Call a tool on a registered MCP server.
AI agents invoke call_server_tool to trigger actions in SuperMCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool acts as a meta-executor: it can invoke any tool on any registered MCP server. The blast radius is critical because the actual effect depends entirely on which server and tool are targeted — it could trigger Read, Write, Destructive, Financial, or Execute operations on any downstream server.
From the tool's definition 'Call a tool on a registered MCP server' — executes arbitrary tools on connected MCP servers through a unified orchestration interface
Attacks that exploit this kind of access
Call a tool on a registered MCP server. It is categorised as a Execute tool in the SuperMCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the SuperMCP Server MCP server in PolicyLayer and add a rule for call_server_tool: 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 SuperMCP Server. Nothing to install.
call_server_tool is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the call_server_tool 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 call_server_tool. 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.
call_server_tool is provided by the SuperMCP Server MCP server (yakupatahanov/supermcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →