- Home
- Skills
- APIs & Backend
- web3-graphql
Web3 Graphql
Query Web3 and on-chain GraphQL endpoints using natural language via the Model Context Protocol.
Free
Works with the AI Agents you already use
web3-graphql
Example session with this skill installed
What is the current staking APR and total ETH volume for Lido? Use the Lido subgraph to get the latest on-chain metrics.
- Read your context and instructions
- Compiled the web3-graphql
Assumptions: Analyzing staking rewards for Lido on Ethereum.
Summary: The current APR is 3.4%. Total staked ETH is 9.8M.
Details: Data fetched from Lido Subgraph via graphql_agent.
Next Step: Would you like a breakdown of validator performance?
Connects securely to your tools. The creator never sees your data.
About this skill
What it does
The Ask GraphQL MCP skill enables your AI agent to interact natively with Web3 and on-chain data through GraphQL endpoints, such as SubGraph and SubQuery. It bridges the gap between natural language requests and complex blockchain schemas by leveraging a specialized Model Context Protocol (MCP) gateway.
Problem it solves
Querying blockchain data via GraphQL usually requires developers to manually inspect schemas, write complex nested queries, and manage endpoint connectivity. This skill automates that process: your agent can now answer questions like 'What is the current staking volume on this protocol?' or 'Analyze recent governance proposals' without the agent needing to manually draft every GraphQL query from scratch.
Why use this skill?
- Automated Discovery: Includes built-in endpoint discovery if you don't have the specific URL at hand.
- Reliability: Standardizes query execution through a dedicated MCP agent, reducing syntax errors and hallucinated schemas.
- Web3 Optimized: Specifically designed for on-chain metrics, pool activity, and protocol analysis.
- Seamless Workflow: Handles everything from free-tier exploration to authenticated, high-throughput production queries with built-in quota management.
Output overview
The skill returns structured interpretations of on-chain data, including assumptions made during the query, a concise answer summary, and the technical details or specific queries provided by the MCP for verification.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for APIs & Backend.
- Max timeout of 120s for complex queries.
- Free tier subject to rate limits (requires API key for high volume).
- Requires an active GraphQL endpoint (or discovery) to function.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
This skill has been used 24 times.
Trust & safety
Security scan
Security scan passed 7 months ago
- Free with an Agensi account
Permissions
No special permissions declared or detected