Prediction market intelligence. Submit any yes/no question and get back a structured bull case, bear case, and implied probability from live web search. Powered by Perplexity sonar-reasoning-pro. Cost: $0.25 per call.
AI agents call sharpsignal_predict to retrieve information from Swarmrails MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is fundamentally a Read operation—it queries external data sources (live web search via Perplexity) and returns structured analysis without side effects. However, severity is medium rather than low because: (1) the tool costs $0.25 per call, creating financial exposure if an AI agent makes many unsupervised calls; (2) prediction market data could influence downstream financial decisions by users; (3) the tool…
From the tool's definition Tool retrieves prediction market intelligence and structured analysis (bull case, bear case, implied probability) from web search results. The description uses query verbs: 'Submit...question and get back,' indicating data retrieval.
Attacks that exploit this kind of access
Prediction market intelligence. Submit any yes/no question and get back a structured bull case, bear case, and implied probability from live web search. Powered by Perplexity sonar-reasoning-pro. Cost: $0.25 per call. It is categorised as a Read tool in the Swarmrails MCP MCP Server, which means it retrieves data without modifying state.
Register the Swarmrails MCP server in PolicyLayer and add a rule for sharpsignal_predict: 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 Swarmrails MCP. Nothing to install.
sharpsignal_predict 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 sharpsignal_predict 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 sharpsignal_predict. 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.
sharpsignal_predict is provided by the Swarmrails MCP server (wizerai1111/swarmrails-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 →