MCP & AI Agent Integration

Langfuse
automation.

15 AI agent actions for Langfuse — callable from any MCP-compatible runtime, Claude, Cursor, or Cerebral OS workflow. Use Langfuse to automate business processes and connect tools in your stack. Full governance, audit trail, and dry-run safety on every execution.

No credit card required
Live in production environments
<200ms median execution
Dry-run before production
Execution trace
live
15
actions
100%
governed
<200ms
latency
15
AI agent actions
8
Read operations
7
Write operations
0
High-risk actions (approval gated)
Business Tools Langfuse is a Business Tools integration — use it to automate business operations and workflow automation from any AI agent or MCP-compatible runtime.
Actions

What you can do
with Langfuse.

Every action below is available as an MCP tool and a verb in Cerebral OS — callable from any AI agent, Claude, Cursor, Windsurf, or your own runtime via the BYOA API. All executions are governed, audited, and dry-run safe.

Get Generation
langfuse:get_generation
Fetch a single generation by ID with usage and cost information.
Read Low risk
Get Session
langfuse:get_session
Fetch a single session by ID with associated traces and metrics.
Read Low risk
Get Span
langfuse:get_span
Fetch a single span by ID with timing and metadata information.
Read Low risk
Get Trace
langfuse:get_trace
Fetch a single trace by ID with all associated spans and generations.
Read Low risk
List Generations
langfuse:list_generations
List generations with optional filtering and pagination.
Read Low risk
List Scores
langfuse:list_scores
List scores with optional filtering and pagination.
Read Low risk
List Sessions
langfuse:list_sessions
List sessions with optional filtering and pagination.
Read Low risk
List Traces
langfuse:list_traces
List traces with optional filtering and pagination.
Read Low risk
Create Generation
langfuse:create_generation
Create a new generation to track an LLM model call.
Write Medium risk
Create Score
langfuse:create_score
Create a score to evaluate a trace or observation.
Write Medium risk
Create Span
langfuse:create_span
Create a new span to track a sub-operation within a trace.
Write Medium risk
Create Trace
langfuse:create_trace
Create a new trace to track an LLM application execution.
Write Medium risk
Update Generation
langfuse:update_generation
Update an existing generation with new data.
Write Medium risk
Update Span
langfuse:update_span
Update an existing span with new data.
Write Medium risk
Update Trace
langfuse:update_trace
Update an existing trace with new data.
Write Medium risk
MCP & Runtime API

Call Langfuse
from any AI agent.

Any AI agent — Claude, Cursor, LangChain, AutoGen, or your own — can call Langfuse actions through the Cerebral OS Runtime API. Governance, credentials, and audit trail fire automatically.

langfuse:get_generation READ
# Call via Runtime API
curl
-X POST \
  "https://api.cerebralos.com/v1/runtime/actions/run"
  -H "X-API-Key: YOUR_KEY" \
  -d '{
    "verb": "langfuse:get_generation",
    "args": {},
    "execution_id": "agent-001"
  }'
langfuse:create_generation WRITE
# Dry-run first — no production risk
curl
-X POST \
  "https://api.cerebralos.com/v1/runtime/actions/run"
  -H "X-API-Key: YOUR_KEY" \
  -d '{
    "verb": "langfuse:create_generation",
    "args": {},
    "execution_id": "agent-001",
    "metadata": {"dryRun": true}
  }'
Get your Runtime API key at app.cerebralos.com/signup — 1,000 free executions, no credit card required.
AI agent examples

What your AI agent
can do with Langfuse.

Real patterns your AI agent can execute via MCP or the Runtime API. Every action governed, dry-run safe, and fully audited.

Trigger
AI agent needs Langfuse data
Call langfuse:get_generation via MCP or Runtime API
AI processes result and takes next action
Full execution logged to audit trail automatically
Trigger
Workflow needs to write to Langfuse
Dry-run validates langfuse:create_generation before execution
Approval gate fires if risk level is high
Action executes with full governance — logged, audited, reversible
Trigger
Event in Langfuse
Process with AI agent
Take governed action
Log to audit trail
How it works

Every Langfuse action
governed end-to-end.

Cerebral OS isn't a connector. It's the execution layer that sits in front of Langfuse — adding governance, dry-run safety, and a full audit trail to every operation.

Governance first
Every verb carries a risk classification. High-risk writes require explicit approval gates before they execute in production.
Dry-run safe
Simulate any Langfuse action before it touches production. See exactly what would happen before a single real call is made.
Immutable audit trail
Every Langfuse action is logged — what ran, what changed, who approved it, when it happened. Full history on every verb, forever.
Connect with

Langfuse works best
alongside these.

Build multi-step workflows that connect Langfuse to the rest of your stack. All governed. All audited.

Langfuse integration

Start free.
No credit card required.

Start free with 1,000 runs — no credit card required. Connect Langfuse in minutes, dry-run every action before it touches production, full audit trail on everything.

Start free — 1,000 runs Browse all integrations →