switch_tenant_id · Langfuse Observability MCP: Risk & Policy

WHAT IT DOES

What switch_tenant_id does on Langfuse Observability

AI agents use switch_tenant_id to create or update resources in Langfuse Observability — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Langfuse Observability environment.

WHY IT NEEDS A POLICY

Why switch_tenant_id needs a policy

This tool modifies system state (the active tenant context) that affects subsequent operations, making it a Write action rather than Read. While not destructive, it has high severity because switching tenant contexts could cause an AI agent to inadvertently operate on wrong tenant data, access unauthorized resources, or create/modify data in the wrong isolation boundary.

From the tool's definition Tool description states it 'Switch[es] the active tenant ID used for all subsequent API requests' and is marked as 'an admin tool for multi-tenant scenarios.' This modifies the operational context and routing of all future requests.

Risk signalsAdmin/system-level operation

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

switch_tenant_id Rate-limited

switch_tenant_id stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "switch_tenant_id": {
      "limits": [
        {
          "counter": "switch_tenant_id_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Langfuse Observability, so you can run agents against it safely.

FAQ

Questions about switch_tenant_id

What does the switch_tenant_id tool do? +

Switch the active tenant ID used for all subsequent API requests. This is an admin tool for multi-tenant scenarios. Pass an empty string to clear the tenant ID. It is categorised as a Write tool in the Langfuse Observability MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on switch_tenant_id? +

Register the Langfuse Observability MCP server in PolicyLayer and add a rule for switch_tenant_id: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Langfuse Observability. Nothing to install.

What risk level is switch_tenant_id? +

switch_tenant_id is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit switch_tenant_id? +

Yes. Add a rate_limit block to the switch_tenant_id rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block switch_tenant_id completely? +

Set action: deny in the PolicyLayer policy for switch_tenant_id. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides switch_tenant_id? +

switch_tenant_id is provided by the Langfuse Observability MCP server (langfuse-observability-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.