AI agents call show_workshop_card to retrieve information from Steam-MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays Steam Workshop search results. It has no capability to modify Workshop items, execute commands, delete data, or commit financial transactions. It is a read-only operation that queries existing data and presents it in a prefab card format. The blast radius is minimal—misuse would only result in displaying search results to the user.
From the tool's definition Tool name 'show_workshop_card' and description 'Prefab card: Steam Workshop search results' indicate retrieval and display of existing Workshop data without modification. The suffix 'card' suggests UI rendering of query results.
Attacks that exploit this kind of access
Prefab card: Steam Workshop search results. It is categorised as a Read tool in the Steam-MCP MCP Server, which means it retrieves data without modifying state.
Register the Steam- MCP server in PolicyLayer and add a rule for show_workshop_card: 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 Steam-MCP. Nothing to install.
show_workshop_card 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 show_workshop_card 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 show_workshop_card. 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.
show_workshop_card is provided by the Steam- MCP server (sandraschi/steam-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 →