Riddle MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| RIDDLE_API_KEY | Yes | Your Riddle API key (format: rdc_live_your_key_here) |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| riddle_screenshotA | Take a screenshot of a URL using the Riddle API. Returns base64-encoded PNG image. |
| riddle_batch_screenshotC | Screenshot multiple URLs. Returns array of base64 images. |
| riddle_run_scriptC | Run a Playwright script on a page (async). Returns job_id to check status later. |
| riddle_get_jobC | Get status and artifacts of a Riddle job |
| riddle_automateA | Run a Playwright script, wait for completion, and return all artifacts. Includes console logs and network HAR. Full sync automation - one call does everything. |
| riddle_click_and_screenshotA | Simple automation: load URL, click a selector, take screenshot. Good for testing button clicks, game starts, etc. Uses force-click by default to handle animated buttons. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 6 tools
Most tools have distinct purposes: automate (full sync), batch_screenshot (multiple URLs), click_and_screenshot (interactive), get_job (status check), run_script (async execution), and screenshot (single capture). However, riddle_automate and riddle_run_script both involve running Playwright scripts, which could cause confusion about when to use each, though their sync vs. async nature helps differentiate them.
All tool names follow a consistent 'riddle_verb_noun' pattern with snake_case throughout, such as riddle_automate, riddle_batch_screenshot, and riddle_get_job. This predictability makes it easy for agents to understand and select tools without naming confusion.
With 6 tools, the server is well-scoped for its automation and screenshot domain. Each tool serves a clear, non-redundant function, from basic screenshots to complex script execution, making the count appropriate and manageable for agents.
The toolset covers core automation workflows: screenshotting (single, batch, interactive), script execution (sync and async), and job status checking. A minor gap is the lack of tools for more advanced automation tasks like form filling or data extraction, but the provided tools allow agents to handle most common scenarios effectively.