Frequently Asked Questions (FAQ) about the EVE Online Market MCP Server
Q: What is an MCP Server? A: MCP (Model Context Protocol) is an open protocol that standardizes how applications provide context to LLMs. The EVE Online Market MCP Server acts as a bridge, allowing AI models to access and interact with EVE Online market data through the ESI API.
Q: What is the ESI API? A: ESI (EVE Swagger Interface) is the official API provided by CCP Games for accessing data from EVE Online.
Q: Why should I use this MCP Server instead of directly accessing the ESI API? A: This MCP Server simplifies data access by handling authentication, rate limiting, and error handling. It also provides pre-built functions for common market data queries and integrates seamlessly with the UBOS platform for AI Agent development.
Q: Do I need an EVE Online account to use this server? A: For accessing public market data (prices, orders, history in public regions), you do not need an EVE Online account. However, to access market data within structures (stations, citadels), you need an account and a valid ESI token with the appropriate permissions.
Q: What scopes are required for accessing structure market data?
A: The following scopes are required: esi-markets.structure_markets.v1 and esi-markets.read_character_orders.v1.
Q: How do I obtain an ESI token? A: You need to register an application on the EVE Online Developers Portal and use the EVE Online SSO (Single Sign-On) to authenticate a user and obtain an access token.
Q: What is rate limiting, and how does the server handle it?
A: The ESI API imposes rate limits to prevent abuse. This server automatically monitors these limits and returns errors if they are reached. The x-esi-error-limit-remain and x-esi-error-limit-reset headers provide information about the current rate limit status.
Q: What is UBOS and how does it relate to this MCP Server? A: UBOS is a full-stack AI Agent Development Platform focused on bringing AI Agents to every business department. This MCP Server integrates seamlessly with UBOS, allowing you to build AI Agents that can access and analyze EVE Online market data to automate trading strategies, optimize logistics, and gain a competitive edge.
Q: Can I use this server to build automated trading bots? A: Yes, absolutely! This server is designed to provide the necessary data for building automated trading bots and other market analysis tools.
Q: Does the server support pagination for large datasets?
A: Yes, endpoints that return large amounts of data, such as get-structure-orders, support pagination. Use the page parameter to specify the desired page (starting from 1).
Q: Is the data cached? A: Yes, ESI responses are cached on the server-side to improve performance. The cache duration varies depending on the endpoint. Cache information can be found in the response headers.
Q: How do I install the server?
A: You can install the server using Smithery with the command npx -y @smithery/cli install @kongyo2/eve-online-mcp --client claude, or manually by cloning the repository, installing dependencies, building the project, and starting the server.
Q: I’m getting errors when trying to access structure market data. What could be the issue?
A: Ensure that you have a valid ESI token with the required scopes (esi-markets.structure_markets.v1 and esi-markets.read_character_orders.v1) and that the token is passed correctly in the token parameter when calling the endpoint.
Q: Can I contribute to this project? A: Yes, contributions are welcome! Please submit pull requests with bug fixes, new features, or improvements to the documentation.
EVE Online Market Data Server
Project Details
- kongyo2/eve-online-mcp
- Last Updated: 6/16/2025
Recomended MCP Servers
Help LLMs to understand your Next apps better
无需服务器,一键部署,快速使用自建节点分享URL进行订阅转换,提供灵活的自定义选项,支持SingBox/Clash/V2Ray/Xray
MCP SERVER for appium
MCP Server for Adobe After Effects. Enables remote control (compositions, text, shapes, solids, properties) via the Model Context...
A universal RPC layer for AI agents. Connect to any function, any language, any framework, in minutes.
Simplest remote MCP server implementation





