getMcpServerTool

THE RISK

Low Risk

Why getMcpServerTool needs a policy

This tool retrieves and returns information about MCP server tools—their schemas and metadata—without modifying, executing, or deleting anything. It is a straightforward data retrieval function with no side effects, making it a Read category risk.

From the tool's definition Tool name 'getMcpServerTool' and description 'Get full MCP server tool details (including input and output schemas)' indicate retrieval of metadata.

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

POLICY

How to control getMcpServerTool

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

policy.json

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

getMcpServerTool is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

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

CAP THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More mcpGraph tools

Destructive deleteGraphTool Delete a tool from the mcpGraph Execute runGraphTool Run an exported tool from the mcpGraph. Can specify existing tool name or run a tool defin Execute testJSONata Test a JSONata expression with context Execute testJSONLogic Test a JSON Logic expression with context Execute testMcpTool Test an MCP tool call directly. Evaluates JSONata expressions in args if context is provid Write addGraphTool Add a new tool to the mcpGraph Write updateGraphTool Update an existing tool in the mcpGraph Read getGraphServer Get full details of the mcpGraph server metadata

All 13 mcpGraph tools →

Read tools on other servers

M-Team MCP Server get_torrent_detail YouTube MCP Server search_channel Android Forensics ADB MCP Server parse_browser_history 0xarchive web3_challenge

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Data exfiltration → How read access becomes an exfiltration channel when chained with untrusted content.
MCP token cost → What connecting this server costs in context-window tokens on every request.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about getMcpServerTool

What does the getMcpServerTool tool do? +

Get full MCP server tool details (including input and output schemas). It is categorised as a Read tool in the mcpGraph MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on getMcpServerTool? +

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

What risk level is getMcpServerTool? +

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

Can I rate-limit getMcpServerTool? +

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

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

getMcpServerTool is provided by the mcpGraph MCP server (teamsparkai/mcpgraph). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every mcpGraph tool call.

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

CHECK YOUR STACK →