Yunxin Mcp Server
by
Provides a suite of tools to access, send, query, and analyze NetEase YunXin IM and RTC data, enabling operational messaging, historical analysis, daily statistics, real‑time monitoring of online users, message volume, API/SDK usage, and RTC room quality.
Yunxin Mcp Server Overview
What is Yunxin Mcp Server about?
Yunxin Mcp Server offers a collection of utilities for interacting with NetEase YunXin instant‑messaging (IM) and real‑time communication (RTC) services. It supports sending messages, retrieving chat histories, extracting daily IM statistics, and monitoring a wide range of RTC metrics such as room members, quality indicators, and top‑ranked rooms.
How to use Yunxin Mcp Server?
- Clone the repository:
git clone https://github.com/netease-im/yunxin-mcp-server.git - Install dependencies (Node.js environment is assumed):
npm install - Follow the how_to_use guide in
docs/how_to_use.mdfor authentication setup and API endpoint configuration. - Execute the desired tool via the provided command‑line scripts or integrate the HTTP APIs into your own services.
Key features of Yunxin Mcp Server
- Message Operations:
send_p2p_msgandsend_team_msgfor sending one‑to‑one or group text messages. - History Queries:
query_p2p_msg_historyandquery_team_msg_historyto fetch chat records within a time range. - Daily IM Statistics:
query_application_im_daily_statscovering active users, message traffic, storage usage, callback performance, etc. - RTC Room Insights: Member listings, online duration, location, device info, and quality metrics (stuck rate, network latency, success rates).
- Top‑20 Room Rankings:
query_rtc_room_top_20for monitoring rooms with highest traffic or quality issues. - Real‑time Distributions:
query_rtc_quality_distributionprovides multi‑dimensional quality breakdowns. - Online & Traffic Monitoring:
query_im_online_connect_latest,query_im_msg_latest,query_im_api_stats_last, andquery_im_sdk_stats_lastfor live user counts, message flow, API/SDK performance.
Use cases of Yunxin Mcp Server
- Operational Messaging: Push promotional or system notifications to individual users or groups.
- Customer Support & Analytics: Retrieve chat histories for sentiment analysis or compliance auditing.
- Service Health Monitoring: Continuously track online user counts, message volume spikes, API latency, and error rates.
- RTC Quality Assurance: Detect rooms with high audio/video stutter, investigate network/region‑specific issues, and prioritize troubleshooting.
- Product Management: Generate daily IM usage reports to guide capacity planning and feature adoption strategies.
FAQ from the Yunxin Mcp Server
Q: Which programming language/environment is required? A: The project is built with Node.js; a recent LTS version (>=14) and npm are sufficient.
Q: How do I obtain the necessary authentication credentials? A: Contact NetEase YunXin technical support or your account manager to receive API keys and secret tokens; set them as environment variables before running the tools.
Q: Can I extend the server with custom queries? A: Yes, the repository provides modular scripts; you can add new endpoints by following the existing pattern and updating the documentation.
Q: Is there a rate limit for the provided APIs? A: Refer to the official YunXin API documentation; the server itself does not impose additional limits.
Q: Where can I find detailed usage examples?
A: Each tool has a dedicated markdown file in the docs/ folder (e.g., send_msg.md, query_msg.md).
Yunxin Mcp Server's README
yunxin-mcp-server
- 如果你是云信的客户，并且希望通过大模型来处理云信IM/RTC相关的功能和数据，那么yunxin-mcp-server可能适合你
- yunxin-mcp-server提供了一系列的工具，来访问和分析云信IM/RTC相关的功能和数据
- 如果你对当前提供的工具有什么建议，或者有其他的工具需求，欢迎留言告诉我们！
- 有任何问题欢迎联系云信技术支持，或者添加微信
hdnxttl
架构图
如何使用
示例：how_to_use
介绍文章：微信公众号
工具集合
send_p2p_msg/send_team_msg
- 功能：发送单聊/群聊消息
- 说明：根据发送方accid和接收方accid，发送一条单聊文本消息；根据发送方accid和群tid，发送一条群聊文本消息
- 场景：发送运营类消息
- 示例：send_msg
query_p2p_msg_history/query_team_msg_history
- 功能：查询单聊/群聊历史消息
- 说明：根据发送方accid和接受方accid，以及时间戳范围，查询历史消息；根据accid和群tid，以及时间戳范围，查询群聊历史消息
- 场景：分析历史消息辅助运营
- 示例：query_msg
query_application_im_daily_stats
- 功能：查询应用IM每日统计数据
- 说明：当前包括：日活、上下行消息量、累积的文件存储量、抄送（次数、成功率和平均耗时）、第三方回调（次数、成功率和平均耗时）
- 场景：分析每日统计数据，检查服务是否有异常
- 示例：query_application_im_daily_stats
query_rtc_room_members/query_rtc_room_members_by_uids
- 功能：查询rtc房间的成员信息
- 说明：查询一个rtc房间中的成员信息，可以查询所有成员，也可以指定uid列表查询部分成员，可以查询成员在线时长、所在的地区和运营商、设备信息等
- 场景：分析rtc房间基本信息
- 示例：query_rtc_room_members
query_rtc_room_stuck_rate/query_rtc_room_user_stuck_rate
- 功能：查询房间音视频卡顿率指标，可以是房间级别或者uid级别
- 说明：查询某个或者某几个房间的卡顿率
- 场景：查询房间卡顿率，监控线上服务
- 示例：query_rtc_room_stuck_rate
query_rtc_room_top_20
- 功能：按照指标获取 Top 20 的房间，根据 Top 20 房间查询近 30 分钟其它相关指标
- 说明：支持指标：通话用户数、用户平均进房时长、视频卡顿率、音频卡顿率、音频网络延时、视频网络延时
- 场景：监控系统整体运行状况
- 示例：query_rtc_room_top_20
query_rtc_quality_distribution
- 功能：查询指标实时多维度分布
- 说明：支持的维度：操作系统、国家、省份、sdk版本、网络；支持的指标：5s 进房成功率、音频卡顿率、视频卡顿率
- 场景：监控系统整体运行状况
- 示例：query_rt_quality_distribution
query_im_online_connect_latest/query_im_online_connect
- 功能：查询在线人数
- 说明：支持查询最新的在线人数，也支持根据时间范围查询在线人数，允许查询最近7天的数据，每次查询最多8小时
- 场景：分析在线人数波动情况
- 示例：query_online_connect
query_im_msg_latest/query_im_msg
- 功能：查询上下行消息量，1分钟一个点
- 说明：支持查询最近n分钟的上下行消息量，也支持根据时间范围查询上下行消息量，允许查询最近7天的数据，每次查询最多8小时
- 场景：分析上下行消息的波动情况
- 示例：query_im_msg
query_im_api_stats/query_im_api_stats_last
- 功能：查询api调用情况，包括调用数量、平均响应时间、错误码情况，1分钟一个点
- 说明：支持查询最近n分钟的api调用情况，也支持根据时间范围查询，允许查询最近7天的数据，每次查询最多8小时；支持查询api的整体情况，也支持查询单个接口的情况
- 场景：分析api调用的情况
- 示例：query_im_api_stats
query_im_sdk_stats/query_im_sdk_stats_last
- 功能：查询sdk调用情况，包括调用数量、平均响应时间、错误码情况，1分钟一个点
- 说明：支持查询最近n分钟的sdk调用情况，也支持根据时间范围查询，允许查询最近7天的数据，每次查询最多8小时；支持查询api的整体情况，也支持查询单个接口的情况(目前支持以下接口级别的统计：登录、单聊消息、群聊消息、系统通知、聊天室消息)
- 场景：分析sdk调用的情况
- 示例：query_im_sdk_stats
Yunxin Mcp Server Reviews
Login Required
Please log in to share your review and rating for this MCP.
Actions
Yunxin Mcp Server's Information
- Author
- netease-im
- Category
- Monitoring & Observability
- Language
- Python
- License
- MIT License
- Stars
- 7
- Updated
- about 1 month ago
Related MCP Servers
Discover more MCP servers with similar functionality and use cases
Netdata
by netdata
Real-time, per‑second infrastructure monitoring platform that provides instant insights, auto‑discovery, edge‑based machine‑learning anomaly detection, and lightweight visualizations without requiring complex configuration.
Arize Phoenix
Officialby Arize-ai
Arize Phoenix is an open-source AI and LLM observability tool for inspecting traces, managing prompts, curating datasets, and running experiments.
Tianji
by msgbyte
Provides website analytics, uptime monitoring, and server status in a single self‑hosted application.
MCP Server For Grafana
by grafana
Provides programmatic access to Grafana dashboards, datasources, alerts, incidents, and related operational data through a Model Context Protocol server, enabling AI assistants and automation tools to query and manipulate Grafana resources.
Dynatrace MCP Server
by dynatrace-oss
Provides a local server that enables real‑time interaction with the Dynatrace observability platform, exposing tools for problem retrieval, DQL execution, Slack notifications, workflow automation, and AI‑assisted troubleshooting.
Logfire MCP
by pydantic
Provides tools to retrieve, query, and visualize OpenTelemetry traces and metrics from Pydantic Logfire via a Model Context Protocol server.
VictoriaMetrics MCP Server
by VictoriaMetrics-Community
Access VictoriaMetrics instances through Model Context Protocol, enabling AI assistants and tools to query metrics, explore labels, debug configurations, and retrieve documentation without leaving the conversational interface.
Axiom
Officialby axiomhq
Axiom MCP Server implements the Model Context Protocol (MCP) for Axiom, enabling AI agents to query logs, traces, and other event data using the Axiom Processing Language (APL). It allows AI agents to perform monitoring, observability, and natural language analysis of data for debugging and incident response.
Datadog
by GeLi2001
Datadog MCP Server is a Model Context Protocol (MCP) server that interacts with the official Datadog API. It enables users to access and manage various Datadog functionalities, including monitoring, dashboards, metrics, events, logs, and incidents.