API & MCP

MCP Server

Connect Claude and other AI tools to Statusfield's live status catalog with the hosted MCP server. Read-only, Hobby plan and up.

The Model Context Protocol (MCP) is an open standard for connecting AI assistants to external tools and live data. Statusfield hosts a read-only MCP server that exposes the same status catalog as the REST API, so you can ask Claude (or any MCP-capable client) questions like "Is GitHub having issues right now?" and get answers straight from live data.

Requirements

The MCP server uses the same sf_ API key as the REST API — no separate credential. Create one at Settings → Integrations → API Keys, where you can also revoke it later. The key is shown only once at creation time.

Hobby plan and up

MCP access is available on the Hobby, Pro, and Team plans — the same gate as the REST API. It is not available on the Free plan. A Free-plan key returns 403 plan_restriction. See /pricing for per-plan limits.

Connecting

The server speaks Streamable HTTP at POST /api/mcp and authenticates with your sf_ key in the Authorization header.

Get an API key

Go to Settings → Integrations → API Keys at statusfield.com/integrations and create a key. Copy it — it is shown only once.

Add it to the Claude Code CLI

Run the following, replacing sf_<your-key> with your key:

claude mcp add --transport http statusfield \
  https://statusfield.com/api/mcp \
  --header "Authorization: Bearer sf_<your-key>"

Or add it to Claude Desktop

Add this block to your claude_desktop_config.json:

{
  "mcpServers": {
    "statusfield": {
      "type": "http",
      "url": "https://statusfield.com/api/mcp",
      "headers": {
        "Authorization": "Bearer sf_<your-key>"
      }
    }
  }
}

Ask a question

Once connected, ask your assistant something like "Is GitHub having any issues right now?" and it will call the matching tool automatically.

Tools

The server exposes four read-only tools:

Tool	Input	Description
`search_services`	`query: string`	Search the catalog by name; returns up to 10 matches as `Name (slug)` lines
`get_service_status`	`slug: string`	Current status of a service and all its components
`list_outages`	(none)	All services currently experiencing an outage or degradation
`list_my_down_services`	(none)	Your own monitored services currently down or degraded

Catalog tools vs. your monitors

search_services, get_service_status, and list_outages operate on Statusfield's public catalog — you look services up by name or slug. list_my_down_services is the exception: it reads your workspace's own monitors and reports which are currently down or degraded. For your full monitor list (healthy ones included), use the REST endpoint GET /api/v2/monitors instead (see the API reference).

Rate limits & quota

Rate limit: your plan's per-workspace burst limit applies to every request. X-RateLimit-Limit and X-RateLimit-Remaining are returned on responses, and a Retry-After (seconds) header is added on 429.
Monthly quota: only tools/call invocations count toward your plan's monthly request quota. Protocol traffic (initialize, tools/list) is free. X-Quota-* headers are returned on metered requests, and exceeding the cap returns 429 quota_exceeded. The counter resets at the start of each UTC month.

See /pricing for the per-plan request and quota limits.

Example prompts

Natural-language questions map onto the tools automatically:

"Is GitHub having any issues right now?" → get_service_status with slug github
"What services are currently down?" → list_outages
"Is anything I monitor down right now?" → list_my_down_services
"Find monitoring services" → search_services with query monitoring

Next steps

API reference — the full REST API, including GET /api/v2/monitors for your own workspace's monitors.
Pricing — per-plan rate limits and monthly quotas.