Skip to main content
Observer runs a remote Model Context Protocol server at https://mcp.use.observer/mcp. It lets any MCP-compatible assistant (Claude, Cursor, and other MCP clients) work with your Observer data: read metrics, services, SLOs, status pages, incidents, and maintenance windows, create the Observer Agents that run your checks, and run write operations such as applying config or opening an incident. Every tool maps one-to-one to a public API operation and is governed by the same API key, the same scopes, and the same plan entitlement as the REST API. The server is stateless and holds no data: it forwards each call to the API with the key you supply on the connection.
RequirementsYou need an obs_pub_ API key (create one under Settings > API keys in the console) with the scopes for the tools you intend to use, on a plan that includes public API access.

Connect

Let the agent connect itselfAn agent can request its own key: you approve one link and it receives a scoped key and configures this server. See Connect an AI agent. The steps below are the manual path.
1

Create an API key

In the console, open Settings > API keys, create a key, and grant only the scopes you need (see the catalog below). Copy the obs_pub_… value.
2

Add the server to your MCP client

The server speaks Streamable HTTP and reads your key from the Authorization header. Most clients accept a remote server like this:
MCP client config
Config shapes vary by client. Some expect a "type": "http" field alongside the url; check your client’s remote-MCP documentation. The endpoint and the Authorization: Bearer header are the same in every case.
3

Confirm the connection

Ask the assistant what it can do. It should call getMe, which needs no scope, and report the key’s scopes, your plan, quotas, and rate limits. If a later call fails with a scope message, add the named scope to the key (or confirm your plan includes public API access).
Scopes are the boundaryA tool only runs if the key carries its scope. A call without the right scope returns an error naming the scope it needs. Give read-only keys for analysis, and scope write keys to just the operations you want an assistant to perform.

Agent skills

Ready-made skills that teach an assistant the working model (scope discipline, the export/apply loop, the incident lifecycle) live in the public skills repository. Copy a skill folder into your agent’s skills directory, or let the assistant read it directly.

Tool catalog

Account

Metrics

Services and SLOs

Status pages

Observer Agents

SLA statements

Incidents

Maintenance

Config as code

Change events

Notes

  • The server is stateless: it opens a fresh session per request and keeps nothing. Your key is read from the connection header on each call and never stored.
  • When a call fails, the tool result carries the API’s error with the details needed to fix the request: the list of validation errors and warnings for a rejected config document, and an upgrade link when a plan limit or a plan without API access is the cause.
  • createAgent and rotateAgentKey return the agent key in the tool result, once. An assistant should hand the install command to you and not keep the key anywhere else.
  • Tool inputs and outputs match the REST API one-to-one. For full field shapes, request/response bodies, and error codes, see the API reference.
  • For safe exploration, connect a key with only read:* scopes. Add write:* scopes when you want an assistant to open incidents, schedule maintenance, or apply config.