Chama uma ferramenta no servidor MCP externo
AI agents invoke proxy_call_tool to trigger actions in MCP Redirect 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 proxies tool calls to an external MCP server. Since it can invoke arbitrary tools on an external server, its effective risk depends on what tools are available there. The act of calling external tools is at minimum Execute-level, and could be Destructive or Financial depending on the proxied tool.
From the tool's definition 'Chama uma ferramenta no servidor MCP externo' (Calls a tool on the external MCP server)
Attacks that exploit this kind of access
Chama uma ferramenta no servidor MCP externo. It is categorised as a Execute tool in the MCP Redirect Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the MCP Redirect Server MCP server in PolicyLayer and add a rule for proxy_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 Redirect Server. Nothing to install.
proxy_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 proxy_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 proxy_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.
proxy_call_tool is provided by the MCP Redirect Server MCP server (marcos2872/mcp-redirect-server). 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 →