The Graph Token MCP Skill for Openclaw

A high-performance MCP skill for querying real-time token metadata, EVM balances, and market data via The Graph Token API.

jolestar
v1.0.1
Mar 8, 2026
0
858
0

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.

npx clawhub@latest install thegraph-token-mcp-skill

2. Manual Installation

Copy the skill folder to one of these locations

Global
~/.openclaw/skills/
Workspace
<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

Copy this prompt to OpenClaw to install it automatically.

Help me install thegraph-token-mcp-skill using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).

Prefer to download?

Get the raw skill files in a ZIP archive.

What is The Graph Token MCP Skill?

The Graph Token MCP Skill enables developers and AI agents to interface directly with The Graph Token API for deep blockchain insights. By utilizing the Model Context Protocol (MCP), this tool provides a standardized way to access token metadata, wallet transfers, and liquidity pool data across multiple networks. As part of the Openclaw Skills ecosystem, it ensures that your AI coding agents can fetch live on-chain data without complex custom integrations.

This skill is built for precision, offering dedicated support for EVM and non-EVM chain families. It leverages the uxc CLI to manage secure JWT authentication and provides a help-first inspection workflow, ensuring that every query is valid before execution.

The Graph Token MCP Skill Use Cases

  • Tracking real-time wallet balances and native token holdings across multiple blockchain networks.
  • Fetching token metadata and contract verification details for DeFi research and auditing.
  • Monitoring DEX pool liquidity, OHLC market data, and historical transfer events.
  • Automating financial reporting and data extraction for Openclaw Skills powered workflows.
  • Integrating live blockchain state into AI-driven trading or portfolio management agents.

How The Graph Token MCP Skill Works

  1. Perform host discovery using uxc to verify the MCP endpoint and protocol version.
  2. Configure a dedicated JWT credential stored securely as an environment variable.
  3. Create an authentication binding to map the Token API host to the specific JWT secret.
  4. Link the remote endpoint to a local CLI command for simplified execution.
  5. Inspect the operation schema using the -h flag to confirm arguments for tools like getV1EvmTokens.
  6. Execute the query and receive a structured JSON envelope containing the blockchain data.

The Graph Token MCP Skill Setup

First, ensure uxc is installed, then set up your credentials using your JWT from the Graph Market dashboard:

# Configure the JWT credential
uxc auth credential set thegraph-token --secret-env THEGRAPH_TOKEN_API_JWT

# Bind the credential to the Token API endpoint
uxc auth binding add --id thegraph-token-mcp --host token-api.mcp.thegraph.com --scheme https --credential thegraph-token --priority 100

# Create a local command link
uxc link thegraph-token-mcp-cli https://token-api.mcp.thegraph.com/

The Graph Token MCP Skill Data Schema & Taxonomy

The skill returns data within a standardized MCP envelope. Use the following schema to parse responses when building Openclaw Skills integrations:

Property Description
ok Boolean flag indicating if the request was successful
kind The type of response (e.g., tool_call_result)
protocol Confirms the usage of the MCP protocol
data The primary payload containing token lists, balances, or market metrics
error Detailed error message if the operation fails

The Graph Token MCP Skill Advanced Features

  • Help-first probing to discover dynamic API updates without manual documentation checks.
  • Support for TVM (Telegram Virtual Machine) and other non-EVM chain families.
  • Dedicated JWT bearer auth binding to prevent credential leakage between different subgraphs.
  • Priority-based authentication routing for environments with multiple API keys.
  • Native JSON envelope parsing for stable automation and multi-agent orchestration.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*