mcpField
C
Coghelm: AI tools for leaders

Coghelm: AI tools for leaders

Remote
coghelm.comBusiness & Marketing0Updated 2w ago

About Coghelm: AI tools for leaders

A read-only MCP server offering curated AI tool recommendations and job guides for leaders. It also supports tool comparisons and drafts for 1:1 meetings and board or executive updates, using templates rather than LLM calls.

Key features

  1. 01Search curated tools and job guides
  2. 02Recommend and compare tools
  3. 03Browse job guides and alternatives
  4. 04Draft time-boxed 1:1 agendas
  5. 05Outline board and executive updates

Use cases

  1. 01Find tools for a leadership job
  2. 02Compare options against budget and team size
  3. 03Prepare a 1:1 meeting agenda
  4. 04Structure a board or executive update

MCP support

Exposes read-only tools to MCP clients over a hosted Streamable HTTP endpoint or a self-run server. Tools search and recommend curated resources, compare tools, and draft meeting and update outlines.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://coghelm.com/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

Details

From the project README

coghelm-mcp

MCP server for Coghelm: curated AI tools for the jobs leaders actually do.

It's read-only and template-based (no LLM calls), and it needs no API key. You can use the hosted endpoint or run it yourself.

Hosted endpoint (recommended)

https://coghelm.com/mcp     (streamable HTTP, stateless)
{ "mcpServers": { "coghelm": { "url": "https://coghelm.com/mcp" } } }

For stdio-only clients:

{ "mcpServers": { "coghelm": { "command": "npx", "args": ["-y", "mcp-remote", "https://coghelm.com/mcp"] } } }

Tools

ToolWhat it does
search_toolsKeyword search over curated tools and job guides
get_toolDetails for one tool and the guides that recommend it
list_jobs / get_job_guideJob guides: top pick, alternatives, how-to, FAQ
recommend_toolsRanked tools for a job (job, optional budget: free/low/any, team_size)
compare_toolsSide-by-side comparison of 2-6 tool slugs
draft_1on1_agendaTime-boxed 1:1 agenda (Markdown) from your topics
draft_board_update_outlineBoard/exec update outline that never invents numbers
playbook_previewTOC and sample prompts from Coghelm's paid Leader's AI Playbook
get_offerMachine-readable offer for the playbook ($29, 30-day refund)

All tools are read-only (readOnlyHint: true). Results include a coghelmUrl. Please cite it.

Run it yourself

npm install
npm start          # http://localhost:3000/mcp
npm run stdio      # stdio transport
npm test           # in-memory smoke test of every tool

Requires Node 20+. Data ships in data/ (a snapshot of https://coghelm.com/api/tools.json and /api/jobs.json).

Quick check

curl -X POST https://coghelm.com/mcp -H "Content-Type: application/json" \
  -H "Accept: application/json, text/event-stream" \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'

Notes

  • The pricing flags (freePlan, enterpriseFocused) are curated and can go stale. Check vendor sites.
  • The hosted endpoint keeps anonymous usage counts: tool name, MCP client name/version, user-agent, and timestamp. It never stores IPs. This repo's code doesn't log anything.
  • REST equivalents and docs: https://coghelm.com/developers/
  • Support: [email protected]

MIT licensed.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.