L
LangFuse
Query LangFuse traces, prompts and scores.
·No reviews yet
Share:
About
Auto-generated
LangFuse is a Model Context Protocol server in the Analytics & Monitoring category. It lets AI assistants that speak MCP call its tools and read its resources over STDIO.
Example tools
Illustrative tool names — the actual tool set is defined by the server at runtime.
list_resources
Enumerate resources exposed by this MCP
get_resource
Fetch a resource by ID
invoke
Invoke the primary action of this MCP
Screenshots
No screenshots yet.
Frequently Asked Questions
Common questions about LangFuse.
- What is the LangFuse MCP and what does it do?
- The LangFuse MCP provides an interface to query LangFuse traces, prompts, and scores. It enables developers to integrate LangFuse observability features directly into their development workflows for AI applications.
- How do I install the LangFuse MCP in an MCP client?
- Installation in clients like Cursor requires specifying the 'langfuse' slug and 'stdio' transport. You typically add it to your client's configuration file, which then enables the client to discover and interact with the MCP server.
- Does the LangFuse MCP require an API key for authentication?
- Yes, the LangFuse MCP uses an API key for authentication. You will need to obtain an API key from LangFuse and configure it within your MCP client or environment to establish a connection.
- What are some typical use cases for the LangFuse MCP?
- Typical use cases include debugging LLM applications by inspecting traces, analyzing prompt effectiveness, and monitoring the performance of AI models. It helps in understanding the behavior of complex AI systems.
- What is a limitation or prerequisite for using the LangFuse MCP?
- A key prerequisite for using the LangFuse MCP is an active LangFuse instance and associated API key. Without a properly configured LangFuse environment, the MCP will not be able to retrieve any observability data.
Install LangFuse
Claude Desktop
Add this to claude_desktop_config.json.
{
"mcpServers": {
"langfuse": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-langfuse"
]
}
}
}Cursor
Add this to ~/.cursor/mcp.json.
{
"mcpServers": {
"langfuse": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-langfuse"
]
}
}
}VS Code
Add this to your workspace settings.json.
{
"mcp.servers": {
"langfuse": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-langfuse"
]
}
}
}Reviews
Sign in to leave a review.
No reviews yet. Be the first!
Discussion(0)
No comments yet.