MCP server

AI agents that support the Model Context Protocol (MCP), such as Claude and many other assistants and coding agents, can work in your workspace through our MCP server:

https://mcp.limitry.com/mcp

Connect

Add the address above as a remote MCP server. In Claude, that’s Settings → Connectors → Add custom connector. The first time, your browser opens:

1. Sign in, if you aren’t already.
2. Choose the one workspace the agent will work in.
3. Choose what it may do. Everything that can change data starts unticked, so tick only what the agent needs.
4. Click Allow.

There’s nothing to copy and no key to store. The agent gets its own sign-in, valid only for that workspace and that access.

Test and live

The agent works in test unless you connect it to live. Test limits and counts are separate from live ones, so an agent trying things out can’t refuse your real customers by mistake. To let an agent work in live, connect it with this address instead, or add it as a second connector:

https://mcp.limitry.com/mcp?environment=live

Every tool result ends with Environment: test or Environment: live, so you and the agent can always tell which side it used. See Test and live.

What the agent can do

The agent’s tools are the API operations you allowed, such as reading the workspace or listing webhook deliveries. It always acts as you, with your role in the workspace: if you couldn’t do something in the app, the agent can’t either. Everything it changes appears in the workspace’s audit log under your name.

Some actions are never available to agents, even with full access: anything that sends your workspace’s data somewhere new or gives out access, such as creating webhook endpoints or credentials. The agent can ask for them instead. You approve or deny in the app, and if the action creates a secret, the app shows it to you, never to the agent. See Approvals.

Staying in control

• Account → Connected apps lists every agent you’ve connected. Disconnect one and it stops working at once.
• The workspace’s audit log records what each agent did.
• If you’re removed from the workspace, your agents lose access too.

For developers

The server follows the MCP authorization specification. A request without a token gets a 401 pointing to /.well-known/oauth-protected-resource/mcp, which names the authorization server: https://api.limitry.com/auth, with dynamic client registration and PKCE. The authorization server issues tokens for the MCP server only.

A tool that changes something takes an optional idempotencyKey argument. When an agent calls the tool again after an error or a timeout, the same key makes the change happen once. Within one call, the server retries a failed attempt with its key. See Idempotency.

For your own scripts, the CLI or the SDK are simpler. See Use with AI agents for the agent skill.