Get information about a repository and whether it's already cloned locally.
AI agents call get_repository_info to retrieve information from Codeglance without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries repository metadata and local state information. It has no capability to modify, execute, delete, or financially impact any system. It is a straightforward read operation that gathers information for analysis purposes.
From the tool's definition Tool name 'get_repository_info' and description 'Get information about a repository' indicate retrieval of data with no modification or side effects. The mention of checking 'whether it's already cloned locally' is a status query operation.
Attacks that exploit this kind of access
Get information about a repository and whether it's already cloned locally. It is categorised as a Read tool in the Codeglance MCP Server, which means it retrieves data without modifying state.
Register the Codeglance MCP server in PolicyLayer and add a rule for get_repository_info: 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 Codeglance. Nothing to install.
get_repository_info 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_info 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_info. 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_info is provided by the Codeglance MCP server (lucidopus/codeglance-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 →