List all available MCP servers (name, title, instructions, version)
AI agents call listMcpServers to retrieve information from mcpGraph without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a straightforward enumeration of available MCP servers and their metadata. It retrieves information only and cannot modify, delete, or execute anything. The blast radius of misuse is minimal—an adversary gains only visibility into available services, which is typically non-sensitive reconnaissance information. Classified as Read with low severity.
From the tool's definition Tool lists MCP servers and their metadata (name, title, instructions, version) without modification or execution. Description explicitly uses 'List' indicating a retrieval operation with no side effects.
Documented attack patterns abuse exactly the kind of access listMcpServers gives an agent:
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 listMcpServers:
{
"version": "1",
"default": "deny",
"tools": {
"listMcpServers": {}
}
} listMcpServers 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.
List all available MCP servers (name, title, instructions, version). It is categorised as a Read tool in the mcpGraph MCP Server, which means it retrieves data without modifying state.
Register the mcpGraph MCP server in PolicyLayer and add a rule for listMcpServers: 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.
listMcpServers 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 listMcpServers 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 listMcpServers. 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.
listMcpServers 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.
Start from mcpGraph, 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.
13 mcpGraph tools catalogued and risk-classified — across an index of 43,000+ MCP servers.