Call GitHub REST API with optional ETag cache & pagination.
AI agents invoke github_request to trigger actions in Promethean OS MCP. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool can call any GitHub REST API endpoint, which means it could perform GET (read), POST (write), PATCH (write), or DELETE (destructive) operations depending on the arguments. Since the endpoint and method are determined at call time, the worst-case outcome must govern: a misconfigured or malicious call could delete repositories, force-push branches, or modify org settings.
From the tool's definition 'Call GitHub REST API with optional ETag cache & pagination' — makes arbitrary GitHub REST API calls
Attacks that exploit this kind of access
Call GitHub REST API with optional ETag cache & pagination. It is categorised as a Execute tool in the Promethean OS MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Promethean OS MCP server in PolicyLayer and add a rule for github_request: 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 Promethean OS MCP. Nothing to install.
github_request is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the github_request 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 github_request. 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.
github_request is provided by the Promethean OS MCP server (octave-commons/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 →