fraud_detector
Détecteur de fraude — Gapup agent-payable C-suite expertise (RISK). Returns a structured, audited deliverable. Reference case: TechManu SAS — Industriel FR €32M CA, 148 FTE · 30j · 21 anomalies · €487k à risque. Inputs are validated server-side — send the documented case fields.
This record as markdown: /tools/io-github-getgapup-mcp-knowledge/fraud-detector.md
What fraud_detector does on Mcp Knowledge
AI agents call fraud_detector to retrieve information from Mcp Knowledge without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
async | boolean | — | If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client ti |
focus | string | — | |
company | object | Yes | |
analysisPeriodDays | integer | Yes | |
transactionVolumes | object | Yes |
Parameters from the server's own tool schema.
Why fraud_detector is rated Low
The tool appears to analyze and detect fraud, returning a structured audit report with identified anomalies and risk amounts. This is primarily a read/analysis operation — it queries and evaluates provided case data to produce a deliverable. It does not explicitly execute code, modify data, or move money.
From the tool's definition Détecteur de fraude — Returns a structured, audited deliverable. Reference case: 21 anomalies · €487k à risque.
Risk signalsHigh parameter count (14 properties)
Attacks that exploit this kind of access
The rule that runs fraud_detector safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Mcp Knowledge, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For fraud_detector, this is the rule to start with:
fraud_detector is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Mcp Knowledge, apply this rule, and every fraud_detector call is checked against it from then on.
Questions about fraud_detector
Détecteur de fraude — Gapup agent-payable C-suite expertise (RISK). Returns a structured, audited deliverable. Reference case: TechManu SAS — Industriel FR €32M CA, 148 FTE · 30j · 21 anomalies · €487k à risque. Inputs are validated server-side — send the documented case fields. It is categorised as a Read tool in the Mcp Knowledge MCP Server, which means it retrieves data without modifying state.
fraud_detector accepts 5 parameters: async, focus, company, analysisPeriodDays, transactionVolumes. Required: company, analysisPeriodDays, transactionVolumes. The full parameter table on this page comes from the server's own tool schema.
Register the Mcp Knowledge MCP server in PolicyLayer and add a rule for fraud_detector: 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 Mcp Knowledge. Nothing to install.
fraud_detector 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 fraud_detector 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 fraud_detector. 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.
fraud_detector is provided by the Mcp Knowledge MCP server (https://mcp.gapup.io). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Mcp Knowledge, and thousands of servers like it.
This server
Across the catalogue