Langfuse MCP Server
by Susanne192
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LANGFUSE_HOST | No | Langfuse instance URL. Use https://cloud.langfuse.com for Langfuse Cloud, or your own instance URL if self-hosted. | https://cloud.langfuse.com |
| LANGFUSE_PUBLIC_KEY | Yes | Langfuse public API key (e.g. pk-...), obtained from Langfuse Cloud → Settings → API Keys. Used to authenticate against the Langfuse API. | |
| LANGFUSE_SECRET_KEY | Yes | Langfuse secret API key (e.g. sk-...), obtained from Langfuse Cloud → Settings → API Keys. Used to authenticate against the Langfuse API. | |
| LANGFUSE_MCP_PROFILE | No | Profile to load from the profiles file; same as --profile. Used to serve multiple Langfuse projects, one MCP server per profile. | |
| LANGFUSE_MAX_AGE_DAYS | No | 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. | 7 |
| LANGFUSE_MCP_READ_ONLY | No | Set to true to disable all write operations for safer read-only access (same as --read-only). 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 and delete_annotation_queue_assignment. | false |
| LANGFUSE_MCP_PROFILES_FILE | No | Path of the profiles file; same as --profiles-file. | $XDG_CONFIG_HOME/langfuse-mcp/profiles.toml (or ~/.config/langfuse-mcp/profiles.toml) |
| LANGFUSE_MCP_DEFAULT_OUTPUT_MODE | No | MCP-exposed default output_mode so clients that omit the parameter automatically use your preferred mode (same as --default-output-mode). Supported values: compact, full_json_string, full_json_file. | |
| LANGFUSE_MCP_TRACE_TIMEOUT_SECONDS | No | Per-request read timeout (seconds) for single-trace fetches (fetch_trace). Raise it if large traces with include_observations=True time out. Must be a positive integer. | 120 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
This server cannot be deployed
Maintenance
ActivityActive
ResponsivenessNo issues