Create or update a voice AI agent. If an agent with the given name exists, it will be updated. Otherwise, a new agent is created with sane defaults.
AI agents use upsert_agent to create or update resources in Elba MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Elba MCP Server environment.
This tool creates or modifies agent configurations reversibly. It is not Destructive (changes are not permanent/irrevocable), not Execute (it doesn't run arbitrary code or trigger uncontrolled external operations), and not Financial. Write is the appropriate category.
From the tool's definition Tool description states 'Create or update a voice AI agent' — these are Write operations that modify data reversibly. 'If an agent with the given name exists, it will be updated. Otherwise, a new agent is created' confirms both create and update semantics.
Attacks that exploit this kind of access
Create or update a voice AI agent. If an agent with the given name exists, it will be updated. Otherwise, a new agent is created with sane defaults. It is categorised as a Write tool in the Elba MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Elba MCP Server MCP server in PolicyLayer and add a rule for upsert_agent: 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 Elba MCP Server. Nothing to install.
upsert_agent 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 upsert_agent 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 upsert_agent. 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.
upsert_agent is provided by the Elba MCP Server MCP server (kolsetu-opensource/elba-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →