Call a specific tool from a specific server. TIP: Use find-tools first to discover the tool and get the correct serverName and toolName
AI agents invoke call-tool to trigger actions in MCP Hub MCP 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 is a meta-execution tool that can invoke any tool on any connected MCP server. Since it can call tools of any category (including Destructive or Financial), its blast radius is critical. The actual effect depends on what tool is called, but the capability to trigger arbitrary operations across all managed servers makes this the highest-risk classification.
From the tool's definition "Call a specific tool from a specific server" — this tool executes arbitrary tools on connected MCP servers, with effects entirely dependent on which tool is invoked.
Documented attack patterns abuse exactly the kind of access call-tool gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP Hub MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for call-tool:
{
"version": "1",
"default": "deny",
"tools": {
"call-tool": {
"limits": [
{
"counter": "call-tool_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}call-tool stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Call a specific tool from a specific server. TIP: Use find-tools first to discover the tool and get the correct serverName and toolName. It is categorised as a Execute tool in the MCP Hub MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the MCP Hub MCP Server MCP server in PolicyLayer and add a rule for call-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 MCP Hub MCP Server. Nothing to install.
call-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-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-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-tool is provided by the MCP Hub MCP Server MCP server (warpdev/mcp-hub-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 7 MCP Hub MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
7 MCP Hub MCP Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.