MCP MongoDB
Provides tools for interacting with MongoDB databases, including reading collections, executing queries, performing multi-collection aggregation pipelines with $lookup operations, and managing database resources.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@MCP MongoDBshow me the top 5 players from the users collection"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP 配置文件
{
"mcpServers": {
"mongodb": {
"command": "node",
"args": [
"E:\\project\\mongodb\\build\\index2.js"
],
"env": {
"MONGO_URI": "mongodb://localhost:27017/"
},
"disabled": false,
"autoApprove": []
},
}
}读取资源请求示例:
<use_mcp_tool> <server_name>mongodb</server_name> <tool_name>read_resource</tool_name>
{ "uri": "mongodb://localhost:27017/common" }
</use_mcp_tool>
CallToolRequestSchema、ReadResourceRequestSchema 的区别
CallToolRequestSchema: 用于执行特定操作 适合执行命令、处理数据等主动操作 示例:获取集合列表、插入数据等
ReadResourceRequestSchema: 用于读取资源内容 适合提供对资源的只读访问 示例:读取集合文档、获取数据库状态等
多表联查示例
<use_mcp_tool> <server_name>mongodb</server_name> <tool_name>multi_collection_query</tool_name>
{ "database": "common", "collection": "players", "pipeline": [ { "$lookup": { "from": "platform", "localField": "platform", "foreignField": "appKey", "as": "platformInfo" } }, { "$unwind": "$platformInfo" }, { "$project": { "_id": 1, "pid": 1, "__v": 1, "bank": 1, "ip": 1, "lobbyUrl": 1, "platform": "$platformInfo", "rtp": 1, "_collection": { "$literal": "players" } } }, { "$limit": 2 } ] }
</use_mcp_tool>
修改托送测试test
pull-request
漫长的过程
跑一下试试
This server cannot be installed
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/nan-qin/mcp-mongodb'
If you have feedback or need assistance with the MCP directory API, please join our Discord server