Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
LANGFUSE_HOSTNoLangfuse instance URL. Defaults to https://cloud.langfuse.com; use your own instance URL when self-hosted. Passed via CLI flag --host or this environment variable.
LANGFUSE_PUBLIC_KEYYesLangfuse public key (from Langfuse Cloud → Settings → API Keys). Passed via CLI flag --public-key or this environment variable.
LANGFUSE_SECRET_KEYYesLangfuse secret key (from Langfuse Cloud → Settings → API Keys). Passed via CLI flag --secret-key or this environment variable.
LANGFUSE_MCP_PROFILENoProfile to load from the profiles file; same as --profile. Selects a Langfuse project profile.
LANGFUSE_MAX_AGE_DAYSNoCaps 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_ONLYNoDisable all write operations for safer read-only access, e.g. LANGFUSE_MCP_READ_ONLY=true langfuse-mcp. Same as the --read-only flag.
LANGFUSE_MCP_PROFILES_FILENoPath of the profiles file; same as --profiles-file. Defaults to $XDG_CONFIG_HOME/langfuse-mcp/profiles.toml (or ~/.config/langfuse-mcp/profiles.toml).
LANGFUSE_MCP_DEFAULT_OUTPUT_MODENoMCP-exposed default output_mode so clients that omit the parameter automatically use your preferred mode. Supported values: compact, full_json_string, full_json_file. Same as --default-output-mode.
LANGFUSE_MCP_TRACE_TIMEOUT_SECONDSNoPer-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

NameDescription

No tools

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources