Check health of all dependencies in a GitHub repo.
AI agents call tool_check_dependencies to retrieve information from Codelens-MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs dependency auditing and health assessment, which are informational queries. It has no side effects: it does not install, update, delete, or execute code. The action is strictly analytical and retrieves existing repository metadata. The blast radius of misuse is minimal—an AI agent cannot cause damage by checking dependencies, only by gathering information.
From the tool's definition Tool name and description indicate it 'checks health of all dependencies' — a read-only query operation that retrieves and analyzes dependency information from a repository without modifying any data.
Attacks that exploit this kind of access
Check health of all dependencies in a GitHub repo. It is categorised as a Read tool in the Codelens-MCP MCP Server, which means it retrieves data without modifying state.
Register the Codelens- MCP server in PolicyLayer and add a rule for tool_check_dependencies: 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 Codelens-MCP. Nothing to install.
tool_check_dependencies 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 tool_check_dependencies 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 tool_check_dependencies. 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.
tool_check_dependencies is provided by the Codelens- MCP server (yashkashte5/codelens-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 →