Skip to main content

Documentation Index

Fetch the complete documentation index at: https://tokenterminal.com/docs/llms.txt

Use this file to discover all available pages before exploring further.

The Token Terminal MCP server gives AI clients structured access to our onchain dataset — projects, products, chains, market sectors, financial metrics, and methodologies — through the Model Context Protocol. It is a centrally hosted remote server compatible with Claude, ChatGPT, Cursor, and any other MCP-compatible client.

Availability

The MCP server is available on every Token Terminal plan. The free tier includes full access to all tools and data with limited usage; paid plans raise the usage limits. For higher limits or enterprise options, contact our team at sales@tokenterminal.xyz.

Setup guides

Claude Code

Set up MCP in Claude Code via the CLI.

Claude Desktop

Set up MCP in the Claude Desktop app.

ChatGPT

Install the Token Terminal app from the ChatGPT app directory.

Codex CLI

Set up MCP in Codex CLI.

Cursor

Set up MCP in the Cursor IDE.

Gemini CLI

Set up MCP in Gemini CLI.

OpenCode

Set up MCP in OpenCode.

Microsoft Copilot Studio

Set up MCP in Microsoft Copilot Studio.

Other clients

Use MCP with any compatible client.

How it works

The server is hosted at https://mcp.tokenterminal.com/mcp and implements the authenticated remote MCP specification over the Streamable HTTP transport. Clients connect directly — there is no local proxy or companion process to run. Authentication is handled by OAuth 2.1 with PKCE, so no API keys or long-lived secrets are exchanged with your client. The first connection opens a browser window in which you sign in to Token Terminal and select the user account and organization the session will operate under. Your client stores the resulting access token and refreshes it transparently.

Available tools

The server exposes the following tools to connected clients.
discover
Resolve entity IDs for projects, chains, metrics, and products. Use this first to find the IDs needed by get_timeseries, get_breakdown, and create_chart.
get_timeseries
Fetch historical metric time series for projects, assets, products, chains, or market sectors.
get_breakdown
Fetch aggregated metric breakdowns — rankings, totals, and comparisons across projects, chains, products, assets, or market sectors.
get_methodologies
Fetch methodology content for any Token Terminal metric, or the included/excluded contract addresses behind a project metric.
create_chart
Create a saved Token Terminal chart from a metric configuration and return its shareable URL.
asset_research
AI-powered analyst for tokens, stablecoins, RWAs, and commodities. Maintains conversation memory across calls.
research_assistant
Experimental all-rounder for broader semantic analytics across projects, chains, ecosystems, assets, and mixed analytical questions. Maintains conversation memory across calls.