Scans the project directory (package.json, config) to automatically detect the
AI agents call analyze_project_and_recommend to retrieve information from Font MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool scans and analyzes project configuration files to provide recommendations. This is a non-destructive, informational operation with no side effects—it retrieves and processes data from the project structure without modifying or executing anything. The blast radius of misuse is minimal since scanning config files cannot harm the system or data.
From the tool's definition Tool name 'analyze_project_and_recommend' and description 'Scans the project directory (package.json, config) to automatically detect' indicate read-only operations on project files.
Documented attack patterns abuse exactly the kind of access analyze_project_and_recommend gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Font MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for analyze_project_and_recommend:
{
"version": "1",
"default": "deny",
"tools": {
"analyze_project_and_recommend": {}
}
}analyze_project_and_recommend 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.
Scans the project directory (package.json, config) to automatically detect the. It is categorised as a Read tool in the Font MCP MCP Server, which means it retrieves data without modifying state.
Register the Font MCP server in PolicyLayer and add a rule for analyze_project_and_recommend: 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 Font MCP. Nothing to install.
analyze_project_and_recommend 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 analyze_project_and_recommend 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 analyze_project_and_recommend. 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.
analyze_project_and_recommend is provided by the Font MCP server (microck/font-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Font MCP, 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 Font MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.