Tetrac

AGENT TOOLKIT

Plain Text (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.

Resources

market-data
market-data
v2.0
Access real-time and historical market data from TTC Box. Get tickers, funding rates, open interest, and volume across 8 CEX and 6 DEX exchanges.
onboarding
onboarding
v1.0
Onboard new agents and users to TTC Box trading platform. Handles registration, API key setup, wallet connection, and initial configuration.
trading
trading
v2.0
Execute trading operations on TTC Box across 8 CEX and 6 DEX exchanges. Place orders, manage positions, set leverage, and control risk.
x402-agent-payments
payments
v2.0
Instructions for AI agents with Solana wallets to pay for TTC Box API access using the x402 protocol. No facilitator needed — agents submit USDC payments directly on-chain.
mpp-payments
payments
v2.0
Pay for TTC Box API access using the Machine Payments Protocol (MPP). Universal gateway supporting Tempo (EVM) and Solana payments via standard HTTP 402 challenges.
Integrate Skills into Your Agent
Two ready-to-go paths, and a DIY option for custom frameworks.

Option 1 — TTC CLI (recommended for Claude Code)

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-key through to the exchanges API so paid tools resolve without an x402 payment. Skills become callable tools in the agent's toolbox.

https://ttc.box/api/v1/mcp

Remote (Streamable HTTP)

{
  "mcpServers": {
    "ttc": {
      "type": "http",
      "url": "https://ttc.box/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.