Loading...
Exposes Langfuse prompt management features via the Model Context Protocol, allowing retrieval and compilation of prompts with variable substitution.
Boost this tool
Subscribe to listing upgrades or segmented pushes.
Exposes Langfuse prompt management features via the Model Context Protocol, allowing retrieval and compilation of prompts with variable substitution.
This server is relatively safe for read-only prompt retrieval. However, proper handling of API keys and input sanitization are crucial to prevent security vulnerabilities. Avoid using with untrusted inputs.
Performance may be limited by the individual fetching of prompts for listing operations. Consider optimizing prompt retrieval for large prompt collections.
Cost depends on Langfuse's API usage and pricing model. Be mindful of the number of API calls made for prompt retrieval and compilation.
npm install
# build current file{
"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"
}
}
}
}LANGFUSE_PUBLIC_KEYLANGFUSE_SECRET_KEYLANGFUSE_BASEURLget-promptsLists available prompts with their arguments.
Read-only operation; no modification of data.
get-promptRetrieves and compiles a specific prompt with provided variables.
Compiles prompts with user-provided variables, which could lead to prompt injection if not handled carefully.
API Key
cloud
This server is relatively safe for read-only prompt retrieval. However, proper handling of API keys and input sanitization are crucial to prevent security vulnerabilities. Avoid using with untrusted inputs.
The server primarily provides read-only access to prompts, limiting the risk of unintended modifications. Sandboxing depends on the client application.
Production Tip
Securely manage and rotate Langfuse API keys to prevent unauthorized access.
The server uses Langfuse API keys (public and secret) for authentication.
Store API keys securely using environment variables or a secrets management system. Avoid hardcoding keys in your application.
The server does not implement caching. Prompt retrieval relies on Langfuse's API.
The server will be unable to retrieve prompts, and errors will be returned to the client application.
Prompt variables are passed as a JSON object to the `get-prompt` tool. Ensure proper sanitization to prevent prompt injection.
Only prompts with the `production` label in Langfuse are returned. Versioning is managed within Langfuse.
No, this server only supports read operations for retrieving and compiling prompts.
Marc Klingen
Contributor