Router for all servers
AI agents invoke router to trigger actions in MCP Registry. 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.
A router that can dispatch to multiple backend services (PostgreSQL, vector search, LLM completions, etc.) effectively enables arbitrary operations across all those systems. Since it can route to write, destructive, financial, or execute-class operations depending on arguments, it must be classified at the highest applicable severity.
From the tool's definition 'Router for all servers' — routes requests to specialized AI services including embeddings, PDF extraction, reranking, vector search, PostgreSQL, LLM completions, markup, and transcription
Attacks that exploit this kind of access
Router for all servers. It is categorised as a Execute tool in the MCP Registry MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the MCP Registry MCP server in PolicyLayer and add a rule for router: 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 Registry. Nothing to install.
router 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 router 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 router. 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.
router is provided by the MCP Registry MCP server (redmadrobot-rnd/mcp-registry). 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 →