Langfuse API runs on your own machine — the client starts it, so there is no endpoint to ping. 32 installs a week from npm. Last commit 10 Oct 2026.
Langfuse public API (Cloud and self-hosted): traces, prompts, datasets and gated writes.
We read the source, 3 h ago · rules ccca72095570
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
const child = spawn(binary, process.argv.slice(2), { stdio: "inherit", shell: false, windowsHide: true });
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add langfuse-api-mcp -- npx -y langfuse-api-mcp
{
"mcpServers": {
"langfuse-api-mcp": {
"args": [
"-y",
"langfuse-api-mcp"
],
"command": "npx"
}
}
}
[mcp_servers.langfuse-api-mcp]
command = "npx"
args = ["-y", "langfuse-api-mcp"]
{
"mcpServers": {
"langfuse-api-mcp": {
"args": [
"-y",
"langfuse-api-mcp"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"langfuse-api-mcp": {
"args": [
"-y",
"langfuse-api-mcp"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
LANGFUSE_PUBLIC_KEY (The project's public key (pk-lf-...).), LANGFUSE_SECRET_KEY (The project's secret key (sk-lf-...).), LANGFUSE_BASE_URL (Your Langfuse host, e.g. https://cloud.langfuse.com; https only, http only for localhost.), LANGFUSE_CA_CERT (Optional PEM file with your corporate or private CA, added to the system trust store.).
The author declared them in the registry entry; get the values from the project itself.
Read and score Opik traces, experiments, datasets and prompts from your AI assistant.
Cloud hosted Okahu MCP server that helps you manage genAI trace data
Build and monitor LLM apps on Orq.ai: AI gateway, agents, prompts, evals, traces.
Airflow MCP — list DAGs/runs/task instances, tail logs, trigger and clear (write-gated)
Search and resolve Zenodo datasets, software, and publications by DOI; trace versions and funding.
Self-hosted, source-traceable memory layer and MCP server for AI agents, on your own Postgres.
List datasets, schemas, run APL queries, and use prompts for exploration, anomalies, and monitoring.
Policy-gated, audited SSH for Linux and Windows hosts: roles, approvals, and an audit log.
Answers built from our own checks of this server.