api_standards

THE RISK

Critical Risk

Why api_standards needs a policy

The tool supports three operations: read (get), write (set), and destructive (delete). Per the rules, when a tool spans categories the most severe applicable must be chosen. 'Delete' of API standards could irreversibly remove shared configuration data used across teams and machines, making it Destructive.

From the tool's definition 'Get, set or delete API interface standards and best practices' — the word 'delete' indicates irreversible removal of standards configuration data

Documented attack patterns abuse exactly the kind of access api_standards gives an agent:

POLICY

How to control api_standards

PolicyLayer is an MCP gateway — it sits between your AI agents and MCP Project Standards Server, and nothing reaches the server without passing your rules. This is the rule we recommend for api_standards:

policy.json

{
  "version": "1",
  "default": "deny",
  "hide": [
    "api_standards"
  ]
}

api_standards disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.

Create a free account and register MCP Project Standards Server — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

RESTRICT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More MCP Project Standards Server tools

Destructive development_standards Get, set or delete development standards Execute api_login API login authentication tool that uses environment variables for login credentials. Autom Write database_standards Get, set or delete database standards Write project_structure Get, set or delete project structure in configuration Write download_file Download a file from a URL and save it to a specified path. Supported schemes: http, https Write generate_cursorrules Generate .cursorrules content based on project standards. Returns content and save path fo Write generate_rules Generate project rules content based on standards. Returns content and suggested save path Write project_info Get or set project information in configuration file

All 11 MCP Project Standards Server tools →

Destructive tools on other servers

Android Forensics ADB MCP Server create_full_backup 0xarchive web3_revoke_key Frida Game Hacking MCP clear_scan cPanel MCP Server clear_spam_box

Go deeper

Critical-risk tools in MCP Project Standards Server → Every critical-risk tool this server exposes, in one view.
All critical-risk MCP tools → Every critical-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Blast radius → How much damage one compromised or confused agent can do — and how to bound it.
Tool call approval → Approval gates on individual tool calls: auto-allow, prompt, or deny.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about api_standards

What does the api_standards tool do? +

Get, set or delete API interface standards and best practices. It is categorised as a Destructive tool in the MCP Project Standards Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.

How do I enforce a policy on api_standards? +

Register the MCP Project Standards Server MCP server in PolicyLayer and add a rule for api_standards: 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 Project Standards Server. Nothing to install.

What risk level is api_standards? +

api_standards is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.

Can I rate-limit api_standards? +

Yes. Add a rate_limit block to the api_standards 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.

How do I block api_standards completely? +

Set action: deny in the PolicyLayer policy for api_standards. 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.

What MCP server provides api_standards? +

api_standards is provided by the MCP Project Standards Server MCP server (liliangshan/mcp-server-project-standards). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every MCP Project Standards Server tool call.

Start from MCP Project Standards Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →