This record as markdown: /tools/io-github-dave-london-github/logs.md
What logs does on Github
AI agents call logs to retrieve information from Github without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why logs is rated Low
This tool retrieves and returns log data without creating, modifying, deleting, or executing any operations. It is a passive data retrieval function with no side effects, fitting the Read category. Severity is low because log retrieval has minimal blast radius—it may expose sensitive information in logs but does not directly modify systems or execute code.
From the tool's definition Tool name 'logs' and description 'Retrieves container logs as structured line arrays' indicate a read-only operation that fetches existing data without modification.
Attacks that exploit this kind of access
The rule that runs logs safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Github, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For logs, this is the rule to start with:
logs 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 Github, apply this rule, and every logs call is checked against it from then on.
Questions about logs
Retrieves container logs as structured line arrays. It is categorised as a Read tool in the Github MCP Server, which means it retrieves data without modifying state.
Register the Github MCP server in PolicyLayer and add a rule for logs: 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 Github. Nothing to install.
logs 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 logs 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 logs. 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.
logs is provided by the Github MCP server (@paretools/github). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Github, and thousands of servers like it.
This server
Across the catalogue