Surface cross-venue price discrepancies between Polymarket, Kalshi, and Limitless as a discovery feed for price discovery and divergence detection. Default threshold is 0.5% spread, below typical round-trip fees — most results are informational, not tradable arbitrage. Raise min_spread to 0.03+ f...
Risk signalsAccepts freeform code/query input (query)
Part of the Parlay server.
Free to start. No card required.
AI agents call scan_discrepancies to retrieve information from Parlay without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though scan_discrepancies only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
{
"version": "1",
"default": "deny",
"tools": {
"scan_discrepancies": {}
}
}See the full Parlay policy for all 6 tools.
These attack patterns abuse exactly the kind of access scan_discrepancies gives an agent. Each links to the full case and the policy that stops it:
Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.
Surface cross-venue price discrepancies between Polymarket, Kalshi, and Limitless as a discovery feed for price discovery and divergence detection. Default threshold is 0.5% spread, below typical round-trip fees — most results are informational, not tradable arbitrage. Raise min_spread to 0.03+ for after-fee opportunities. The optional query parameter post-filters results by topic keywords on event titles — it does not perform a topic search; for topic-driven retrieval use discover_markets or search_markets. Pairs with missing volume data on at least one venue are flagged 'volume_unconfirmed'. All results are indicative only — not trade recommendations. Real-money venues only. Orderbook depth is not confirmed in Phase 1.. It is categorised as a Read tool in the Parlay MCP Server, which means it retrieves data without modifying state.
Register the Parlay MCP server in PolicyLayer and add a rule for scan_discrepancies: 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 Parlay. Nothing to install.
scan_discrepancies 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 scan_discrepancies 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 scan_discrepancies. 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.
scan_discrepancies is provided by the Parlay MCP server (https://mcp.parlay.run/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 6 Parlay tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.