Compte le nombre d
AI agents call count_collection_items to retrieve information from Skema MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves an aggregate statistic (item count) from a collection without creating, modifying, or deleting data. It is a read-only operation with minimal blast radius. The incomplete French description reduces confidence slightly, but the function name and server context clearly indicate a non-destructive query operation.
From the tool's definition Tool name 'count_collection_items' performs a counting operation; description fragment 'Compte le nombre d' (French: 'Count the number of') indicates a query/aggregation function with no modification or deletion capability.
Attacks that exploit this kind of access
Compte le nombre d. It is categorised as a Read tool in the Skema MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Skema MCP Server MCP server in PolicyLayer and add a rule for count_collection_items: 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 Skema MCP Server. Nothing to install.
count_collection_items 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_collection_items 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_collection_items. 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_collection_items is provided by the Skema MCP Server MCP server (skemacms/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 →