Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@fund-mcp search for stock information on Alibaba"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
一个基于Model Context Protocol (MCP)的基金知识库服务器，提供基金相关知识的查询和检索功能，支持多种部署模式和协议。 A fund knowledge base server based on Model Context Protocol (MCP), providing query and retrieval functions of fund-related knowledge, and supporting multiple deployment modes and protocols.## 工具列表 Tool List
本MCP服务封装下列工具，可让模型通过标准化接口调用以下功能。 本MCP服务封装下列工具，可让模型通过标准化接口调用以下功能。
工具 Tool | 描述 Description |
fund.echo | Echo back a message. Example interface for scaffold. |
fund.knoewledge | 获取的知识库列表信息 |
fund.stock_search | 搜索股票信息，基于东方财富API |
工具在线测试： https://mcp.xiaobenyang.com/inspector/1777316659313667
Online Tool test https://mcp.xiaobenyang.com/inspector/1777316659313667
Related MCP server: Fund MCP Server
如何获取 XBY-APIKEY ？ How to get XBY-APIKEY ?
访问小笨羊科技网站 https://xiaobenyang.com，注册用户即可获得APIKEY Visit XiaoBenYang website https://xiaobenyang.com, register and get the APIKEY.
{
"mcpServers": {
"基金知识查询服务器": {
"headers": {
"XBY-APIKEY": "<YOUR_XBY_APIKEY>"
},
"type": "sse",
"url": "https://mcp.xiaobenyang.com/1777316659313667/sse"
}
}
}{
"mcpServers": {
"基金知识查询服务器": {
"headers": {
"XBY-APIKEY": "<YOUR_XBY_APIKEY>"
},
"type": "streamable_http",
"url": "https://mcp.xiaobenyang.com/1777316659313667/mcp"
}
}
}{
"mcpServers": {
"基金知识查询服务器": {
"command": "npx",
"args": [
"-y",
"xiaobenyang-mcp"
],
"env": {
"XBY_APIKEY": "<YOUR_XBY_APIKEY>",
"mcpId": "1777316659313667",
},
"transport": "stdio"
}
}
}
Echo back a message. Example interface for scaffold.
Inputs: message (required).
获取的知识库列表信息
Inputs: kw, pageSize, pageNum.
搜索股票信息，基于东方财富API
Inputs: input (required), count.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 3 tools
Each tool has a clearly distinct purpose: fund.echo is for testing/scaffolding, fund.knowledge retrieves knowledge base information, and fund.stock_search searches for stock data. There is no overlap in functionality, making tool selection unambiguous for an agent.
The naming is mixed in conventions: fund.echo uses a simple verb, fund.knowledge uses a noun (with a typo in the description), and fund.stock_search uses a verb_noun pattern. While readable, there is inconsistency in verb usage and structure across the tools.
With only 3 tools, the server feels thin for a financial domain (fund-mcp), as it lacks core operations like data updates, analysis, or portfolio management. However, the count is not extreme, so it is borderline appropriate but limited in scope.
The tool surface is significantly incomplete for a financial server: it includes a test tool (echo), a knowledge base tool, and a stock search tool, but misses essential operations such as retrieving detailed stock data, managing portfolios, or performing financial calculations. This will likely cause agent failures in broader financial tasks.
Token-free MCP server for structured RevoGrid Core, Pro, and Enterprise knowledge retrieval.
MCP server for querying Forkast documentation
MCP server for querying BrainKB, a knowledge base for neuroscience knowledge graphs.
Personal knowledge base MCP server with semantic search, auto-categorization, metadata extraction
