Langfuse Agent MCP server
Commit Nov 13, 2026Enables agentic models to query, create, and manage Langfuse observability traces, datasets, prompt templates, and system configurations.
Also known as Knuckles-Team/langfuse-agent
- Stars
- 1
- Tools
- 87
- Downloads, 30 days
- —
- Latest version
- —
- Last commit
- Nov 13, 2026
- License
- MIT
What is Langfuse Agent MCP?
Langfuse Agent enables agentic models to query, create, and manage Langfuse observability traces, datasets, prompt templates, and system configurations. It exposes 87 tools, such as langfuse_datasets, langfuse_ingest, langfuse_management.
Summary generated from the project's README
About Langfuse Agent MCP server
Langfuse Agent serves as a bridge between agentic models and the Langfuse LLM engineering platform. It allows AI agents to interact directly with observability traces, datasets, prompt templates, and system configurations. The server functions as both a production-grade agent and an MCP server, providing developers with ways to manage their LLM lifecycle through programmatic interfaces or integrated execution entrypoints.
Users can choose between two primary tool modes to manage token usage and IDE compatibility. The condensed mode groups over 80 methods into five optimized modules like langfuse_datasets and langfuse_observability to minimize overhead. Alternatively, the verbose mode provides a 1:1 mapping to the public API, offering over 80 specific tools for granular operations. The system supports enterprise security features including OIDC token delegation and Eunomia policies, making it suitable for professional development environments.
What you can do with it
- 1Manage observability dataAn AI agent can query and manage traces and observations within the Langfuse platform.
- 2Optimize token consumptionDevelopers can use condensed tool modules to reduce the amount of context sent to the model.
Written from the project's README. Every use case is checked against a quote from it.
Langfuse Agent MCP tools 87
Detected from the READMElangfuse_datasetslangfuse_ingestlangfuse_managementlangfuse_observabilitylangfuse_prompts_modelslangfuse_annotation_queues_create_queuelangfuse_annotation_queues_create_queue_assignmentlangfuse_annotation_queues_create_queue_itemlangfuse_annotation_queues_delete_queue_assignmentlangfuse_annotation_queues_delete_queue_itemlangfuse_annotation_queues_get_queuelangfuse_annotation_queues_get_queue_item
Show all 87 toolsShow fewer tools
langfuse_annotation_queues_list_queue_itemslangfuse_annotation_queues_list_queueslangfuse_annotation_queues_update_queue_itemlangfuse_blob_storage_integrations_delete_blob_storage_integrationlangfuse_blob_storage_integrations_get_blob_storage_integration_statuslangfuse_blob_storage_integrations_get_blob_storage_integrationslangfuse_blob_storage_integrations_upsert_blob_storage_integrationlangfuse_comments_createlangfuse_comments_getlangfuse_comments_get_by_idlangfuse_dataset_items_createlangfuse_dataset_items_deletelangfuse_dataset_items_getlangfuse_dataset_items_listlangfuse_dataset_run_items_createlangfuse_dataset_run_items_listlangfuse_datasets_createlangfuse_datasets_delete_runlangfuse_datasets_getlangfuse_datasets_get_runlangfuse_datasets_get_runslangfuse_datasets_listlangfuse_health_healthlangfuse_llm_connections_listlangfuse_llm_connections_upsertlangfuse_media_getlangfuse_media_get_upload_urllangfuse_media_patchlangfuse_metrics_getlangfuse_models_createlangfuse_models_deletelangfuse_models_getlangfuse_models_listlangfuse_observations_get_manylangfuse_opentelemetry_export_traceslangfuse_organizations_delete_organization_membershiplangfuse_organizations_delete_project_membershiplangfuse_organizations_get_organization_api_keyslangfuse_organizations_get_organization_membershipslangfuse_organizations_get_organization_projectslangfuse_organizations_get_project_membershipslangfuse_organizations_update_organization_membershiplangfuse_organizations_update_project_membershiplangfuse_projects_createlangfuse_projects_create_api_keylangfuse_projects_deletelangfuse_projects_delete_api_keylangfuse_projects_getlangfuse_projects_get_api_keyslangfuse_projects_updatelangfuse_prompt_version_updatelangfuse_prompts_createlangfuse_prompts_deletelangfuse_prompts_getlangfuse_prompts_listlangfuse_scim_create_userlangfuse_scim_delete_userlangfuse_scim_get_resource_typeslangfuse_scim_get_schemaslangfuse_scim_get_service_provider_configlangfuse_scim_get_userlangfuse_scim_list_userslangfuse_score_configs_createlangfuse_score_configs_getlangfuse_score_configs_get_by_idlangfuse_score_configs_updatelangfuse_scores_createlangfuse_scores_get_manylangfuse_sessions_getlangfuse_sessions_listlangfuse_trace_deletelangfuse_trace_delete_multiplelangfuse_trace_getlangfuse_trace_listx-mcp-enabled
Configuration
LANGFUSE_DATASETSTOOLLANGFUSE_KGTOOLLANGFUSE_MANAGEMENTTOOLLANGFUSE_OBSERVABILITYTOOLLANGFUSE_PROMPTS_MODELSTOOLMCP_TOOL_MODE
Automated checks
Ran Nov 14, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachableknuckles-team/langfuse-agent is public and reachablegithub.com/knuckles-team/langfuse-agent ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-11-13github.com/knuckles-team/langfuse-agent ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model87 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNo tool named like delete, drop or execPass
- Remote endpoint answers the MCP handshakeNot checked
README
View on GitHubLangfuse Agent
API | MCP | Agent
Documentation — Installation, deployment, usage across the API, CLI, and MCP interfaces, and guidance for provisioning the Langfuse platform are maintained in the official documentation.
Overview
Langfuse Agent is a production-grade Agent and Model Context Protocol (MCP) server designed to interface directly with the Langfuse LLM Engineering and Observability platform. It enables agentic models to query, create, and manage observability traces, datasets, prompt templates, and system configurations.
Key Features
- Consolidated Action-Routed MCP Tools: Minimizes token overhead and eliminates tool bloat in LLM contexts by grouping 80+ methods into 4 optimized, togglable tool modules.
- Enterprise-Grade Security: Complete support for Eunomia policies, OIDC token delegation, and granular execution context tracking.
- Integrated Graph Agent: Built-in Pydantic AI agent supporting the Agent Control Protocol (ACP) and standard Web interfaces (AG-UI).
- Optional Telemetry & Tracing: OTLP export and Langfuse instrumentation enable only when their runtime configuration is present.
CLI or API
This agent wraps the Langfuse API. The operator can interact with it programmatically or via its integrated execution entrypoints.
Detailed instructions on how to use the underlying API wrappers, extended schema bindings, and developer SDK references are maintained in docs/index.md.
MCP
This server use dynamic Action-Routed tools to optimize token overhead and maximize IDE compatibility.
Available MCP Tools
Auto-generated — do not edit between the markers below.
Condensed action-routed tools (MCP_TOOL_MODE=condensed or both)
| MCP Tool | Toggle Env Var | Description |
|---|---|---|
langfuse_datasets |
LANGFUSE_DATASETSTOOL |
Perform langfuse_datasets operations. |
langfuse_ingest |
LANGFUSE_KGTOOL |
Perform langfuse_ingest operations. |
langfuse_management |
LANGFUSE_MANAGEMENTTOOL |
Perform langfuse_management operations. |
langfuse_observability |
LANGFUSE_OBSERVABILITYTOOL |
Perform langfuse_observability operations. |
langfuse_prompts_models |
LANGFUSE_PROMPTS_MODELSTOOL |
Perform langfuse_prompts_models operations. |
Verbose 1:1 API-mapped tools (MCP_TOOL_MODE=verbose or both)
| MCP Tool | Toggle Env Var | Description |
|---|---|---|
langfuse_annotation_queues_create_queue |
APITOOL |
Create an annotation queue |
langfuse_annotation_queues_create_queue_assignment |
APITOOL |
Create an assignment for a user to an annotation queue |
langfuse_annotation_queues_create_queue_item |
APITOOL |
Add an item to an annotation queue |
langfuse_annotation_queues_delete_queue_assignment |
APITOOL |
Delete an assignment for a user to an annotation queue |
langfuse_annotation_queues_delete_queue_item |
APITOOL |
Remove an item from an annotation queue |
langfuse_annotation_queues_get_queue |
APITOOL |
Get an annotation queue by ID |
langfuse_annotation_queues_get_queue_item |
APITOOL |
Get a specific item from an annotation queue |
langfuse_annotation_queues_list_queue_items |
APITOOL |
Get items for a specific annotation queue |
langfuse_annotation_queues_list_queues |
APITOOL |
Get all annotation queues |
langfuse_annotation_queues_update_queue_item |
APITOOL |
Update an annotation queue item |
langfuse_blob_storage_integrations_delete_blob_storage_integration |
APITOOL |
Delete a blob storage integration by ID (requires organization-scoped API key) |
langfuse_blob_storage_integrations_get_blob_storage_integration_status |
APITOOL |
Get the sync status of a blob storage integration by integration ID (requires organization-scoped API key) |
langfuse_blob_storage_integrations_get_blob_storage_integrations |
APITOOL |
Get all blob storage integrations for the organization (requires organization-scoped API key) |
langfuse_blob_storage_integrations_upsert_blob_storage_integration |
APITOOL |
Create or update a blob storage integration for a specific project (requires organization-scoped API key). The configuration is validated by performing a test upload to the bucket. |
langfuse_comments_create |
APITOOL |
Create a comment. Comments may be attached to different object types (trace, observation, session, prompt). |
langfuse_comments_get |
APITOOL |
Get all comments |
langfuse_comments_get_by_id |
APITOOL |
Get a comment by id |
langfuse_dataset_items_create |
APITOOL |
Create a dataset item |
langfuse_dataset_items_delete |
APITOOL |
Delete a dataset item and all its run items. This action is irreversible. |
langfuse_dataset_items_get |
APITOOL |
Get a dataset item |
langfuse_dataset_items_list |
APITOOL |
Get dataset items. Optionally specify a version to get the items as they existed at that point in time. Note: If version parameter is provided, datasetName must also be provided. |
langfuse_dataset_run_items_create |
APITOOL |
Create a dataset run item |
langfuse_dataset_run_items_list |
APITOOL |
List dataset run items |
langfuse_datasets_create |
APITOOL |
Create a dataset |
langfuse_datasets_delete_run |
APITOOL |
Delete a dataset run and all its run items. This action is irreversible. |
langfuse_datasets_get |
APITOOL |
Get a dataset |
langfuse_datasets_get_run |
APITOOL |
Get a dataset run and its items |
langfuse_datasets_get_runs |
APITOOL |
Get dataset runs |
langfuse_datasets_list |
APITOOL |
Get all datasets |
langfuse_health_health |
APITOOL |
Check health of API and database |
langfuse_llm_connections_list |
APITOOL |
Get all LLM connections in a project |
langfuse_llm_connections_upsert |
APITOOL |
Create or update an LLM connection. The connection is upserted on provider. |
langfuse_media_get |
APITOOL |
Get a media record |
langfuse_media_get_upload_url |
APITOOL |
Get a presigned upload URL for a media record |
langfuse_media_patch |
APITOOL |
Patch a media record |
langfuse_metrics_get |
APITOOL |
Query aggregate observation or score metrics through Metrics API v2. |
langfuse_models_create |
APITOOL |
Create a model |
langfuse_models_delete |
APITOOL |
Delete a model. Cannot delete models managed by Langfuse. You can create your own definition with the same modelName to override the definition though. |
langfuse_models_get |
APITOOL |
Get a model |
langfuse_models_list |
APITOOL |
Get all models |
langfuse_observations_get_many |
APITOOL |
Get a list of observations with cursor-based pagination and flexible field selection. ## Cursor-based Pagination This endpoint uses cursor-based pagination for efficient traversal of large datasets. The cursor is returned in the response… |
langfuse_opentelemetry_export_traces |
APITOOL |
OpenTelemetry Traces Ingestion Endpoint This endpoint implements the OTLP/HTTP specification for trace ingestion, providing native OpenTelemetry integration for Langfuse Observability. Supported Formats: - Binary Protobuf: `Conte… |
langfuse_organizations_delete_organization_membership |
APITOOL |
Delete a membership from the organization associated with the API key (requires organization-scoped API key) |
langfuse_organizations_delete_project_membership |
APITOOL |
Delete a membership from a specific project (requires organization-scoped API key). The user must be a member of the organization. |
langfuse_organizations_get_organization_api_keys |
APITOOL |
Get all API keys for the organization associated with the API key (requires organization-scoped API key) |
langfuse_organizations_get_organization_memberships |
APITOOL |
Get all memberships for the organization associated with the API key (requires organization-scoped API key) |
langfuse_organizations_get_organization_projects |
APITOOL |
Get all projects for the organization associated with the API key (requires organization-scoped API key) |
langfuse_organizations_get_project_memberships |
APITOOL |
Get all memberships for a specific project (requires organization-scoped API key) |
langfuse_organizations_update_organization_membership |
APITOOL |
Create or update a membership for the organization associated with the API key (requires organization-scoped API key) |
langfuse_organizations_update_project_membership |
APITOOL |
Create or update a membership for a specific project (requires organization-scoped API key). The user must already be a member of the organization. |
langfuse_projects_create |
APITOOL |
Create a new project (requires organization-scoped API key) |
langfuse_projects_create_api_key |
APITOOL |
Create a new API key for a project (requires organization-scoped API key) |
langfuse_projects_delete |
APITOOL |
Delete a project by ID (requires organization-scoped API key). Project deletion is processed asynchronously. |
langfuse_projects_delete_api_key |
APITOOL |
Delete an API key for a project (requires organization-scoped API key) |
langfuse_projects_get |
APITOOL |
Get Project associated with API key (requires project-scoped API key). You can use GET /api/public/organizations/projects to get all projects with an organization-scoped key. |
langfuse_projects_get_api_keys |
APITOOL |
Get all API keys for a project (requires organization-scoped API key) |
langfuse_projects_update |
APITOOL |
Update a project by ID (requires organization-scoped API key). |
langfuse_prompt_version_update |
APITOOL |
Update labels for a specific prompt version |
langfuse_prompts_create |
APITOOL |
Create a new version for the prompt with the given name |
langfuse_prompts_delete |
APITOOL |
Delete prompt versions. If neither version nor label is specified, all versions of the prompt are deleted. |
langfuse_prompts_get |
APITOOL |
Get a prompt |
langfuse_prompts_list |
APITOOL |
Get a list of prompt names with versions and labels |
langfuse_scim_create_user |
APITOOL |
Create a new user in the organization (requires organization-scoped API key) |
langfuse_scim_delete_user |
APITOOL |
Remove a user from the organization (requires organization-scoped API key). Note that this only removes the user from the organization but does not delete the user entity itself. |
langfuse_scim_get_resource_types |
APITOOL |
Get SCIM Resource Types (requires organization-scoped API key) |
langfuse_scim_get_schemas |
APITOOL |
Get SCIM Schemas (requires organization-scoped API key) |
langfuse_scim_get_service_provider_config |
APITOOL |
Get SCIM Service Provider Configuration (requires organization-scoped API key) |
langfuse_scim_get_user |
APITOOL |
Get a specific user by ID (requires organization-scoped API key) |
langfuse_scim_list_users |
APITOOL |
List users in the organization (requires organization-scoped API key) |
langfuse_score_configs_create |
APITOOL |
Create a score configuration (config). Score configs are used to define the structure of scores |
langfuse_score_configs_get |
APITOOL |
Get all score configs |
langfuse_score_configs_get_by_id |
APITOOL |
Get a score config |
langfuse_score_configs_update |
APITOOL |
Update a score config |
langfuse_scores_create |
APITOOL |
Create a typed score through Langfuse's current score-write API. |
langfuse_scores_get_many |
APITOOL |
Query scores through the cursor-based Scores API v3. |
langfuse_sessions_get |
APITOOL |
Get a session. Please note that traces on this endpoint are not paginated, if you plan to fetch large sessions, consider GET /api/public/traces?sessionId=<sessionId> |
langfuse_sessions_list |
APITOOL |
Get sessions |
langfuse_trace_delete |
APITOOL |
Delete a specific trace |
langfuse_trace_delete_multiple |
APITOOL |
Delete multiple traces |
langfuse_trace_get |
APITOOL |
Get a specific trace |
langfuse_trace_list |
APITOOL |
Get list of traces |
5 action-routed tool(s) · 81 verbose 1:1 tool(s). MCP_TOOL_MODE selects the surface (intent default · condensed action-routed · verbose 1:1 · both). Auto-generated — do not edit.
Detailed tool schemas, parameter shapes, and validation constraints are preserved in docs/usage.md.
Dynamic Tool Selection & Visibility
This MCP server supports dynamic toolset selection and visibility filtering at runtime. This allows the operator to restrict the set of exposed tools to prevent blowing up the LLM's context window.
The operator can configure tool filtering via multiple input channels:
- CLI Arguments: Pass
--toolsor--toolsets(or their disabled counterparts--disabled-toolsand--disabled-toolsets) during startup. - Environment Variables: Define standard environment variables:
MCP_ENABLED_TOOLS/MCP_DISABLED_TOOLSMCP_ENABLED_TAGS/MCP_DISABLED_TAGS
- HTTP SSE Request Headers: Pass custom headers during transport initialization:
x-mcp-enabled-tools/x-mcp-disabled-toolsx-mcp-enabled-tags/x-mcp-disabled-tags
- HTTP SSE Request Query Parameters: Append query parameters directly to the operator's transport connection URL:
?tools=tool1,tool2?tags=tag1
When query strings or parameters are provided, an LLM-free Knowledge Graph resolution layer (using DynamicToolOrchestrator) matches query intents against known tool tags, names, or descriptions, with safe fallback and automated 24-hour background cache refreshing.
MCP Configuration Examples
Install the connector-focused
[mcp]extra. Examples uselangfuse-agent[mcp]to add FastMCP / FastAPI throughscion-sdk[mcp]; the required Agent Utilities core still carriesmedulla. The[agent-runtime]extra additionally enables model orchestration.
stdio Transport (local IDEs — Cursor, Claude Desktop, VS Code)
{
"mcpServers": {
"langfuse-mcp": {
"command": "uvx",
"args": [
"--from",
"langfuse-agent[mcp]",
"langfuse-mcp"
],
"env": {
"MCP_TOOL_MODE": "intent",
"LANGFUSE_DATASETSTOOL": "True",
"LANGFUSE_KGTOOL": "True",
"LANGFUSE_MANAGEMENTTOOL": "True",
"LANGFUSE_OBSERVABILITYTOOL": "True",
"LANGFUSE_PROMPTS_MODELSTOOL": "True"
}
}
}
}
Runtime references require an alias-aware launcher such as Arbora. Other launchers must omit those entries and inject the resolved values through their own runtime secret boundary.
Streamable-HTTP Transport (networked / production)
{
"mcpServers": {
"langfuse-mcp": {
"command": "uvx",
"args": [
"--from",
"langfuse-agent[mcp]",
"langfuse-mcp",
"--transport",
"streamable-http",
"--port",
"8000"
],
"env": {
"TRANSPORT": "streamable-http",
"HOST": "127.0.0.1",
"PORT": "8000",
"MCP_TOOL_MODE": "intent",
"LANGFUSE_DATASETSTOOL": "True",
"LANGFUSE_KGTOOL": "True",
"LANGFUSE_MANAGEMENTTOOL": "True",
"LANGFUSE_OBSERVABILITYTOOL": "True",
"LANGFUSE_PROMPTS_MODELSTOOL": "True"
}
}
}
}
Alternatively, connect to a pre-deployed Streamable-HTTP instance by url:
{
"mcpServers": {
"langfuse-mcp": {
"url": "http://localhost:8000/langfuse-mcp/mcp"
}
}
}
Run a reviewed container image as a least-privilege stdio child (no listener or published port):
docker run -i --rm \
--read-only \
--cap-drop=ALL \
--security-opt=no-new-privileges \
--pids-limit=256 \
--tmpfs /tmp:rw,noexec,nosuid,nodev,size=64m \
-e TRANSPORT=stdio \
-e MCP_TOOL_MODE=intent \
-e LANGFUSE_DATASETSTOOL=True \
-e LANGFUSE_KGTOOL=True \
-e LANGFUSE_MANAGEMENTTOOL=True \
-e LANGFUSE_OBSERVABILITYTOOL=True \
-e LANGFUSE_PROMPTS_MODELSTOOL=True \
registry.example.invalid/langfuse-agent@sha256:<digest> langfuse-mcp
For containerized network HTTP, supply an authenticated TLS ingress (or
direct server TLS), exact MCP_ALLOWED_HOSTS, and an exact trusted-proxy
CIDR policy through the operator-owned deployment profile. The generator
does not emit an unauthenticated non-loopback listener.
Auto-generated from the code-read env surface (MCP_TOOL_MODE + package vars) — do not edit.
Additional Deployment Options
langfuse-agent can run as a local stdio process or container, or behind a remote
network boundary. The
Deployment guide carries
the detailed transport contract.
- Local container — launch a reviewed immutable image as a least-privilege stdio child with no listener or published port.
- Remote URL — connect through an operator-supplied authenticated HTTPS
ingress. Keep its URL, outbound identity references, trust profile, and exact
MCP_ALLOWED_HOSTSinAgentConfig.
Agent
This repository features a fully integrated Pydantic AI Graph Agent. It communicates over the Agent Control Protocol (ACP) and interacts smoothly with the Agent Web UI (AG-UI) and Terminal interface.
Running the Agent CLI
To start the interactive command-line agent, first let the process supervisor inject the Langfuse credentials and any model-provider secret. Then run:
langfuse-agent --provider openai --model-id gpt-4o
Docker Compose Orchestration
The checked-in docker/agent.compose.yml runs the MCP and agent services with
restricted containers and loopback-published ports. Provide pinned image digests
and let the process supervisor inject materialized child credentials at runtime;
never add them to the Compose file or a checked-in env file. Arbora deployments
keep only the corresponding *_REF settings in AgentConfig.
Detailed graph node architecture explanations, custom skill configurations, and agentic trace guides are available in docs/deployment.md.
Security & Governance
Built directly upon the enterprise-ready scion-sdk core, standard security parameters are fully supported:
Access Control & Policy Enforcement
- Eunomia Policies: Fine-grained, policy-driven tool authorization. Supports
none, localembedded(mcp_policies.json), or centralizedremotemodes. - OIDC Token Delegation: Compliant with RFC 8693 token exchange for flowing authenticating user credentials from Web UI / ACP → Agent → MCP.
- Scoped Credentials: Execution context runs restricted to the specific caller identity.
Runtime Security Grid
| Feature | Feature | Enablement |
|---|---|---|
| Tool Guard | Sensitivity inspection with human-in-the-loop validation | Enabled by default |
| Prompt Injection Defense | Input scanning, repetition monitoring, and recursive loop blocks | Enabled by default |
| Context Safety Guard | Stuck-loop detectors and contextual overflow preemptive alerts | Enabled by default |
Configuration & Environment Variables
Arbora configuration uses AgentConfig and secret references. Do not store
credential values in .env files or MCP catalogs.
Core API & Credentials
| Variable | Description | Default |
|---|---|---|
LANGFUSE_HOST |
Canonical Langfuse service URL. | https://cloud.langfuse.com |
LANGFUSE_PUBLIC_KEY_REF |
Runtime reference to the project public key. | (unset) |
LANGFUSE_SECRET_KEY_REF |
Runtime reference to the project secret key. | (unset) |
LANGFUSE_TLS_PROFILE_REF |
Runtime reference to a reusable TLS profile. | (unset) |
LANGFUSE_CA_BUNDLE_REF |
Runtime reference to a PEM trust store. | (unset) |
LANGFUSE_CLIENT_CERT_REF |
Runtime reference to an mTLS client certificate. | (unset) |
LANGFUSE_CLIENT_KEY_REF |
Runtime reference to the matching mTLS private key. | (unset) |
LANGFUSE_CLIENT_KEY_PASSWORD_REF |
Optional runtime reference for an encrypted client key. | (unset) |
LANGFUSE_PERSISTENCE_HMAC_KEY_REF |
Dedicated identity-HMAC key reference for graph persistence. | (unset) |
Server Configuration
| Variable | Description | Default |
|---|---|---|
HOST |
The hostname/address the server binds to. | 127.0.0.1 |
PORT |
The port the server listens on. | 8004 |
TRANSPORT |
The communication protocol (stdio, streamable-http, sse). |
stdio |
AUTH_TYPE |
Server authentication strategy (key, delegated, none). |
key |
Agent Customization
| Variable | Description | Default |
|---|---|---|
DEFAULT_AGENT_NAME |
Custom name showed for the Pydantic AI Graph Agent. | "Langfuse Agent" |
AGENT_DESCRIPTION |
Short description of the agent's responsibilities. | "AI agent for Langfuse Agent operations." |
AGENT_SYSTEM_PROMPT |
Custom system instructions override for the agent. | "" |
Tool Toggle Switches
Individual tool modules can be enabled or disabled to minimize client context size. These names match the authoritative "Toggle Env Var" column in the Available MCP Tools table above:
LANGFUSE_OBSERVABILITYTOOL(Default:True): Toggles observation/tracing tools.LANGFUSE_DATASETSTOOL(Default:True): Toggles datasets and annotation queue tools.LANGFUSE_PROMPTS_MODELSTOOL(Default:True): Toggles prompt template and model connectivity tools.LANGFUSE_MANAGEMENTTOOL(Default:True): Toggles comments, SCIM, and project management tools.
Langfuse Agent MCP questions
What tools does Langfuse Agent MCP provide?
It exposes 87 tools, including langfuse_datasets, langfuse_ingest, langfuse_management, langfuse_observability, langfuse_prompts_models.
What does Langfuse Agent do?
It acts as a production-grade agent and MCP server that interfaces with the Langfuse platform to manage observability traces, datasets, and prompts.
How does the server handle tool bloat in LLM contexts?
The server uses consolidated action-routed MCP tools to group over 80 methods into 4 optimized, togglable modules, minimizing token overhead.
Does it support integrated agents?
Yes, it includes a built-in Pydantic AI agent that supports the Agent Control Protocol (ACP) and standard Web interfaces.