). Anchored to ICF Global Coaching Study 2025, Tandem Coach 2026 credential bands, and CEE market survey data. Same logic as the live calculator at marian.coach.

Parametersscopecontextterritoryclient_rolecoaching_typecoach_seniority

build_mentoring_business_case

Get your company to pay: ROI math, manager email, one-pager

Build the case that gets your company to pay for leadership mentoring — everything on marian.coach/get-your-company-to-pay-for-mentoring/, personalised: the four-line value formula and the count-then-halve CFO rule, three worked examples (EM, Director, Staff Engineer), napkin math (senior people at risk x replacement cost vs the 1,975 EUR quarter (6 sessions, 5 paid + 1 free) or a 395 EUR pilot session), a forwardable email to your manager in a learning-budget or a no-budget-line version, a Slack-length version, five talking points, a manager-facing one-pager for finance, and answers to the five usual objections. English or Czech, tykani or vykani. Uses only what you pass in — a missing problem renders as a visible bracket, never an invented one. From 3,662 mentoring sessions at marian.coach.

Parameterskpislangrolecompanycontextproblemdecide_byformalitysituationteam_sizeyour_namealternatives+5 more

Version history

2
  1. v1.7.1LatestOct 9, 2026
  2. v1.4.0Sep 16, 2026

Score

100% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

Other Marian integrations