Langfuse MCP Server

Agent-facing Model Context Protocol server and skill for Langfuse observability.

Use langfuse-mcp from Claude Code, Codex, Cursor, or any MCP client to query traces, inspect generations, debug exceptions, analyze sessions, manage prompts, browse datasets, and understand what your AI agents did in production.

What You Can Do

• Debug failing agent runs from Langfuse traces and observations.
• Find exceptions, slow generations, high-latency spans, and affected users.
• Inspect sessions and user journeys without leaving your agent workflow.
• Manage prompt versions, labels, datasets, annotation queues, and scores.
• Install the included langfuse agent skill for ready-made debugging playbooks.

Project Links

• Quick Start
• Agent Skill
• Tools
• Selective Tool Loading
• Read-Only Mode
• Other Clients

Why langfuse-mcp?

Langfuse is where your traces live. langfuse-mcp makes that telemetry directly usable by agents that need to answer questions like "what failed?", "why was this slow?", "which prompt version ran?", or "what happened in this user's session?"

Positioning relative to the native Langfuse MCP (as of June 2026):

This project does not mirror every native Langfuse MCP tool. It focuses on agent debugging ergonomics — compact trace inspection, exception triage, session analysis, routing-decision workflows, local tool-group gating, and an included skill with ready-made investigation playbooks. Use the native MCP for the broad hosted API surface; use langfuse-mcp as a local, token-disciplined layer.

Quick Start

Requires uv (for uvx) and Python 3.10 or newer. CI verifies Python 3.10 through 3.14.

Get credentials from Langfuse Cloud → Settings → API Keys. If self-hosted, use your instance URL for LANGFUSE_HOST.

# Claude Code (project-scoped, shared via .mcp.json)
claude mcp add \
  -e LANGFUSE_PUBLIC_KEY=pk-... \
  -e LANGFUSE_SECRET_KEY=sk-... \
  -e LANGFUSE_HOST=https://cloud.langfuse.com \
  --scope project \
  langfuse -- uvx langfuse-mcp

# Codex CLI (user-scoped, stored in ~/.codex/config.toml)
codex mcp add langfuse \
  --env LANGFUSE_PUBLIC_KEY=pk-... \
  --env LANGFUSE_SECRET_KEY=sk-... \
  --env LANGFUSE_HOST=https://cloud.langfuse.com \
  -- uvx langfuse-mcp

To pin a CI-verified interpreter explicitly, add --python 3.14 before langfuse-mcp.

Restart your CLI, then verify with /mcp (Claude Code) or codex mcp list (Codex).

Agent Skill

This repo ships a first-party langfuse skill for Claude Code and Codex. The skill gives agents concrete playbooks for trace debugging, exception triage, latency analysis, prompt management, and dataset work.

Install it when you want the agent to know when to reach for Langfuse and which MCP tools to call first.

Via skills (recommended):

npx skills add avivsinai/langfuse-mcp -g -y

Via skild:

npx skild install @avivsinai/langfuse -t claude -y

Manual install:

cp -r skills/langfuse ~/.claude/skills/   # Claude Code
cp -r skills/langfuse ~/.codex/skills/    # Codex CLI

After installing the skill, try:

help me debug langfuse traces
find exceptions in the last day
why was this user's session slow?

The MCP server provides the tools; the skill provides the agent-facing workflow. See skills/langfuse/SKILL.md, skills/langfuse/references/setup.md, and skills/langfuse/references/tool-reference.md.

Tools (48 total)

Dataset Item Updates (Upsert)

Langfuse uses upsert for dataset items. To edit an existing item, call create_dataset_item with item_id. If the ID exists, it updates; otherwise it creates a new item.

create_dataset_item(
  dataset_name="qa-test-cases",
  item_id="item_123",
  input={"question": "What is 2+2?"},
  expected_output={"answer": "4"}
)

Metrics Queries

query_metrics aggregates telemetry server-side (cost, latency, tokens, counts, score values) so agents can answer "what did inference cost?" or "what's p95 latency by model?" without pulling raw traces. Call get_metrics_schema for the full view/dimension/measure catalog.

query_metrics(
  view="observations",
  metrics=[{"measure": "totalCost", "aggregation": "sum"},
           {"measure": "latency", "aggregation": "p95"}],
  dimensions=["providedModelName"],
  age=1440,  # last 24h; or pass from_timestamp / to_timestamp
)

High-cardinality fields (id, traceId, userId, sessionId) must be used in filters, not dimensions. The v2 metrics endpoint is Langfuse Cloud-only; self-hosted instances may return 404.

Selective Tool Loading

Load only the tool groups you need to reduce token overhead:

langfuse-mcp --tools traces,prompts

Available groups: traces, observations, routing, sessions, exceptions, prompts, datasets, annotation_queues, scores, metrics, schema

The routing group is router-neutral. It reads Langfuse span observations with metadata.schema_version: "mcp.route_decision.v1" and filters on route-decision fields stored in observation metadata, such as decision_id, router_name, provider, and capability_id.

Read-Only Mode

Disable all write operations for safer read-only access:

langfuse-mcp --read-only
# Or via environment variable
LANGFUSE_MCP_READ_ONLY=true langfuse-mcp

This disables: create_text_prompt, create_chat_prompt, update_prompt_labels, create_dataset, create_dataset_item, delete_dataset_item, create_dataset_run_item, delete_dataset_run, create_annotation_queue, create_annotation_queue_item, update_annotation_queue_item, delete_annotation_queue_item, create_annotation_queue_assignment, delete_annotation_queue_assignment

Default Output Mode

Set the MCP-exposed default output_mode so clients that omit the parameter automatically use your preferred mode:

langfuse-mcp --default-output-mode full_json_file
# Or via environment variable
LANGFUSE_MCP_DEFAULT_OUTPUT_MODE=full_json_file langfuse-mcp

Supported values: compact, full_json_string, full_json_file

This updates the default shown in MCP tool schemas. Clients can still override it per call by passing output_mode explicitly.

Other Clients

Cursor

Create .cursor/mcp.json in your project (or ~/.cursor/mcp.json for global):

{
  "mcpServers": {
    "langfuse": {
      "command": "uvx",
      "args": ["langfuse-mcp"],
      "env": {
        "LANGFUSE_PUBLIC_KEY": "pk-...",
        "LANGFUSE_SECRET_KEY": "sk-...",
        "LANGFUSE_HOST": "https://cloud.langfuse.com",
        "LANGFUSE_MCP_DEFAULT_OUTPUT_MODE": "full_json_file"
      }
    }
  }
}

Docker (single project)

docker run --rm -i \
  -e LANGFUSE_PUBLIC_KEY=pk-... \
  -e LANGFUSE_SECRET_KEY=sk-... \
  -e LANGFUSE_HOST=https://cloud.langfuse.com \
  ghcr.io/avivsinai/langfuse-mcp:latest

HTTP transport — shared ser