golemry
Create and manage scheduled, guarded AI agent jobs with built-in quality control and 900+ connectors.
What it can do
- Create Job: Create a new AI agent job that runs a prompt with a specified LLM model. A job is either scheduled (runs automatically on a recurring cron schedule) or an event trigger job (no schedule).
- List Available Llms: List the LLM providers and models you can use, based on configured API keys. Returns, per provider, the models already in use by existing jobs and the full set of available models
- List Jobs: List all your jobs, with their schedule (if any), status, and most recent execution details.
What data it sees
Do you need an account
No: the server works without sign-in
Create and manage scheduled, guarded AI agent jobs with built-in quality control and 900+ connectors. This gives any agent the power to setup recurring AI tasks in a safe an reliable way and outsource task execution.
- Create jobs from plain language: A prompt, a model, and a cron schedule or event trigger.
- Guarded by an overseer: Every result is checked before delivery, and anything that looks off is escalated to you, so silent failures don't slip through.
- 900+ connectors: Gmail, GitHub, web search, and more, usable directly inside jobs.
How to connect
How to connect golemry to Claude
The server address to paste into Claude settings:
https://golemry--golemry.run.tools
- Open Claude (claude.ai or the desktop app).
- Go to Settings → Connectors.
- Click Add custom connector.
- Paste the server address copied below into Remote MCP server URL and click Add.
- In a chat, click + → Connectors and switch the new connector on.
Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.
Authorization
After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.
How to connect golemry to ChatGPT
The server address to paste into ChatGPT settings:
https://golemry--golemry.run.tools
- Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
- Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
- Open Settings → Connectors and click Create.
- Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
- Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
- In a new chat open + → Apps/Connectors and enable the connector.
OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.
Authorization
On first use ChatGPT opens the service's sign-in window. Sign in and approve access.
How to connect golemry to Cursor
The server address to paste into Cursor settings:
https://golemry--golemry.run.tools
Fastest: click Open in Cursor below and confirm the prompt.
Manually:
- In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
- Paste the JSON copied below into
~/.cursor/mcp.json(per project:.cursor/mcp.jsonin the repo root). - Save the file. The server appears in the MCP list; authorize it there if asked.
Authorization
If the service needs sign-in, an authorize button appears next to the server in the MCP list.
Server tool list (14)
Raw names from tools/list. Only developers need these.
| create_job | Create a new AI agent job that runs a prompt with a specified LLM model. A job is either scheduled (runs automatically on a recurring cron schedule) or an event trigger job (no schedule). |
| list_available_llms | List the LLM providers and models you can use, based on configured API keys. Returns, per provider, the models already in use by existing jobs and the full set of available models. Prefer cheap, up-to-date models. |
| list_jobs | List all your jobs, with their schedule (if any), status, and most recent execution details. |
| get_job | Get full details for a specific job including its prompt, model, schedule, and last execution result. |
| run_job | Immediately run an existing job once. |
| update_job | Update an existing job's name, prompt, model, schedule and more. |
| list_executions | List recent job executions (most recent first, paginated, optionally filtered by jobId) |
| get_execution | Returns the execution's agent transcript and logs, both paginated and ordered most-recent-first. |
| list_connected_connectors | List the connectors the user has ALREADY connected (gmail, github, etc.). These can be used in jobs. |
| list_connectable_connectors | List connectors the user could connect but has NOT connected yet (gmail, github, etc.); for connectors they have already connected, use list_connected_connectors instead. Use this to recommend an integration when a request may need a service they haven't connected. The user has to connect a connector at https://golemry.com/app/connectors before it is available for jobs. |
| list_connector_tools | List all available tools of a connector. Works for any connector, including ones the user has not connected yet, so you can inspect what a connector offers before recommending it. Only connected connectors can be used in jobs. |
| get_connector_tool | Get the full description and input parameter schema for a single tool of a connector. |
| run_connected_tool | Run a single tool of an already connected connector, using arguments from the tool's input schema. Use this for one-off actions the user asks for directly, or setup tasks. For recurring or scheduled work, create a job instead. |
| get_doc_links | Get links to Golemry's documentation (website, docs page, docs llms.txt) |