A single Kalshi market by ticker. Returns yes/no bid+ask and last price (dollars, implied probability), volume, liquidity, open interest, open/close times, and settled result. Read-only (no Kalshi key needed).
AI agents call predict.kalshi-market to retrieve information from Mcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries market data from Kalshi prediction markets and returns information without side effects. Despite the financial domain context (the server settles payments in USDC), this specific tool only retrieves and displays market information—bid/ask spreads, pricing, and settlement data. It does not execute trades, transfer funds, or modify any state.
From the tool's definition Tool description explicitly states 'Read-only (no Kalshi key needed)' and lists retrieval operations: 'Returns yes/no bid+ask and last price (dollars, implied probability), volume, liquidity, open interest, open/close times, and settled result.' No…
Attacks that exploit this kind of access
A single Kalshi market by ticker. Returns yes/no bid+ask and last price (dollars, implied probability), volume, liquidity, open interest, open/close times, and settled result. Read-only (no Kalshi key needed). It is categorised as a Read tool in the Mcp MCP Server, which means it retrieves data without modifying state.
Register the MCP server in PolicyLayer and add a rule for predict.kalshi-market: 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 Mcp. Nothing to install.
predict.kalshi-market 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 predict.kalshi-market 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 predict.kalshi-market. 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.
predict.kalshi-market is provided by the MCP server (@2sio/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 →