AI agents call hound_repos to retrieve information from MCP-Hound without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only retrieves and enumerates repository metadata without any capability to modify, execute, or delete data. It has no side effects beyond information disclosure. The blast radius of misuse is minimal—an attacker gains awareness of available repositories but cannot access their contents, execute code, or modify data through this tool alone. Classified as Read with low severity.
From the tool's definition Tool description explicitly states "List all repositories indexed by Hound code search. Returns repository names and URLs." The verb "List" and the read-only nature of returning repository metadata with no modification capability.
Attacks that exploit this kind of access
List all repositories indexed by Hound code search. Returns repository names and URLs. It is categorised as a Read tool in the MCP-Hound MCP Server, which means it retrieves data without modifying state.
Register the MCP-Hound MCP server in PolicyLayer and add a rule for hound_repos: 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-Hound. Nothing to install.
hound_repos 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 hound_repos 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 hound_repos. 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.
hound_repos is provided by the MCP-Hound MCP server (jmagly/mcp-hound). 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 →