Outlit MCP

Key points before installing/using this skill: - The skill will ask for and use an Outlit MCP API key and tells the agent how to add it to local MCP config files (project .cursor/mcp.json, Claude desktop config in your OS profile) or call a 'claude mcp add' command. The metadata does not list any required credential or config paths — verify this discrepancy with the publisher. - Do not paste high-privilege or long-lived org-wide API keys into chat. If you try it, prefer a limited-scope, read-only API key created for this skill and rotate/delete it after testing. - Confirm the endpoint (https://mcp.outlit.ai/mcp) and the publisher are legitimate. There is no homepage or publisher info in the registry metadata, which reduces transparency. - The skill's instructions will modify files in your project or user profile if followed. Require the agent to ask for explicit permission before writing to any local files or running the 'claude' CLI. If you do not use Claude or .cursor, those steps are unnecessary — ensure the agent checks first. - If you want to proceed: ask the publisher to update the skill metadata to declare the API key/primary credential and the config paths it will write to, or run the integration manually yourself (add the MCP server entry) rather than letting the agent modify files automatically. - If unsure, test in an isolated environment (throwaway account or VM) and limit the API key's permissions to read-only/organization-scoped access.