list_discussions
AI agents call list_discussions to retrieve information from GitHub MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
List operations retrieve and present data without modifying repositories, issues, or any GitHub resources. The absence of a description lowers confidence slightly, but the clear naming convention and context among sibling tools (which include write operations like create_issue and create_pr_review) confirms this is a non-destructive query operation.
From the tool's definition Tool name 'list_discussions' indicates a retrieval operation that queries GitHub discussions. The 'list' prefix is a strong semantic indicator of a read-only action with no side effects.
Attacks that exploit this kind of access
list_discussions. It is categorised as a Read tool in the GitHub MCP Server MCP Server, which means it retrieves data without modifying state.
Register the GitHub MCP Server MCP server in PolicyLayer and add a rule for list_discussions: 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 MCP Server. Nothing to install.
list_discussions 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 list_discussions 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 list_discussions. 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.
list_discussions is provided by the GitHub MCP Server MCP server (software-engineer-mj/github-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 →