Screen for Post-Earnings Announcement Drift (PEAD) setups.
AI agents call screen_pead to retrieve information from Momentum without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a quantitative screening tool that queries historical data to identify stocks exhibiting PEAD patterns. Screening is a passive analysis function that retrieves and filters existing market data without side effects. No write, execution, destructive, or financial operations occur—the tool merely returns informational results for analyst review.
From the tool's definition Tool name 'screen_pead' and description 'Screen for Post-Earnings Announcement Drift (PEAD) setups' indicate data retrieval and analysis.
Documented attack patterns abuse exactly the kind of access screen_pead gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Momentum, and nothing reaches the server without passing your rules. This is the rule we recommend for screen_pead:
{
"version": "1",
"default": "deny",
"tools": {
"screen_pead": {}
}
}screen_pead is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Screen for Post-Earnings Announcement Drift (PEAD) setups. It is categorised as a Read tool in the Momentum MCP Server, which means it retrieves data without modifying state.
Register the Momentum MCP server in PolicyLayer and add a rule for screen_pead: 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 Momentum. Nothing to install.
screen_pead 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 screen_pead 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 screen_pead. 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.
screen_pead is provided by the Momentum MCP server (mphinance/momentum-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Momentum, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
52 Momentum tools catalogued and risk-classified — across an index of 43,000+ MCP servers.