Best for
- Developers building AI agents that need on-chain data
- Smart contract auditing and data analysis
- Building DeFi dashboards or monitoring tools
The project is no longer receiving updates but core functionality remains usable. Suitable for developers needing quick access to on-chain data, but note its read-only nature and reliance on an external API.
Strongest · Documentation 8/20 Weakest · Security and permissions 6/20
Static review · not runListed 2026-08-07
Read the FMRS scoring method →Runtime:Node.js
BANKLESS_API_TOKEN
Access token for the Bankless API, required for the server to run; obtain it per https://docs.bankless.com/bankless-api/other-services/onchain-mcp.
npx @bankless/onchain-mcp.{
"mcpServers": {
"bankless": {
"command": "npx",
"args": [
"@bankless/onchain-mcp"
],
"env": {
"BANKLESS_API_TOKEN": "your_api_token_here"
}
}
}
}
Shown for Claude Desktop. Other clients may use a different file or key (VS Code uses "servers") — the configurator below converts it.
{
"servers": {
"bankless": {
"command": "npx",
"args": [
"@bankless/onchain-mcp"
],
"env": {
"BANKLESS_API_TOKEN": "your_api_token_here"
}
}
}
}
Goes in your project's .vscode/mcp.json (VS Code uses a "servers" key).
claude mcp add bankless -e BANKLESS_API_TOKEN=your_api_token_here -- npx @bankless/onchain-mcp
Run it in a terminal; replace any <…> placeholders with your own values first.
After setup, tools like read_contract, get_abi, and get_events should appear in the client's tool list; calling get_proxy on a known proxy contract confirms the API token works.
Once connected, you can ask your AI assistant things like:
No matching tools
Listed from the project's documentation, not tested by this site.
The Bankless Onchain MCP Server provides a framework for interacting with on-chain data via the Bankless API. It implements the Model Context Protocol (MCP) to allow AI models to access blockchain state and event data in a structured way. It supports contract operations (read state, get proxy, ABI, source), event operations (get logs, build topic), and transaction operations (history and details).
Manage your Hevy workout data from AI assistants via MCP.
Firecrawl's official MCP server for web search, scraping, and structured extraction for AI agents
One binary. One grammar. Evidence from the biomedical sources you already trust.
Encrypted, fully offline long-term memory for AI agents
Source revision f81f69a14560 Data synced 2026-10-12 Read the FMRS scoring method