Registers a persistent background monitor for a specific Polymarket market that fires alerts when user-defined conditions are met. Supported conditions (at least one required): oddsThresholdPct (fire when implied probability crosses a target level), oddsMovePct (fire when probability moves by a d...
Risk signalsHigh parameter count (11 properties)
Part of the Syenite server.
Free to start. No card required.
AI agents may call prediction.watch to permanently remove or destroy resources in Syenite. Without a policy, an autonomous agent could delete critical data in a loop with no way to undo the damage. PolicyLayer blocks destructive tools by default and requires explicit human approval before enabling them.
Without a policy, an AI agent could call prediction.watch in a loop, permanently destroying resources in Syenite. There is no undo for destructive operations. PolicyLayer blocks this tool by default and only allows it when a human explicitly approves the action.
Destructive tools permanently remove data. Block by default. Only enable with explicit approval workflows.
{
"version": "1",
"default": "deny",
"hide": [
"prediction.watch"
]
} See the full Syenite policy for all 46 tools.
These attack patterns abuse exactly the kind of access prediction.watch gives an agent. Each links to the full case and the policy that stops it:
Other destructive tools across the catalogue. The same approach applies to each: deny by default, or require human approval.
Registers a persistent background monitor for a specific Polymarket market that fires alerts when user-defined conditions are met. Supported conditions (at least one required): oddsThresholdPct (fire when implied probability crosses a target level), oddsMovePct (fire when probability moves by a delta% within a windowMinutes window), liquidityDropPct (fire when liquidity falls by a percentage from baseline), resolutionApproachingHours (fire when the market closes within N hours), and volumeSpikeMultiple (fire when 24h volume exceeds baseline by a multiple). Requires either slug or conditionId to identify the market (both returned by prediction.trending and prediction.search); optionally provide webhookUrl to receive POST payloads when conditions fire. Triggered alerts flow through alerts.check; use the returned watch ID with alerts.remove to stop monitoring. Does not place or cancel orders.. It is categorised as a Destructive tool in the Syenite MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Syenite MCP server in PolicyLayer and add a rule for prediction.watch: 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 Syenite. Nothing to install.
prediction.watch is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the prediction.watch 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 prediction.watch. 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.
prediction.watch is provided by the Syenite MCP server (@syenite/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 46 Syenite 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.