Coghelm: AI tools for leaders MCP Server
by thelconsultingcom.coghelm/coghelmv1.1.0
Curated AI tools for leaders: recommend and compare tools by job, plus 1:1 and board templates.
context tax
~1,573 tok/turn10 tools
security
97/100
cold start
hosted
freshness
Active2d ago
Our reading of Coghelm: AI tools for leaders, from the data
Coghelm: AI tools for leaders is an MCP server from thelconsulting, listed in the official MCP Registry.
Its 10 tools add about 1,573 tokens to every model turn (measured 2026-10-19).
Maintenance is active: the last public signal was 2 days ago (2026-10-17).
It runs as a hosted endpoint, so there is nothing to install.
Install Coghelm: AI tools for leaders MCP server
Install in Claude Code
claude mcp add --transport http coghelm https://coghelm.com/mcpInstall in Cursor
{
"mcpServers": {
"coghelm": {
"url": "https://coghelm.com/mcp"
}
}
}Install in Claude Desktop
{
"mcpServers": {
"coghelm": {
"command": "npx",
"args": [
"-y",
"mcp-remote",
"https://coghelm.com/mcp"
]
}
}
}Or add it as a custom connector under Settings → Connectors. The config above bridges via mcp-remote.
Install in VS Code
{
"servers": {
"coghelm": {
"type": "http",
"url": "https://coghelm.com/mcp"
}
}
}Install in Windsurf
{
"mcpServers": {
"coghelm": {
"serverUrl": "https://coghelm.com/mcp"
}
}
}Remote endpoints
- streamable-http
https://coghelm.com/mcp
Context tax
Connecting this server adds ~1,573 tokens of tool definitions to every model turn (moderate, 10 tools). Measured 2026-10-19 via its hosted endpoint; o200k tokenizer, worst case for clients that load all tools up front. How we measure
| Model | Per 1,000 turns | With prompt caching |
|---|---|---|
| Claude Opus 5.5 | $6.29 | $0.315 |
| Claude Sonnet 5.5 | $3.15 | $0.315 |
| Claude Haiku 5.5 | $0.157 | — |
Input prices as of 2026-10-06. Excludes your own prompt and output.
Tools (10)
draft_board_update_outline317 tokDraft a board/exec update outline (Markdown) with the proven structure: headline, asks first, numbers vs plan, wins, misses, risks, outlook. Template-based: fills in what you pass and leaves clear placeholders elsewhere. Never invents numbers.
draft_1on1_agenda315 tokDraft a structured 1:1 agenda (Markdown) for a manager and a direct report, time-boxed to the meeting length. Template-based: fills in the topics, carry-overs, wins, concerns, and goals you pass; leaves prompts where you pass nothing. Puts the report's topics first.
recommend_tools242 tokRecommend AI tools for a job a leader needs done (e.g. 'run better 1:1s', 'write a board update', 'research a competitor', 'grant writing'), using Coghelm's curated job guides and directory. Optional constraints: budget ('free' keeps only tools with a known free plan; 'low' ranks free plans first) and team size (small teams rank enterprise tools last). Returns ranked tools with reasons, pricing notes, and Coghelm links.
compare_tools126 tokCompare 2-6 Coghelm tools by slug (e.g. ['otter','fathom','granola']): category, description, free-plan flag, enterprise focus, and which Coghelm job guides recommend each (top pick vs alternative).
search_tools108 tokSearch Coghelm's curated AI tools for leaders (and job guides) by keyword, e.g. 'meeting notes', 'grant writing', 'slides'.
get_offer83 tokMachine-readable offer for the Leader's AI Playbook: $29 USD one-time, digital PDF, 30-day full refund, terms URL, support email, and a Stripe buy URL. Purchases must be completed by the human at checkout.
playbook_preview77 tokPreview Coghelm's Leader's AI Playbook (PDF): table of contents, what each chapter contains, two sample prompts, and the offer summary. Use when a user wants deeper prompts/templates for leadership work.
get_tool74 tokGet details for one tool by slug (e.g. 'claude', 'granola'), including its Coghelm page and job guides that recommend it.
get_job_guide69 tokGet a full job guide by slug: intro, top pick and why, alternatives, how-to steps, and FAQ.
list_jobs65 tokList Coghelm's job guides (jobs leaders do, like running 1:1s or writing a board update), each with its top pick tool.
Security signals
97/100 — no known issues found as of 2026-10-19, from the checks below. This is not a guarantee of safety; review what a server can do before connecting it.
Deductions
- No security policy (SECURITY.md)-3
Checks
- ✓Repository hygiene (archived, activity, license, security policy)
- ✓Tool descriptions (prompt-injection and hidden-text heuristics)
- ○Package metadata (install scripts, provenance) — pending
- ○Source scan (secrets, CVEs, risky code) by vectra-guard — pending
Scan it yourself before installing with vectra-guard, the open-source agent security CLI. Scoring rules
Freshness
Active — last maintenance signal 2d ago. The newest of the signals below sets the band.
Last commit (default branch)
2026-10-17 · 2d ago · GitHub
Latest release
no data · GitHub
Package published
no data · npm/PyPI
Registry entry updated
2026-10-17 · 2d ago · official registry · v1.1.0
FAQ
›How do I install the Coghelm: AI tools for leaders MCP server in Claude Code?
Run: claude mcp add --transport http coghelm https://coghelm.com/mcp. For Cursor, VS Code, Claude Desktop and Windsurf, use the install tabs above.
›Does Coghelm: AI tools for leaders require an API key?
No required environment variables are declared in its published metadata.
›Can I use Coghelm: AI tools for leaders as a remote (hosted) MCP server?
Yes. It is a hosted MCP server; connect to its URL with any client that supports remote MCP.
›Is Coghelm: AI tools for leaders in the official MCP registry?
Yes, as com.coghelm/coghelm.
›How many tokens does Coghelm: AI tools for leaders add to my context?
Its tool definitions total about 1,573 tokens, resent on every turn.
Sources and method
- Official MCP Registry entry
- updated 2026-10-17
- GitHub repository
- fetched 2026-10-19
- Tool list (tools/list), measured by us
- 2026-10-19
- Security signals, computed by us
- 2026-10-19
- Last checked against all sources
- 2026-10-19
The description, packages and links come from the maintainer's own published metadata. Token cost, security signals, freshness and the reading above are MCPSkillHub's own measurements; see the methodology. Spot an error? Request a correction or claim the listing.