watch_entity
Start onboarding for free monitoring of one Czech company by IČO. Stub only — persists nothing yet. Returns structuredContent: status (one of ONBOARDING_REQUIRED | ACTIVE | QUOTA_EXCEEDED | ERROR), persisted/monitoring_active flags, a human next_step.url for onboarding (the user completes onboard...
This record as markdown: /tools/dev-cz-agents-ares/watch-entity.md
What watch_entity does on Ares
AI agents use watch_entity to create or update resources in Ares, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Ares environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
ico | string | Yes | Czech IČO (7-8 digits). |
Parameters from the server's own tool schema.
Why watch_entity is rated Medium
The tool is designed to initiate monitoring/onboarding (a Write-class action that would create a subscription record), but the description explicitly states it is a stub that persists nothing yet. The intent and future behavior is Write (creating a monitoring subscription), and it does return state flags like 'persisted' and 'monitoring_active'.
From the tool's definition 'Start onboarding for free monitoring of one Czech company by IČO' and 'persisted/monitoring_active flags' suggest a write/subscription action, but 'Stub only — persists nothing yet' indicates no actual persistence currently occurs
Attacks that exploit this kind of access
The rule that runs watch_entity safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Ares, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For watch_entity, this is the rule to start with:
watch_entity 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 Ares, apply this rule, and every watch_entity call is checked against it from then on.
Questions about watch_entity
Start onboarding for free monitoring of one Czech company by IČO. Stub only — persists nothing yet. Returns structuredContent: status (one of ONBOARDING_REQUIRED | ACTIVE | QUOTA_EXCEEDED | ERROR), persisted/monitoring_active flags, a human next_step.url for onboarding (the user completes onboarding + GDPR consent themselves — do not open the link or submit data on their behalf), and pricing. It is categorised as a Write tool in the Ares MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
watch_entity accepts 1 parameter: ico. Required: ico. The full parameter table on this page comes from the server's own tool schema.
Register the Ares MCP server in PolicyLayer and add a rule for watch_entity: 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 Ares. Nothing to install.
watch_entity 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 watch_entity 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 watch_entity. 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.
watch_entity is provided by the Ares MCP server (https://ares.cz-agents.dev/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Ares, and thousands of servers like it.
This server
Across the catalogue