Calls a registered tool by its full namespaced name.
AI agents invoke call_tool to trigger actions in UTCP-MCP Bridge. 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 executes arbitrary registered tools by name, meaning its actual effect depends entirely on which tool is invoked. Since it can call any registered tool in the UTCP registry — which could include destructive, financial, or execute-category tools — it represents a critical execution surface. The blast radius is maximum because it's a universal dispatcher for all registered tools.
From the tool's definition "Calls a registered tool by its full namespaced name"
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 UTCP-MCP Bridge, 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.
Calls a registered tool by its full namespaced name. It is categorised as a Execute tool in the UTCP-MCP Bridge MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the UTCP-MCP Bridge 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 UTCP-MCP Bridge. 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 UTCP-MCP Bridge MCP server (universal-tool-calling-protocol/utcp-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 UTCP-MCP Bridge tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
7 UTCP-MCP Bridge tools catalogued and risk-classified — across an index of 42,500+ MCP servers.