Score the codebase against architectural rules and patterns
AI agents call get_architectural_score to retrieve information from DependencyMCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries architectural metrics and scoring information about a codebase. It performs no side effects, creates no changes, executes no code, and makes no destructive or financial operations. It is a pure analytical/read operation that inspects code structure and returns scoring results, consistent with the Read category for tools that retrieve or query data without side effects.
From the tool's definition The tool 'get_architectural_score' performs analysis and scoring of a codebase against rules and patterns.
Documented attack patterns abuse exactly the kind of access get_architectural_score gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and DependencyMCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for get_architectural_score:
{
"version": "1",
"default": "deny",
"tools": {
"get_architectural_score": {}
}
}get_architectural_score is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Score the codebase against architectural rules and patterns. It is categorised as a Read tool in the DependencyMCP Server MCP Server, which means it retrieves data without modifying state.
Register the DependencyMCP Server MCP server in PolicyLayer and add a rule for get_architectural_score: 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 DependencyMCP Server. Nothing to install.
get_architectural_score 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_architectural_score 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_architectural_score. 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_architectural_score is provided by the DependencyMCP Server MCP server (mkearl/dependency-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from DependencyMCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
4 DependencyMCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.