get github repositories from a given username
AI agents call get_repos to retrieve information from HTTP MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves public GitHub repository data for a specified user. It performs a query/read operation with no side effects, no data modification, no code execution, and no destructive actions. The data retrieved is public and the operation is non-destructive and reversible by nature (it is a lookup). Severity is low because the blast radius of misuse is limited to retrieving already-public information.
From the tool's definition Tool description states 'get github repositories from a given username' and server description indicates it 'enables AI assistants to fetch public GitHub repository lists'. The verb 'fetch' and 'get' indicate retrieval without modification.
Attacks that exploit this kind of access
get github repositories from a given username. It is categorised as a Read tool in the HTTP MCP Server MCP Server, which means it retrieves data without modifying state.
Register the HTTP MCP Server MCP server in PolicyLayer and add a rule for get_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 HTTP MCP Server. Nothing to install.
get_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 get_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 get_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.
get_repos is provided by the HTTP MCP Server MCP server (kh-mahmoud/streamable-mcp). 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 →