Fivexer

MCP server

@fivexer/mcp exposes a Fivexer workspace to Claude Code, Claude Desktop, Cursor, and any other MCP client — 54 tools covering tasks, workers, skills, teams, decisions, learning, and stats.

It is how an agent asks for work to be routed ("file this as a billing task, high priority") and how it reads the result back, without you writing any integration code.

Hosted connector (no install)

Hosted clients — claude.ai connectors, ChatGPT connectors, anything that cannot spawn a local process — connect over HTTP and authorize with OAuth. Add a custom connector pointing at:

https://api.5xer.com/mcp

No API key is involved and there is nothing to install. For Claude Code over the same transport:

bash
claude mcp add --transport http fivexer https://api.5xer.com/mcp

Local stdio server

For a local process that should use a workspace key directly:

bash
claude mcp add fivexer \
  -e FIVEXER_API_KEY=sk_test_... \
  -e FIVEXER_BASE_URL=https://api.5xer.com \
  -- npx -y @fivexer/mcp

Both variables are required — the server refuses to start without them rather than guessing an origin. npx @fivexer/mcp init walks through it interactively and prints ready-made snippets for Claude Code, Cursor (~/.cursor/mcp.json), and Claude Desktop (claude_desktop_config.json).

The key you supply is a workspace key, so the tools reach everything that plane reaches. Use an sk_test_ key against a sandbox workspace while you are exploring.

What the tools cover

AreaTools
Taskscreate, bulk create, get, list, cancel, accept, reject, complete, escalate, unpark, context, comments, attachments
Workersupsert, list, remove, availability, queue, identities, invites, join links
Skillscreate, list, update, delete, suggest
Teamscreate, list, delete, members, presence
Routingsuggest_workers, list_decisions, list_parked_tasks
Learningstatus, worker stats, preview weights, apply weights, record feedback, reset
Observabilityget_stats, get_sla_stats, break_metrics, check_quota

Read-only tools are annotated as such, so a client that distinguishes them can run those without prompting.

The concepts resource

The server also publishes fivexer://concepts — a short mental model of the platform: the task lifecycle, how routingWeights and hard vetoes work, wildcard syntax, skill thresholds, and geo limits. Agents that read it before calling tools make far fewer wrong-shaped requests, because the rules that surprise people (weight 0 is a veto, wildcards are suffix-only) are stated up front.

Related

  • @fivexer/agent — the other direction: run an AI agent as a worker that receives routed tasks.
  • Auth & keys — what a workspace key can reach.

Was this page helpful?