marian-coach-eng-leadership-toolkitBLOCK
MCP server: engineering leadership answers from 3,662 mentoring sessions. Benchmarks, 1:1 playbooks, developer value calculator. One URL, no install.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
"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
b117ece84489OBSERVED · 2026-10-10Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.
claude mcp add ai-engineering-leader-toolkit -- npx -y [email protected]
{
"mcpServers": {
"ai-engineering-leader-toolkit": {
"command": "npx",
"args": [
"-y",
"[email protected]"
]
}
}
}Exposed tools (2)
2 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
get_more_tools | read | |
get_started | read |
Trust audit
BLOCKgrade D · trust 69/100 Do not install this without reading the findings. The audit found something that could harm you or your machine.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | FAIL |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | WARN |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- UNDECLARED (1 observation(s))
- Network
- declared (5 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (8)
/^(delete_user|delete_database|drop_table|run_sql|run_shell|execute_command|sudo|admin_login|reset_password|read_secrets|get_api_key|get_env|get_config|read_file|write_file|list_files|send_payment|tra
streamable-http
.oxfmtrc.json
.oxlintrc.json
join(ROOT, "../../web/mc-web/public/.well-known/agent-card.json");
@a2a-js/sdk, agents, zod, esbuild, oxfmt, oxlint, vitest, wrangler
> Work out whether 1:1 leadership mentoring fits your situation, and what it would cost, in about sixteen minutes. Nine tools walk through focus areas, package options and a dated session plan, then c
system use found in code, not declared in the description
Gates applied: no_behavioural_pass.
b117ece84489full audit observations/trust-audit/mcp-server/marian-kamenistak__ai-engineering-leader-toolkit.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-10 | b117ece84489 | BLOCK | D | 69 | first audit |
Questions
What is the marian-coach-eng-leadership-toolkit MCP server?
MCP server: engineering leadership answers from 3,662 mentoring sessions. Benchmarks, 1:1 playbooks, developer value calculator. One URL, no install.
What tools does marian-coach-eng-leadership-toolkit expose?
2 in total: 2 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is marian-coach-eng-leadership-toolkit safe to connect to an agent?
No — not without reading the findings first. The audit graded it D (69/100) and found 1 critical or high issue in the source. Each one is listed on this page with the file and line it is on.
What credentials does marian-coach-eng-leadership-toolkit need?
No credential environment variables were found in its source, so it appears to need none.
How does marian-coach-eng-leadership-toolkit run?
It speaks streamable-http, so it runs as a service you connect to over the network. It is published on npm as ai-engineering-leader-toolkit at 1.7.1.
How current is this page?
The grade is for one exact copy of the source (b117ece84489), read on 2026-10-10. The repository is watched and re-audited when it changes.