clerk.replace_user_metadata
Replace the entire contents of one metadata namespace for a Clerk user. Call clerk.get_connected_accounts first. Pass clerk_instance_id to target a specific connection, or omit it to use the default account. The metadata body fully replaces the chosen namespace. Returns the updated user summary. ...
This record as markdown: /tools/io-github-vee3io-vee3/clerk.replace-user-metadata.md
What clerk.replace_user_metadata does on Vee3
AI agents use clerk.replace_user_metadata to create or update resources in Vee3, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Vee3 environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
user_id | string | Yes | Clerk user id (user_...) whose metadata to replace. |
metadata | object | Yes | New metadata dict that fully replaces the chosen namespace. Pass an empty object to clear all keys. |
metadata_type | string | Yes | Metadata namespace to replace. |
clerk_instance_id | object | — | Clerk instance id (ins_...) from clerk.get_connected_accounts. Omit to use the default connected account. |
Parameters from the server's own tool schema.
Why clerk.replace_user_metadata is rated Medium
Overwrites entire metadata namespace for a user, potentially destroying existing metadata irreversibly.
From the tool's definition fully replaces the chosen namespace
Attacks that exploit this kind of access
The rule that runs clerk.replace_user_metadata safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Vee3, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For clerk.replace_user_metadata, this is the rule to start with:
clerk.replace_user_metadata 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.
The button opens the PolicyLayer dashboard: create your workspace, connect Vee3, apply this rule, and every clerk.replace_user_metadata call is checked against it from then on.
Questions about clerk.replace_user_metadata
Replace the entire contents of one metadata namespace for a Clerk user. Call clerk.get_connected_accounts first. Pass clerk_instance_id to target a specific connection, or omit it to use the default account. The metadata body fully replaces the chosen namespace. Returns the updated user summary. Cost = 8 tokens. It is categorised as a Write tool in the Vee3 MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
clerk.replace_user_metadata accepts 4 parameters: user_id, metadata, metadata_type, clerk_instance_id. Required: user_id, metadata, metadata_type. The full parameter table on this page comes from the server's own tool schema.
Register the Vee3 MCP server in PolicyLayer and add a rule for clerk.replace_user_metadata: 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.
clerk.replace_user_metadata is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the clerk.replace_user_metadata 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.
Set action: deny in the PolicyLayer policy for clerk.replace_user_metadata. 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.
clerk.replace_user_metadata 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.
This server
Across the catalogue