Langfuse API MCP Server
io.github.rodrigorjsf/langfuse-api-mcp
What this kind of tool is for
- Hand your agent a structured way to call a model or an inference API.
- Compare outputs from two different providers on the same prompt.
- Wire retrieval, embeddings, or generation into an existing agent workflow.
How to compare servers like this
- Provider coverage:
- Match the tool's supported providers and models to the ones your project uses.
- Cost exposure:
- Model-backed tools spend real API budget; check how usage and limits are configured.
- Maintenance signal:
- The provider landscape shifts weekly; prefer tools updated within the last few months.
- Config surface:
- Prefer tools whose environment-variable or config keys are documented plainly.
This page carries your copy-paste config: pick your MCP client in the install section on this page and use the copy button.
What is the Langfuse API MCP server?
Langfuse public API (Cloud and self-hosted): traces, prompts, datasets and gated writes.
How to install Langfuse API
Copy-paste configuration for popular MCP clients.
LANGFUSE_PUBLIC_KEYrequiredsecretThe project's public key (pk-lf-...).
LANGFUSE_SECRET_KEYrequiredsecretThe project's secret key (sk-lf-...).
LANGFUSE_BASE_URLrequiredYour Langfuse host, e.g. https://cloud.langfuse.com; https only, http only for localhost.
LANGFUSE_CA_CERTOptional PEM file with your corporate or private CA, added to the system trust store.
{
"mcpServers": {
"langfuse-api-mcp": {
"command": "npx",
"args": [
"-y",
"langfuse-api-mcp"
],
"env": {
"LANGFUSE_PUBLIC_KEY": "<YOUR_LANGFUSE_PUBLIC_KEY>",
"LANGFUSE_SECRET_KEY": "<YOUR_LANGFUSE_SECRET_KEY>",
"LANGFUSE_BASE_URL": "<YOUR_LANGFUSE_BASE_URL>",
"LANGFUSE_CA_CERT": "<YOUR_LANGFUSE_CA_CERT>"
}
}
}
}Related MCP servers

io.github.rog0x/i18n
Locale detect, translations, plurals for AI agents

CUDA-Q Docs
CUDA-Q docs, API reference, and runnable examples for AI agents, pinned to your installed version.

AI-controlled algorithmic trading engine exposing 40 MCP tools across 9 namespaces.

io.github.rohithraju-ops/mcp-ml-lab
Run end-to-end ML experiments from natural language (XGBoost, LightGBM, Optuna).

Trending content on 12 networks, best time, hashtags, templates, drafts and review, publish to 11.

io.github.roeiba/pmd
MCP server for PMD static code analyzer - run code analysis and detect duplicates