AI agents call ci_list_bindings to retrieve information from Run402 without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays CI/CD deployment binding configurations and authorization scopes. While it performs no destructive or write operations, the information it exposes (GitHub Actions subjects, OIDC bindings, route_scopes, deployment permissions) is security-sensitive.
From the tool's definition Tool name 'ci_list_bindings' and description 'List CI/OIDC deploy bindings for a project' indicate retrieval of security configuration data. The phrase 'inspect which GitHub Actions subjects can deploy' confirms this is a query operation with no modification.
Attacks that exploit this kind of access
List CI/OIDC deploy bindings for a project, including route_scopes when delegated. Use this to inspect which GitHub Actions subjects can deploy before editing bindings. It is categorised as a Read tool in the Run402 MCP Server, which means it retrieves data without modifying state.
Register the Run402 MCP server in PolicyLayer and add a rule for ci_list_bindings: 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 Run402. Nothing to install.
ci_list_bindings 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 ci_list_bindings 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 ci_list_bindings. 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.
ci_list_bindings is provided by the Run402 MCP server (kychee-com/run402). 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 →