Get user info from GitHub, via Octokit
AI agents call userInfoOctokit to retrieve information from Puch AI MCP Starter without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries public or authenticated user information from GitHub without modifying, executing code, deleting, or performing financial operations. The 'Get' verb and informational nature (user info) clearly indicate a Read category. Severity is low because GitHub user information retrieval has minimal blast radius and does not expose sensitive systems to misuse.
From the tool's definition Tool description states 'Get user info from GitHub', which is a retrieval operation with no side effects. Octokit is GitHub's official API client library used for read-only queries.
Attacks that exploit this kind of access
Get user info from GitHub, via Octokit. It is categorised as a Read tool in the Puch AI MCP Starter MCP Server, which means it retrieves data without modifying state.
Register the Puch AI MCP Starter MCP server in PolicyLayer and add a rule for userInfoOctokit: 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 Puch AI MCP Starter. Nothing to install.
userInfoOctokit 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 userInfoOctokit 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 userInfoOctokit. 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.
userInfoOctokit is provided by the Puch AI MCP Starter MCP server (somnath-chattaraj/mcp-server). 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 →