Returns a ranked Markdown list of modules likely affected by changes to a file, based on graph coupling (calls + imports + decision links). No LLM call.
AI agents call predict_impact to retrieve information from Memex without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
predict_impact queries the existing temporal knowledge graph to retrieve impact analysis data. This is a retrieval operation with no side effects—it does not write to the graph, execute external operations, destroy data, or commit financial transactions. The graph itself remains unchanged.
From the tool's definition Tool returns a ranked list of potentially affected modules and is explicitly stated to make 'No LLM call', indicating it reads from the knowledge graph without modifying it.
Documented attack patterns abuse exactly the kind of access predict_impact gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Memex, and nothing reaches the server without passing your rules. This is the rule we recommend for predict_impact:
{
"version": "1",
"default": "deny",
"tools": {
"predict_impact": {}
}
}predict_impact 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.
Returns a ranked Markdown list of modules likely affected by changes to a file, based on graph coupling (calls + imports + decision links). No LLM call. It is categorised as a Read tool in the Memex MCP Server, which means it retrieves data without modifying state.
Register the Memex MCP server in PolicyLayer and add a rule for predict_impact: 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 Memex. Nothing to install.
predict_impact 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 predict_impact 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 predict_impact. 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.
predict_impact is provided by the Memex MCP server (stifler7/memex). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Memex, 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.
13 Memex tools catalogued and risk-classified — across an index of 43,000+ MCP servers.