get_capabilities

SERVERBusinys SOURCE@businys/mcp-server

Low RISK CLASS

Category Read

Parameters 00 required

Recommended Allowedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/app-businys-mcp-server/get-capabilities.md

WHAT IT DOES

What get_capabilities does on Businys

AI agents call get_capabilities to retrieve information from Businys without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

RISK

Why get_capabilities is rated Low

This is a capability discovery/introspection tool that queries metadata about available tools and permissions. It retrieves information only and cannot modify, execute, delete, or commit financial actions. The blast radius of misuse is minimal—an agent might learn about available tools earlier than intended, but this poses no direct risk. Classified as Read.

From the tool's definition Tool name 'get_capabilities' and description 'Discover which tools, practices, and resources are available' and 'Returns the list of allowed tools' indicate pure data retrieval with no modifications, side effects, or operations.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs get_capabilities safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Businys, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For get_capabilities, this is the rule to start with:

get_capabilities Allowed

get_capabilities is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "get_capabilities": {}
  }
}

ALLOW ONLY THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Businys, apply this rule, and every get_capabilities call is checked against it from then on.

FAQ

Questions about get_capabilities

What does the get_capabilities tool do? +

Discover which tools, practices, and resources are available for the current API key. Returns the list of allowed tools grouped by category, active practices, and permission scopes. Use this before calling unfamiliar tools to avoid 403 errors. It is categorised as a Read tool in the Businys MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on get_capabilities? +

Register the Businys MCP server in PolicyLayer and add a rule for get_capabilities: 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 Businys. Nothing to install.

What risk level is get_capabilities? +

get_capabilities is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit get_capabilities? +

Yes. Add a rate_limit block to the get_capabilities 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 get_capabilities completely? +

Set action: deny in the PolicyLayer policy for get_capabilities. 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 get_capabilities? +

get_capabilities is provided by the Businys MCP server (@businys/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Businys, and thousands of servers like it.

This server

All 248 Businys tools →

Across the catalogue

get_cocktail_by_category on Cocktails RAG MCP Server →get_torrent_detail on M-Team MCP Server →aiva_get_affiliate on AIVA MCP Server →get-chuck-categories on Jokes MCP Server → The MCP Attack Database →

Guides

Roll out MCP under one policy →Data exfiltration →MCP token cost →