New Your team’s decisions, in one playbook every coding agent works from. Never answer your agent twice

clerk.create_actor_token

Create an actor token that lets one user impersonate another in a connected Clerk application. Sensitive — the returned token is a high-privilege secret that grants impersonation access; do not log or expose it. Call clerk.get_connected_accounts first. Pass clerk_instance_id to target a specific ...

SERVERVee3 SOURCEhttps://mcp.vee3.io/mcp
High RISK CLASS
Category Execute
Parameters 52 required
Recommended Rate-limitedsee the rule below
Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/io-github-vee3io-vee3/clerk.create-actor-token.md

What clerk.create_actor_token does on Vee3

AI agents invoke clerk.create_actor_token to trigger actions in Vee3. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.

ParameterTypeRequiredDescription
user_id string Yes Clerk user id (user_...) of the user being impersonated.
actor_sub string Yes Clerk user id (user_...) of the impersonating actor (maps to actor.sub).
clerk_instance_id object Clerk instance id (ins_...) from clerk.get_connected_accounts. Omit to use the default connected account.
expires_in_seconds object Actor token lifetime in seconds (minimum 1). Defaults to 3600 (1 hour).
session_max_duration_in_seconds object Maximum duration in seconds for the session created from this token (minimum 1). Defaults to 1800 (30 minutes).

Parameters from the server's own tool schema.

Why clerk.create_actor_token is rated High

Creates tokens enabling one user to impersonate another, a severe privilege escalation risk.

From the tool's definition actor token grants impersonation access; high-privilege secret

Questions about clerk.create_actor_token

What does the clerk.create_actor_token tool do? +

Create an actor token that lets one user impersonate another in a connected Clerk application. Sensitive — the returned token is a high-privilege secret that grants impersonation access; do not log or expose it. Call clerk.get_connected_accounts first. Pass clerk_instance_id to target a specific connection, or omit it to use the default account. Cost = 15 tokens. It is categorised as a Execute tool in the Vee3 MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

What parameters does clerk.create_actor_token accept? +

clerk.create_actor_token accepts 5 parameters: user_id, actor_sub, clerk_instance_id, expires_in_seconds, session_max_duration_in_seconds. Required: user_id, actor_sub. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on clerk.create_actor_token? +

Register the Vee3 MCP server in PolicyLayer and add a rule for clerk.create_actor_token: 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 Vee3. Nothing to install.

What risk level is clerk.create_actor_token? +

clerk.create_actor_token is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit clerk.create_actor_token? +

Yes. Add a rate_limit block to the clerk.create_actor_token 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 clerk.create_actor_token completely? +

Set action: deny in the PolicyLayer policy for clerk.create_actor_token. 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 clerk.create_actor_token? +

clerk.create_actor_token is provided by the Vee3 MCP server (https://mcp.vee3.io/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

More on Vee3, and thousands of servers like it.

// THE MCP REGISTRY

PolicyLayer tracks 44,603 MCP servers and 515,000+ tools.

Every server has a live record: who publishes it, whether it answers without auth, its risk grade, every tool classified, the recommended policy. This page is one line of Vee3's. Pull the full record:

Teams ship this data inside their own products. See what a licence covers →

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.