Claude Code
Add the Hermes AI API MCP server to Claude Code, sign in with OAuth and optionally install the Agent Skill.
Add the MCP server
Run this in a terminal. It adds the server over Streamable HTTP.
terminal
claude mcp add --transport http hermes-ai-api https://api.hermes-ai.net/mcpSign in
In Claude Code, run /mcp and choose hermes-ai-api. Your browser opens to sign in. Sign in with Google or GitHub and allow the request.
- What the app can do: Run models and spend your prepaid credits, and read your tasks, results and balance.
- What it cannot do: Manage API keys, billing or payments, or use any admin feature.
- Disconnect any time: Account security lists every connected app. Disconnecting stops its access immediately.
Install the Agent Skill (optional)
The skill teaches an agent the Hermes AI API workflow over the REST API with an API key. Unzip it into ~/.claude/skills (all projects) or a project's .claude/skills folder, and set HERMES_API_KEY.
terminal
mkdir -p ~/.claude/skills
curl -L https://api.hermes-ai.net/skills/hermes-ai-api.zip -o /tmp/hermes-ai-api.zip
unzip -o /tmp/hermes-ai-api.zip -d ~/.claude/skillsMCP tools
Once signed in, ask in plain language. Your agent picks a model, shows the price and runs the task with these tools:
| Tool | What it does |
|---|---|
search_models | Find models by output type or keywords, with prices. |
get_model | Read a model's input fields, allowed values and current price. |
create_task | Run a model. Charges credits only if the task succeeds. |
wait_for_task | Wait until a task finishes and return its results. |
get_task | Check a task. Finished images are returned inline. |
list_tasks | List your recent tasks. |
get_balance | Show available, reserved and spent credits. |
Let your agent do the setup
Prefer one step? Copy the setup prompt from the Agents page into your agent; it runs these steps for you. Agents