Use with AI agents

AI agents can do in your workspace what you could do yourself, within the access you give them. They act as you, and the audit log records what they did. There are three ways to connect one, from least setup to most:

Your agent	Use
Claude, ChatGPT or another app with MCP	The MCP server. Nothing to install.
A coding agent with a terminal	The CLI, with --json.
Your own software	The API or the SDK.

Agents work in test

An agent works in test unless you name live, through the MCP server and the CLI alike. Test limits and counts are separate from live ones, so a mistake while the agent tries things out never refuses your real customers. Every answer the agent gets names its environment, Environment: test or Environment: live. See Test and live.

MCP server

Add https://mcp.limitry.com/mcp as a remote MCP server in your agent. You sign in once in the browser and choose one workspace and what the agent may do there, and that’s all it can do. See MCP server for the details and safeguards. To let it work in live, connect https://mcp.limitry.com/mcp?environment=live.

CLI

Coding agents such as Claude Code, Cursor and Codex work well with the CLI:

npm install -g @limitry/cli
limitry login                                  # you approve it in the browser
limitry workspace list --json
limitry workspace webhook-endpoints list --workspace acme --json

With --json, the agent gets the API’s exact JSON, errors as JSON on stderr, and an exit code of 0 or 1. In CI, or a sandbox without a browser, set LIMITRY_TOKEN to a personal access token limited to what the agent needs. To act in live, the agent passes --environment live, or you set LIMITRY_ENVIRONMENT=live.

Teach your agent: the skill

The agent skill is one file that teaches an agent everything on this page: how to sign in, choose the workspace, every command and operation, the error codes, and what to leave to a person. It’s at /docs/skill/SKILL.md, and it’s generated from the API, so it always matches.

To install it for every project in Claude Code:

mkdir -p ~/.claude/skills/limitry
curl -fsSL https://limitry.com/docs/skill/SKILL.md \
  -o ~/.claude/skills/limitry/SKILL.md

Or put it in a project’s .claude/skills/limitry/. Other agents that support skills take the same file in their own skills folder.

Docs for agents

The documentation is also available as plain text: /docs/llms.txt indexes every page, and /docs/llms-full.txt has everything in one file. The site’s /llms.txt points to these, the API, the MCP server and the skill.

What agents can’t do

Some operations stay with people, even when an agent has full access: anything that sends your workspace’s data somewhere new or gives out access, such as creating API keys or adding webhook endpoints. Copying limits from test to live stays with people too. The agent asks instead, and you approve or deny (see Approvals). A secret created this way never reaches the agent.