langfuse-mcp 0.9.0

Langfuse MCP server for accessing and analyzing telemetry data via natural language

Langfuse MCP Server

Model Context Protocol server for Langfuse observability. Query traces, debug errors, analyze sessions, manage prompts.

Why langfuse-mcp?

Comparison with official Langfuse MCP (as of Jan 2026):

	langfuse-mcp	Official
Traces & Observations	Yes	No
Sessions & Users	Yes	No
Exception Tracking	Yes	No
Prompt Management	Yes	Yes
Dataset Management	Yes	No
Annotation Queues	Yes	No
Scores (v2)	Yes	No
Selective Tool Loading	Yes	No

This project provides a full observability toolkit — traces, observations, sessions, exceptions, prompts, datasets, annotation queues, and scores — while the official MCP focuses on prompt management.

Quick Start

Requires uv (for uvx).

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 --python 3.11 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 --python 3.11 langfuse-mcp

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

Tools (37 total)

Category	Tools
Traces	fetch_traces, fetch_trace
Observations	fetch_observations, fetch_observation
Sessions	fetch_sessions, get_session_details, get_user_sessions
Exceptions	find_exceptions, find_exceptions_in_file, get_exception_details, get_error_count
Prompts	list_prompts, get_prompt, get_prompt_unresolved, create_text_prompt, create_chat_prompt, update_prompt_labels
Datasets	list_datasets, get_dataset, list_dataset_items, get_dataset_item, create_dataset, create_dataset_item, delete_dataset_item
Annotation Queues	list_annotation_queues, create_annotation_queue, get_annotation_queue, list_annotation_queue_items, get_annotation_queue_item, create_annotation_queue_item, update_annotation_queue_item, delete_annotation_queue_item, create_annotation_queue_assignment, delete_annotation_queue_assignment
Scores	list_scores_v2, get_score_v2
Schema	get_data_schema

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"}
)

Skill

This project includes a skill with debugging playbooks.

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

Try asking: "help me debug langfuse traces"

See skills/langfuse/SKILL.md for full documentation.

Selective Tool Loading

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

langfuse-mcp --tools traces,prompts

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

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_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": ["--python", "3.11", "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

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

Optional environment variables

Variable	Default	Description
LANGFUSE_MAX_AGE_DAYS	7	Caps the lookback window for time-based tools (fetch_traces, fetch_observations, etc.). Set to match your Langfuse instance's data retention — e.g. 30 if your retention is 30 days.

Development

uv venv --python 3.11 .venv && source .venv/bin/activate
uv pip install -e ".[dev]"
pytest

License

MIT