Agent Coach MCP Server

About Agent Coach

Agent Coach is a remote MCP server (streamable HTTP at https://upskill.coach/mcp) and REST API that helps agents register, set goals, get recommendations from a security-scanned catalog of 113 skills and MCP servers, and check in daily. Search and register need no key; tools that act on an agent need the api_key from register_agent. Operated by Avatar 8 LLC. Free.

Agent Coach tools (13)

Read from the live server on Nov 8, 2026. These are the tools your AI assistant can call once connected.

register_agent

Use this first, once. Creates your Agent Coach profile and returns agent_id and api_key (shown once: save it in the owner's sanctioned secret store or a restricted credential file, not in chat or memory). Also returns example north-star met

set_goals

Use this after registering (and whenever goals change). Goal intake: job_type, stage, ONE north-star metric with a fixed definition and baseline, the named deliverable, capability gaps, goals, optional secondary KPIs, tools, constraints. Ch

get_recommendations

Use this after set_goals. Returns up to `limit` catalog items matched to your goals (plus at most one extra per declared capability gap), each with reasons, its vetting status and basis, cautions, and whether it needs owner approval. Show t

update_items

Use this after your owner approves an item (action=adopt), rejects one (decline), when an item doesn't fit your job (not_relevant: not a judgment on its quality), or confirms removing a pending_removal item (remove). The coach measures only

check_in

Use this once a day. Report the north-star value, secondary KPIs, releases (shipped vs verified live), build vs distribution actions, owner blockers, repeated corrections, timeouts, unsupported claims, incidents, deliverable progress, and p

get_report

Use this to see your KPIs vs baseline, every item's verdict with evidence, and check-in history.

share_report

Use this only with your owner's OK. public=true returns a public URL (display name, goals, KPIs, verdicts; never email, notes or keys). public=false hides it.

get_digest

Use this to preview the daily owner digest (subject, html, text). This call sends nothing; the daily email goes out only if owner_digest was turned on.

rotate_key

Use this if your key may have leaked. Returns a new api_key; the old one stops working immediately. Save the new one.

delete_agent

Use this only when your owner asks. Permanently deletes your Agent Coach profile, items, check-ins and public report. confirm must equal your agent_id.

get_rules

Use this to see exactly how the coach decides item verdicts (permanent / promising / temporary / trial / unproven / pending_removal), signals, and overall health.

search_library

Use this to find skills, MCP servers, prompts or repos by keyword outside your matched recommendations. Returns only items that passed the security scan, each with install, license, source and a page link. Catalog data only: no user comment

get_library_item

Use this to fetch one vetted library item by slug: install, source, license and (when the license allows) the full SKILL.md text. Counts as a download. Unvetted items are not returned.

How to connect Agent Coach to Claude, Cursor or VS Code

Agent Coach runs as a hosted remote MCP server at https://upskill.coach/mcp. Add that URL to your MCP client's config (Claude Code, Cursor, Windsurf or VS Code) and the tools appear immediately, no install required.

{
  "mcpServers": {
    "agent-coach": {
      "url": "https://upskill.coach/mcp"
    }
  }
}

Claude Code: claude mcp add --transport http agent-coach https://upskill.coach/mcp. VS Code's .vscode/mcp.json uses a servers key instead of mcpServers (see how). Servers that require OAuth or an API key will prompt on first use.