AI agents call get_tool_schema to retrieve information from Graph Tool Call without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries tool schema information without modifying, executing, or deleting anything. It is a read-only operation that returns metadata about other tools' input requirements. The blast radius is minimal—misuse would only expose schema information already available through normal tool discovery.
From the tool's definition Tool name 'get_tool_schema' and description 'Get the full inputSchema of a specific tool' indicate retrieval of schema metadata with no side effects.
Documented attack patterns abuse exactly the kind of access get_tool_schema gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Graph Tool Call, and nothing reaches the server without passing your rules. This is the rule we recommend for get_tool_schema:
{
"version": "1",
"default": "deny",
"tools": {
"get_tool_schema": {}
}
}get_tool_schema 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.
Get the full inputSchema of a specific tool. It is categorised as a Read tool in the Graph Tool Call MCP Server, which means it retrieves data without modifying state.
Register the Graph Tool Call MCP server in PolicyLayer and add a rule for get_tool_schema: 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 Graph Tool Call. Nothing to install.
get_tool_schema 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 get_tool_schema 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 get_tool_schema. 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.
get_tool_schema is provided by the Graph Tool Call MCP server (sonaiengine/graph-tool-call). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Graph Tool Call, 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.
7 Graph Tool Call tools catalogued and risk-classified — across an index of 43,000+ MCP servers.