coach.marian/eng-leadership-toolkit

by marian.coach · remote · no sign-in to list tools · v1.7.1 · published by coach.marian

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

Changes · 7

Compare Registry entry

11 tools: 7 change things and 4 only read.

Scanned Oct 21, 2026

Deletes or cancels0Claude Code: deny
Can't be undone0Claude Code: ask
Changes things7Claude Code: ask: see these tools
Only reads4Claude Code: allow: see these tools

2 checks matched something in the tool definitions. No finding is not a safety guarantee. How the checks work.

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

Findings

Matches of fixed checks, with the text they matched.

1 warn1 info

Warnget_started
The server marks "get_started" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
Matched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "get_started" says "get": a word for reading.
What this check looks for
Infoestimate_coaching_cost
The description mentions "credential".
Matched text
description: "...Coaching Study 2025, Tandem Coach 2026 credential bands, and CEE market survey data. Same..."
What this check looks for

Tools

Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.

11 tools

Changes things 7Creates or changes something that can be changed back.Claude Code: ask

assess_team_lead_readinessAnswers "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 tic…No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it
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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
build_mentoring_business_caseBuild 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…No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it
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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
calculate_developer_valueAssess a software developer's market value: score 15 skills across 5 pillars (core craft, systems & judgment, impact & ownership, collaboration & influence, AI leverage), get a wei…No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it
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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
calculate_engineering_manager_valueAssess an engineering leader's market value: score 15 leadership skills across 5 pillars (people & talent, delivery & execution, technical direction, stakeholder influence, AI leve…No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it
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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
choose_mentor_coach_or_advisorDecide 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 horizo…No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it
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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
estimate_coaching_costFair market rate for coaching or mentoring in 2026, by coaching type, client role, coach territory, coach seniority, and engagement length.1 finding
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Info
  The description mentions "credential".
  Matched text
  description: "...Coaching Study 2025, Tandem Coach 2026 credential bands, and CEE market survey data. Same..."
  What this check looks for
Description, as the server wrote it
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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_startedCall 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.1 finding
Why it is in this group
- The name "get_started" says "get": a word for reading.
- The description's first verb is "call": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
  The server marks "get_started" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
  Matched text
  annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "get_started" says "get": a word for reading.
  What this check looks for
Description, as the server wrote it
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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false

Only reads 4Looks things up and changes nothing.Claude Code: allow

get_engineering_leadership_benchmarksReal 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, tea…No findings
Why it is in this group
- The name "get_engineering_leadership_benchmarks" says "get": a word for reading.
Description, as the server wrote it
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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_first_time_manager_guidanceGuidance for the IC→manager transition: the EM responsibility triangle (leadership/processes/delivery — pick two), the six most common first-time-manager failure modes, readiness s…No findings
Why it is in this group
- The name "get_first_time_manager_guidance" says "get": a word for reading.
Description, as the server wrote it
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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_more_toolsCheck for additional tools whenever your task might benefit from specialized capabilities, even if existing tools could work as a fallback.No findings
Why it is in this group
- The name "get_more_tools" says "get": a word for reading.
Description, as the server wrote it
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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_one_on_one_playbookSituation-specific 1:1 scripts and templates from Marian Kamenistak's mentoring practice: first mentoring/direction-setting session, underperformance conversation, promoting a deve…No findings
Why it is in this group
- The name "get_one_on_one_playbook" says "get": a word for reading.
Description, as the server wrote it
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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Install

Pinned to version 1.7.1. Values in angle brackets are yours to fill in.

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

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json

{
  "permissions": {
    "allow": [
      "mcp__eng-leadership-toolkit__get_more_tools",
      "mcp__eng-leadership-toolkit__get_engineering_leadership_benchmarks",
      "mcp__eng-leadership-toolkit__get_one_on_one_playbook",
      "mcp__eng-leadership-toolkit__get_first_time_manager_guidance"
    ],
    "ask": [
      "mcp__eng-leadership-toolkit__get_started",
      "mcp__eng-leadership-toolkit__calculate_developer_value",
      "mcp__eng-leadership-toolkit__calculate_engineering_manager_value",
      "mcp__eng-leadership-toolkit__assess_team_lead_readiness",
      "mcp__eng-leadership-toolkit__choose_mentor_coach_or_advisor",
      "mcp__eng-leadership-toolkit__estimate_coaching_cost",
      "mcp__eng-leadership-toolkit__build_mentoring_business_case"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. It assumes the server is installed as eng-leadership-toolkit. Review it before you use it.

Keep track

Get told when this server's tools change: a new tool, a new description, a new class.

https://anlyon.dev/servers/coach.marian/eng-leadership-toolkit/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Anlyon alternative

7 of these tools change something. Run those as governed actions.

Declare what an action changes, and Anlyon puts it under a shared limit, binds every approval to the exact request, and grades the outcome. It works on any HTTPS API you can describe as an action.

Anlyon does not run, proxy or govern this MCP server. A tool your own code calls directly is not routed through Anlyon and is not governed by it.

Import an OpenAPI spec →

Compare with other servers for the same product.

Source: MCP Registry · repository. Synced Oct 21, 2026, 17:47 UTC.

For agents: Markdown · JSON · report this listing