List all exported tools from the mcpGraph (name and description)
AI agents call listGraphTools 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 tool retrieves information about exported tools in a declarative graph orchestration system. It has no side effects, cannot execute code or external operations, and does not modify or delete data. The only action is querying and returning a list of tool metadata (names and descriptions).
From the tool's definition Tool name 'listGraphTools' and description 'List all exported tools from the mcpGraph' indicate a read operation that retrieves/queries data about available tools without modifying, executing, or deleting anything.
Documented attack patterns abuse exactly the kind of access listGraphTools 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 listGraphTools:
{
"version": "1",
"default": "deny",
"tools": {
"listGraphTools": {}
}
}listGraphTools 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 exported tools from the mcpGraph (name and description). 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 listGraphTools: 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.
listGraphTools 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 listGraphTools 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 listGraphTools. 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.
listGraphTools 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.