get_repository
AI agents call get_repository to retrieve information from Mcp Read Only Argocd without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves repository information from Argo CD without modifying data. It follows the read-only pattern of its server and sibling tools. No side effects or data modifications are implied. Low severity due to limited blast radius of querying repository metadata in a read-only context.
From the tool's definition Tool name 'get_repository' on a server explicitly described as 'read-only access to Argo CD instances' with sibling tools that are all read operations (get_*, list_*).
Attacks that exploit this kind of access
get_repository. It is categorised as a Read tool in the Mcp Read Only Argocd MCP Server, which means it retrieves data without modifying state.
Register the Mcp Read Only Argocd MCP server in PolicyLayer and add a rule for get_repository: 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 Mcp Read Only Argocd. Nothing to install.
get_repository 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 get_repository 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 get_repository. 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.
get_repository is provided by the Mcp Read Only Argocd MCP server (lukleh/mcp-read-only-argocd). 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 →