evmquery-mcp

Read any contract on any EVM chain through a single MCP endpoint.

Community: Submitted by a user or imported; check the owner before granting accessOnlineNo sign-inGlobalFreeRead-only

What it can do

  • Execute Query: Execute a CEL expression against EVM smart contracts. Returns the query result, execution metadata, and credits consumed. Contract names from schema.contracts become variables in the ex
  • Describe Schema: Describe the available methods, properties, and context for the given schema. Returns all callable methods on each contract, plus available CEL helper functions, list macros, and type

What data it sees

Do you need an account

No: the server works without sign-in

Read any contract on any EVM chain through a single MCP endpoint.

Ask questions in plain English and evmquery resolves the right contract, ABI, and call for you — then returns a clean, typed answer.

What it does

  • Resolves contracts automatically
  • Calls any view function without you wiring up an ABI
  • Returns structured results ready for the next tool in your chain

Good for

  • Wallet/allowance/balance checks
  • Token metadata (ERC-20, ERC-721, ERC-1155)
  • Quick reads against unknown or new contracts during research

Currently supported chains

  • Ethereum Mainnet
  • Base
  • BNB Smart Chain

How to connect

How to connect evmquery-mcp to Claude

The server address to paste into Claude settings:

https://evmquery-mcp.run.tools

  1. Open Claude (claude.ai or the desktop app).
  2. Go to Settings → Connectors.
  3. Click Add custom connector.
  4. Paste the server address copied below into Remote MCP server URL and click Add.
  5. In a chat, click + → Connectors and switch the new connector on.

Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.

Authorization

After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.

How to connect evmquery-mcp to ChatGPT

The server address to paste into ChatGPT settings:

https://evmquery-mcp.run.tools

  1. Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
  2. Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
  3. Open Settings → Connectors and click Create.
  4. Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
  5. Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
  6. In a new chat open + → Apps/Connectors and enable the connector.

OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.

Authorization

On first use ChatGPT opens the service's sign-in window. Sign in and approve access.

How to connect evmquery-mcp to Cursor

The server address to paste into Cursor settings:

https://evmquery-mcp.run.tools

Fastest: click Open in Cursor below and confirm the prompt.

Manually:

  1. In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
  2. Paste the JSON copied below into ~/.cursor/mcp.json (per project: .cursor/mcp.json in the repo root).
  3. Save the file. The server appears in the MCP list; authorize it there if asked.

Authorization

If the service needs sign-in, an authorize button appears next to the server in the MCP list.

Server tool list (2)

Raw names from tools/list. Only developers need these.

execute_queryExecute a CEL expression against EVM smart contracts. Returns the query result, execution metadata, and credits consumed. Contract names from schema.contracts become variables in the expression. Use describe_schema first to discover callable methods and available CEL functions (formatUnits, cel.bind, list macros, etc.). Example — read an ERC-20 balance: chain: 'evm_ethereum' schema: { contracts: { usdc: '0xA0b86991c6218b36c1d19D4a2e9Eb0cE3606eB48' }, context: { wallet: 'sol_address' } } context: { wallet: '0x1234...' } expression: 'formatUnits(usdc.balanceOf(wallet), usdc.decimals())' Pricing: 1 credit for pure CEL, otherwise totalCalls + totalRounds credits (e.g. a single balanceOf costs 2 credits). Response format: result value with type annotation, block metadata (block number, on-chain calls, execution rounds) when applicable, and credits consumed.
describe_schemaDescribe the available methods, properties, and context for the given schema. Returns all callable methods on each contract, plus available CEL helper functions, list macros, and type definitions. Call this before writing expressions to discover what is queryable. Common patterns: ERC-20 balance: formatUnits(usdc.balanceOf(wallet), usdc.decimals()) Multi-wallet balances: wallets.map(w, formatUnits(token.balanceOf(w), token.decimals())) Filter non-zero holders: wallets.filter(w, token.balanceOf(w) > solInt(0)) Check all holders meet threshold: wallets.all(w, token.balanceOf(w) > parseUnits('100', 18)) Any wallet has balance: wallets.exists(w, token.balanceOf(w) > solInt(0)) Bind intermediate values: cel.bind(supply, token.totalSupply(), formatUnits(supply, token.decimals())) Native ETH balance: solAddress('0x...').balance() Is zero address: isZeroAddress(owner)