pwned-passwords-range
Look up breached-password hash suffixes for a 5-character SHA-1 prefix using k-anonymity.
This record as markdown: /tools/io-github-derekslinz-meta-data-mcp/pwned-passwords-range.md
What pwned-passwords-range does on Meta Data Mcp
AI agents call pwned-passwords-range to retrieve information from Meta Data Mcp without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why pwned-passwords-range is rated Low
This tool performs a simple data retrieval against public breach databases. While the data concerns compromised passwords, the tool itself only reads/queries; it does not execute code, modify data, delete records, or move money. The security concern is informational rather than operational — an AI agent using this tool to check if passwords are breached poses minimal direct risk.
From the tool's definition Tool description states 'Look up breached-password hash suffixes' — a query operation that retrieves data from an open API (Have I Been Pwned) without modifying, executing code, or deleting anything. The k-anonymity method is a read-only lookup mechanism.
Attacks that exploit this kind of access
The rule that runs pwned-passwords-range safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Meta Data Mcp, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For pwned-passwords-range, this is the rule to start with:
pwned-passwords-range 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 Meta Data Mcp, apply this rule, and every pwned-passwords-range call is checked against it from then on.
Questions about pwned-passwords-range
Look up breached-password hash suffixes for a 5-character SHA-1 prefix using k-anonymity. It is categorised as a Read tool in the Meta Data Mcp MCP Server, which means it retrieves data without modifying state.
Register the Meta Data MCP server in PolicyLayer and add a rule for pwned-passwords-range: 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 Meta Data Mcp. Nothing to install.
pwned-passwords-range 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 pwned-passwords-range 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 pwned-passwords-range. 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.
pwned-passwords-range is provided by the Meta Data MCP server (pypi:meta-data-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Meta Data, and thousands of servers like it.
This server
Across the catalogue