Tetrac
Agent Toolkit

Skills & tools for your trading agents

Connect your own agent to the TTC API for real-time market data and begin perp trading across CEX & DEX exchanges in a standardized way.

Plain Text (Agents)
Skills
Integrate

Integrate skills into your agent

Two ready-to-go paths, and a DIY option for custom frameworks.

Option 1 — TTC CLIRecommended

The ttc CLI ships with all skills pre-bundled under .claude/skills/. Claude Code auto-discovers them — no loader, no prompt injection, no schema glue. Install the binary, open the repo, and the skills are live.

https://gitlab.com/tradingtoolcrypto/rust-cli-ttc-api
# install the CLI
cargo install ttc-cli

# open the project in Claude Code
claude

# skills listed below are available immediately:
#   skill-trading, skill-dca, skill-twap, skill-momentum,
#   skill-market-maker, skill-loop-trading, skill-shark,
#   skill-signal-patrol, skill-portfolio-manager,
#   skill-market-overview, skill-onboarding, skill-claude-diag

Why this is the best path: Claude Code is a flat-rate terminal agent — you are not paying per-LLM-call through an API gateway, and CLI tools use ~25× fewer tokens than MCP for the same task.

Option 2 — MCP server

For any MCP-capable host (Claude Desktop, Cursor, Windsurf, custom agents): point at the TTC MCP endpoint and pass your session headers — the server forwards ttc-auth-token and ttc-public-keythrough to the exchanges API so paid tools resolve without an x402 payment. Skills become callable tools in the agent's toolbox.

https://tetrac.xyz/api/v1/mcp

Remote (Streamable HTTP)

{
  "mcpServers": {
    "ttc": {
      "type": "http",
      "url": "https://tetrac.xyz/api/v1/mcp",
      "headers": {
        "ttc-auth-token": "${TTC_AUTH_TOKEN}",
        "ttc-public-key": "${TTC_PUBLIC_KEY}"
      }
    }
  }
}

Export TTC_AUTH_TOKEN and TTC_PUBLIC_KEY in your shell (never hard-code them).

Local (stdio)

{
  "mcpServers": {
    "ttc": {
      "command": "ttc",
      "args": ["mcp"]
    }
  }
}

Works everywhere MCP works — but expect higher token usage and a stateful connection per session.

Option 3 — custom agent framework

Building your own agent loop? Read the SKILL.md files from disk, inject their frontmatter into the system prompt, and invoke the ttc binary as a subprocess when the model calls a skill. That is the entire integration.