AI agents call card_schema to retrieve information from Scrumdo without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears designed to query or return the structure/schema of card objects, which is a read-only information retrieval operation with no side effects. However, confidence is moderate due to empty description. If it actually modifies schema or executes operations, this classification would be incorrect.
From the tool's definition Tool name 'card_schema' suggests retrieving schema/metadata information about cards. No description provided to confirm, but naming convention and context (ScrumDo board operations) indicates a data retrieval function rather than modification or execution.
Attacks that exploit this kind of access
card_schema. It is categorised as a Read tool in the Scrumdo MCP Server, which means it retrieves data without modifying state.
Register the Scrumdo MCP server in PolicyLayer and add a rule for card_schema: 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 Scrumdo. Nothing to install.
card_schema 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 card_schema 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 card_schema. 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.
card_schema is provided by the Scrumdo MCP server (scrumdollc/scrumdo-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 →