Using OverSkill from AI agents (Claude, Cursor, Codex)
OverSkill is built for AI agents to use. Here's how to wire up Claude, Cursor, Codex, or your own agent.
OverSkill was designed with AI agents as first-class users. Claude, Cursor, Codex, and other agents can build apps on OverSkill directly — no humans in the loop required for most tasks.
Why this matters
You can ask Claude or another agent to:
- Build a new app on your OverSkill account
- Iterate on an existing app based on user feedback
- Generate templates for sale on the marketplace
- Maintain a portfolio of apps for clients
The agent talks to OverSkill the same way you would — through the chat interface — just programmatically.
Connecting your agent
OverSkill ships with an MCP server (Model Context Protocol) at https://overskill.com/.well-known/mcp/server-card.json. Most modern AI agents support MCP natively. To wire it up:
- In your agent's config, add OverSkill as an MCP server
- Use the URL above (or
https://overskill.com/SKILL.mdfor skill-style agents) - Authenticate with your OverSkill account
- The agent can now create, edit, and publish apps on your behalf
Agent-friendly surfaces
Beyond MCP, OverSkill exposes everything agents need:
- Every help article has a
.mdURL (e.g./help/articles/what-is-overskill.md) for clean markdown /llms.txt— short site map for LLMs/llms-full.txt— full API reference/SKILL.md— primary skill manifest/agents— brand-pillar page with discovery details
What agents can and can't do
With proper authentication, agents can do anything you can do — including spend credits, publish apps, and process payments. So the credentials matter. Use scoped tokens where possible.
Agents CANNOT:
- Bypass the credit meter (they pay just like you do)
- Skip identity verification for payouts
- Take over an account they aren't authorized for
Pricing for agent-driven usage
Same as humans. Credits are credits. There's no separate agent tier
— your agents draw from the same balance as your manual builds.