AI agents call count_companies_on_addon to retrieve information from Schematic without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves a count metric about companies associated with an add-on. It performs no side effects, creates no new data, executes no external operations, and deletes nothing. It is a straightforward read operation querying billing/entitlement metadata. Low severity because misuse yields only information disclosure with no operational impact.
From the tool's definition Tool name 'count_companies_on_addon' and description 'Count how many companies have a specific add-on' indicate a query/retrieval operation that returns aggregate data without modifying any state.
Attacks that exploit this kind of access
Count how many companies have a specific add-on. It is categorised as a Read tool in the Schematic MCP Server, which means it retrieves data without modifying state.
Register the Schematic MCP server in PolicyLayer and add a rule for count_companies_on_addon: 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 Schematic. Nothing to install.
count_companies_on_addon is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the count_companies_on_addon 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 count_companies_on_addon. 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.
count_companies_on_addon is provided by the Schematic MCP server (@schematichq/schematic-mcp). 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 →