get_market_by_slug
AI agents call get_market_by_slug to retrieve information from Polymarket without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves market data by slug identifier with no capability to modify, delete, or execute operations. It is consistent with the server's read-only design. Even with an empty description, the naming convention and server context strongly indicate it performs a simple data query with no side effects.
From the tool's definition Server is described as providing a 'read-only interface for querying markets' and this tool (get_market_by_slug) falls into the sibling pattern of read-only data retrieval tools (get_book, get_books, get_positions, get_price_history, etc.).
Attacks that exploit this kind of access
get_market_by_slug. It is categorised as a Read tool in the Polymarket MCP Server, which means it retrieves data without modifying state.
Register the Polymarket MCP server in PolicyLayer and add a rule for get_market_by_slug: 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 Polymarket. Nothing to install.
get_market_by_slug 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 get_market_by_slug 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 get_market_by_slug. 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.
get_market_by_slug is provided by the Polymarket MCP server (pr1m8/polymarket-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 →