// SCAN REPORT

Langfuse Mcp Extended

24 tools. 8 can modify or destroy data without limits.

3 destructive tools with no built-in limits. Policy required.

Last updated: 30 Jun 2026

8 can modify or destroy data

16 read-only

24 tools total

Community server · catalogue entry verified 30/06/2026

How to control Langfuse Mcp Extended ↓

TOOL MAP

What Langfuse Mcp Extended exposes to your agents

Read (16) Write / Execute (5) Destructive / Financial (3)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Langfuse Mcp Extended tools

Destructive · High deleteDatasetItem This tool permanently removes data without possibility of recovery. Destructive · High deleteScore The tool permanently deletes a score record with no undo capability. Destructive · High deleteTrace The tool permanently removes trace data without the ability to recover it. Write · Medium createDataset This tool creates new datasets, which is a write operation that modifies state by adding records to the Langfuse system.

8 of Langfuse Mcp Extended's 24 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Langfuse Mcp Extended

PolicyLayer is an MCP gateway — it sits between your AI agents and Langfuse Mcp Extended, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations

{
  "deleteDatasetItem": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "createDataset": {
    "limits": [
      {
        "counter": "createdataset_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "getDataset": {
    "limits": [
      {
        "counter": "getdataset_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Langfuse Mcp Extended — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON LANGFUSE MCP EXTENDED →

Instant setup, no code required.

FULL CATALOGUE

All 24 Langfuse Mcp Extended tools

DESTRUCTIVE 3 tools

Destructive deleteDatasetItem Delete a specific dataset item. This action is irreversible. Destructive deleteScore Delete a specific score. This action is irreversible. Destructive deleteTrace Delete a specific trace. This action is irreversible.

WRITE 5 tools

Write createDataset Create a new dataset for evaluation. Datasets contain items with expected inputs/outputs for testing LLM appli Write createDatasetItem Create or upsert a dataset item. Use id parameter for idempotent updates. Write createDatasetRunItem Create a dataset run item linking a trace/observation to a dataset item for evaluation. Write createScore Create a score for a trace or observation. Supports numeric, boolean, and categorical score types. Write createScoreConfig Create a score configuration that defines validation rules for scores. Supports numeric ranges, categorical va

READ 16 tools

Read getDataset Get a dataset by name including its items and run names. Read getDatasetItem Get a specific dataset item by ID. Read getDatasetRun Get a specific dataset run by name including its run items. Read getObservation Get a specific observation with all details including input/output, usage, costs, and timing. Read getScore Get a specific score by ID. Read getScoreConfig Get a specific score configuration by ID. Read getSession Get a specific session by ID including its traces. Read getTrace Get a specific trace with full details including all observations and scores. Read listDatasetItems List items in a dataset with optional filtering. Read listDatasetRuns List all runs for a specific dataset. Read listDatasets List all datasets in the project. Read listObservations List observations (generations, spans, events) with cursor-based pagination. Includes usage metrics, costs, an Read listScoreConfigs List all score configurations in the project. Read listScores List scores with filtering. Supports both trace and observation scores. Read listSessions List all sessions. Sessions group multiple traces from the same user interaction. Read listTraces List traces with filtering and pagination. Returns trace metadata including latency, cost, and observation/sco

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Langfuse Mcp Extended

Can an AI agent delete data through the Langfuse Mcp Extended MCP server? +

Yes. The Langfuse Mcp Extended server exposes 3 destructive tools including deleteDatasetItem, deleteScore, deleteTrace. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Langfuse Mcp Extended? +

The Langfuse Mcp Extended server has 5 write tools including createDataset, createDatasetItem, createDatasetRunItem. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Langfuse Mcp Extended.

How many tools does the Langfuse Mcp Extended MCP server expose? +

24 tools across 3 categories: Destructive, Read, Write. 16 are read-only. 8 can modify, create, or delete data.

How do I enforce a policy on Langfuse Mcp Extended? +

Register the Langfuse Mcp Extended MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Langfuse Mcp Extended tool call.

Deterministic rules across all 24 Langfuse Mcp Extended tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON LANGFUSE MCP EXTENDED →

Instant setup, no code required.

24 Langfuse Mcp Extended tools catalogued and risk-classified — across an index of 43,000+ MCP servers.