Forensic orderbook analysis for one Kalshi market. Detects manipulation-vulnerable patterns: (1) wide spread (>$0.10), (2) shallow depth (<10 contracts), (3) few price levels, (4) single-order dominance (>80% in top level), (5) penny-wall pattern (large bids at ≤$0.005, commonly used to fake dept...
Part of the Predictionguard server.
Free to start. No card required.
AI agents call pg_kalshi_orderbook_analysis to retrieve information from Predictionguard 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 pg_kalshi_orderbook_analysis 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": {
"pg_kalshi_orderbook_analysis": {}
}
}See the full Predictionguard policy for all 41 tools.
These attack patterns abuse exactly the kind of access pg_kalshi_orderbook_analysis 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.
Forensic orderbook analysis for one Kalshi market. Detects manipulation-vulnerable patterns: (1) wide spread (>$0.10), (2) shallow depth (<10 contracts), (3) few price levels, (4) single-order dominance (>80% in top level), (5) penny-wall pattern (large bids at ≤$0.005, commonly used to fake depth). Returns 0-100 score, severity, and full level-by-level data. Kalshi returns bids only — implied asks computed via yes_bid + no_bid = $1 reciprocity.. It is categorised as a Read tool in the Predictionguard MCP Server, which means it retrieves data without modifying state.
Register the Predictionguard MCP server in PolicyLayer and add a rule for pg_kalshi_orderbook_analysis: 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 Predictionguard. Nothing to install.
pg_kalshi_orderbook_analysis 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 pg_kalshi_orderbook_analysis 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 pg_kalshi_orderbook_analysis. 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.
pg_kalshi_orderbook_analysis is provided by the Predictionguard MCP server (https://feedoracle.io/predictionguard/mcp/). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 41 Predictionguard 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.