Skip to main content

Quicknode MCP

Updated on
Feb 27, 2026

Overview

The Quicknode MCP server (@quicknode/mcp) connects your Quicknode account to MCP-compatible AI assistants like Claude Code, Codex, and Cursor. Once configured, you can create and manage endpoints, monitor usage, configure security settings, and review billing data through natural language instead of navigating the dashboard or writing API scripts.

The MCP server wraps Quicknode's Admin API and exposes it as a set of tools that AI assistants can call on your behalf. The assistant interprets your request, selects the appropriate tool, and executes it after confirmation.

Requirements


Configuration

Add the Quicknode MCP server to your assistant's configuration file.

For Claude Code, run the following command in your terminal:

# Add the Quicknode MCP server to Claude Code
claude mcp add quicknode-mcp -e QUICKNODE_API_KEY=<your-quicknode-api-key> -- npx -y @quicknode/mcp

Replace <your-quicknode-api-key> with an API key generated from your Quicknode dashboard. The key must have Admin API permissions enabled.

Once your configuration is complete, the MCP tools should appear in the assistant's tool list.

info

For a detailed walkthrough with screenshots covering API key creation and assistant setup, see the Quicknode MCP guide.

Available Tools

The MCP server exposes the following tool categories through the Admin API:

Endpoint Management

Create, read, update, and delete Quicknode endpoints across any supported chain and network.

Tool
Description
get-endpoints
List all endpoints on your account
get-endpoint
Get details for a specific endpoint
create-endpoint
Create a new endpoint on a specified chain and network
delete-endpoint
Delete an endpoint
get-endpoint-metrics
Retrieve performance metrics for an endpoint
get-endpoint-logs
Fetch recent logs for an endpoint
get-endpoint-log-details
Get detailed information for a specific log entry

Rate Limits

Configure method-level and endpoint-level rate limits.

Tool
Description
update-endpoint-rate-limits
Set overall rate limits for an endpoint
get-endpoint-method-rate-limits
List method-specific rate limits
create-endpoint-method-rate-limit
Add a rate limit for a specific RPC method
update-endpoint-method-rate-limit
Update an existing method rate limit
delete-endpoint-method-rate-limit
Remove a method rate limit

Security

Manage authentication and access control settings for endpoints.

Tool
Description
get-endpoint-security-options
View current security settings
update-endpoint-security-options
Update security configuration
create-endpoint-security-domain-mask
Add a domain mask restriction
delete-endpoint-security-domain-mask
Remove a domain mask restriction
create-endpoint-security-ip
Add an IP allowlist entry
delete-endpoint-security-ip
Remove an IP allowlist entry
create-endpoint-security-jwt
Add JWT authentication
delete-endpoint-security-jwt
Remove JWT authentication
create-endpoint-security-referrer
Add a referrer restriction
delete-endpoint-security-referrer
Remove a referrer restriction
create-endpoint-security-token
Create an authentication token
delete-endpoint-security-token
Delete an authentication token

Usage and Billing

Monitor RPC usage and review billing information.

Tool
Description
get-rpc-usage
Get overall RPC usage for the current billing period
get-rpc-usage-by-endpoint
Break down usage by endpoint
get-rpc-usage-by-method
Break down usage by RPC method
get-rpc-usage-by-chain
Break down usage by chain
get-billing-invoices
List billing invoices
get-billing-payments
List billing payments

Chains

Query available chains and networks.

Tool
Description
get-chains
List all supported chains and their available networks

Example Prompts

You do not need to reference tool names directly. The AI assistant maps natural language to the appropriate tool. Some examples:

Endpoint management:

  • "Create a new Base mainnet endpoint"
  • "Show me all my endpoints and their current status"

Security:

  • "Add JWT authentication to my Ethereum mainnet endpoint"
  • "Review security settings across all endpoints"

Usage and billing:

  • "Which endpoint is using the most credits this month?"
  • "Show me my billing history for the past 6 months"

Debugging:

  • "Check the logs for my Arbitrum endpoint from the last hour"

How It Works

The MCP server runs locally on your machine via npx. When your AI assistant receives a request that involves Quicknode infrastructure, it calls the appropriate MCP tool, which makes authenticated requests to the Quicknode Admin API using your API key. The assistant handles the response formatting and presents the results in natural language.

Write operations (creating endpoints, modifying security settings, deleting resources) require your explicit confirmation before the assistant executes them.


tip

Quicknode MCP manages your account-level infrastructure. If you want AI coding agents to have accurate knowledge of Quicknode's APIs and products when writing code, see Blockchain Skills. For AI-optimized documentation discovery, see LLM-Optimized Docs.

Resources

We ❤️ Feedback!

If you have any feedback or questions about this documentation, let us know. We'd love to hear from you!

Share this doc