Langfuse Prompt Management MCP Server
OfficialLangfuse 提示管理 MCP 服务器
用于Langfuse 提示管理的模型上下文协议(MCP) 服务器。此服务器允许您通过模型上下文协议访问和管理您的 Langfuse 提示。
演示
Claude Desktop 中 Langfuse Prompts MCP 的快速演示(取消静音以进行画外音解释):
https://github.com/user-attachments/assets/61da79af-07c2-4f69-b28c-ca7c6e606405
Related MCP server: Langfuse MCP Server
特征
MCP 提示
该服务器实现了MCP Prompts 规范,用于提示发现和检索。
prompts/list:列出所有可用的提示可选的基于游标的分页
返回提示名称及其所需参数,限制:所有参数都被视为可选的,并且不包括描述,因为变量在 Langfuse 中没有规范
如果提示超过一页,则包含下一个分页光标
prompts/get:获取特定提示将 Langfuse 提示(文本和聊天)转换为 MCP 提示对象
使用提供的变量编译提示
工具
为了提高与不支持提示功能的其他 MCP 客户端的兼容性,服务器还导出复制 MCP 提示功能的工具。
get-prompts:列出可用的提示用于分页的可选
cursor参数返回提示及其参数的列表
get-prompt:检索并编译特定提示必需的
name参数:要检索的提示的名称可选
arguments:带有提示变量的 JSON 对象
发展
npm install
# build current file
npm run build
# test in mcp inspector
npx @modelcontextprotocol/inspector node ./build/index.js用法
步骤 1:构建
npm install
npm run build第 2 步:将服务器添加到您的 MCP 服务器:
克劳德桌面
通过编辑claude_desktop_config.json配置 Claude for Desktop
{
"mcpServers": {
"langfuse": {
"command": "node",
"args": ["<absolute-path>/build/index.js"],
"env": {
"LANGFUSE_PUBLIC_KEY": "your-public-key",
"LANGFUSE_SECRET_KEY": "your-secret-key",
"LANGFUSE_BASEURL": "https://cloud.langfuse.com"
}
}
}
}确保将环境变量替换为你的实际 Langfuse API 密钥。现在就可以在 Claude Desktop 中使用服务器了。
光标
将新服务器添加到 Cursor:
名称:
Langfuse Prompts类型:
command命令:
LANGFUSE_PUBLIC_KEY="your-public-key" LANGFUSE_SECRET_KEY="your-secret-key" LANGFUSE_BASEURL="https://cloud.langfuse.com" node absolute-path/build/index.js
限制
MCP 服务器仍在开发中,并且存在一些限制:
仅返回 Langfuse 中带有
production标签的提示所有参数都被视为可选的,并且不包含描述,因为变量在 Langfuse 中没有规范
列表操作需要在后台单独获取每个提示来提取参数,这种方法虽然有效,但效率不高
欢迎贡献!如果您有任何建议或反馈,请打开 issue 或 PR ( repo )。
This server cannot be deployed
Maintenance
Related MCP Connectors
- PromptOTOAuthcom.promptot
Manage, version, and publish LLM prompts with blocks, variables, and evaluations.
Enable secure connectivity between Sentry issues and debugging data, and LLM clients, using a Model Context Protocol (MCP) server.
Generate contextual prompts and reusable agent skills, evaluate prompts with the 16-dimension Prompt Score, and manage saved work in PromptDrive. Twelve MCP tools also provide authorized access to private Memory for source-grounded answers. Connect over Streamable HTTP using OAuth 2.1 and PKCE. Generation consumes account quota and automatically saves successful results; Memory access follows account permissions and plan limits.
Read and write your Fresh Jots notes from Claude, Cursor, and any MCP client.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceEnables users to organize, search, and manage a shared library of prompts across AI tools via the Model Context Protocol. It supports hierarchical folder organization, tagging, and template variable substitution for dynamic prompt generation.MIT
- AlicenseBqualityDmaintenanceModel Context Protocol server for Langfuse observability. Query traces, analyze accuracy, detect failures, track costs, debug latency, manage prompts and datasets.582MIT
- AlicenseBqualityDmaintenanceEnables AI assistants to manage, store, and retrieve prompts through the Model Context Protocol, with a web UI for prompt management and optional secure sharing via Dev Tunnels.1MIT
- AlicenseNot gradedqualityDmaintenanceMCP server for Langfuse Prompt Management that enables listing and retrieving Langfuse prompts via MCP prompts and tools.MIT