Scan an MCP tool description/manifest for tool-poisoning and prompt-injection smells; returns a risk score and flagged patterns. Renders the interactive AINumbers tool as a widget; inputs are applied via the AIN Bridge and the tool runs client-side (zero PII, zero network).
AI agents call scan_tool_poisoning to retrieve information from Ainumbers Mcp Apps without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
inputs | object | — | Map of tool input element IDs to values (see manifest input_schema). Applied via AIN Bridge prefill. |
Parameters from the server's own tool schema.
scan_tool_poisoning performs static analysis on tool manifests to detect security smells. This is fundamentally a retrieval and analysis function that examines input and produces a risk assessment report. It does not modify any data, execute code, delete records, or move money. Even though it analyzes security threats, the tool itself is defensive and non-destructive.
From the tool's definition Tool description states it 'scans' and 'returns a risk score and flagged patterns' — a query/analysis operation with no side effects. No creation, modification, deletion, code execution, or financial action is performed.
Attacks that exploit this kind of access
Scan an MCP tool description/manifest for tool-poisoning and prompt-injection smells; returns a risk score and flagged patterns. Renders the interactive AINumbers tool as a widget; inputs are applied via the AIN Bridge and the tool runs client-side (zero PII, zero network). It is categorised as a Read tool in the Ainumbers Mcp Apps MCP Server, which means it retrieves data without modifying state.
scan_tool_poisoning accepts 1 parameter: inputs. The full parameter table on this page comes from the server's own tool schema.
Register the Ainumbers Mcp Apps MCP server in PolicyLayer and add a rule for scan_tool_poisoning: 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 Ainumbers Mcp Apps. Nothing to install.
scan_tool_poisoning 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 scan_tool_poisoning 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 scan_tool_poisoning. 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.
scan_tool_poisoning is provided by the Ainumbers Mcp Apps MCP server (postoaklabs/ainumbers-mcp-apps). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →