AI agents use jis_request_intent to create or update resources in Jis — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Jis environment.
The tool initiates a consent or intent request targeting another identity, which creates a new record or interaction request. This is a Write operation (creating a request/record) rather than Execute since it triggers a consent workflow rather than arbitrary code or external operations. It is not Financial or Destructive.
From the tool's definition 'Request bilateral intent from a jis: identity' and 'no interaction without mutual consent' — this sends a consent/intent request to another identity
Attacks that exploit this kind of access
Request bilateral intent from a jis: identity. This is the core of the Intent-Centric Web - no interaction without mutual consent. It is categorised as a Write tool in the Jis MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Jis MCP server in PolicyLayer and add a rule for jis_request_intent: 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 Jis. Nothing to install.
jis_request_intent 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 jis_request_intent 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 jis_request_intent. 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.
jis_request_intent is provided by the Jis MCP server (jaspertvdm/mcp-server-jis). 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 →