MCP server registry. Actions: "find_tool" (single-call tool discovery — BM25-ranked search by intent, returns top match with required args, confidence label, and auto-activates server; PREFER THIS for tool discovery), "find_tools" (batch find_tool — pass intents:['intent1','intent2',...] to disco...
Accepts freeform code/query input (query); High parameter count (18 properties)
Part of the Agent Discover MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents may call registry to permanently remove or destroy resources in Agent Discover. Without a policy, an autonomous agent could delete critical data in a loop with no way to undo the damage. Intercept blocks destructive tools by default and requires explicit human approval before enabling them.
Without a policy, an AI agent could call registry in a loop, permanently destroying resources in Agent Discover. There is no undo for destructive operations. Intercept blocks this tool by default and only allows it when a human explicitly approves the action.
Destructive tools permanently remove data. Block by default. Only enable with explicit approval workflows.
tools:
registry:
rules:
- action: deny
reason: "Blocked by default — enable with approval"See the full Agent Discover policy for all 1 tools.
Agents calling destructive-class tools like registry have been implicated in these attack patterns. Read the full case and prevention policy for each:
Other tools in the Destructive risk category across the catalogue. The same policy patterns (deny, require_approval) apply to each.
registry is one of the critical-risk operations in Agent Discover. For the full severity-focused view — only the critical-risk tools with their recommended policies — see the breakdown for this server, or browse all critical-risk tools across every MCP server.
MCP server registry. Actions: "find_tool" (single-call tool discovery — BM25-ranked search by intent, returns top match with required args, confidence label, and auto-activates server; PREFER THIS for tool discovery), "find_tools" (batch find_tool — pass intents:['intent1','intent2',...] to discover N tools in ONE round-trip; use for multi-step tasks), "get_schema" (full input_schema for a tool already returned by find_tool — only needed for fat schemas with optional/polymorphic args), "list" (search local registry by server), "install" (add server from marketplace or manual config), "uninstall" (remove server), "activate" / "deactivate" (start/stop server and expose/hide its tools), "browse" (search official MCP registry), "status" (show active servers and tools), "sync" (re-read AGENT_DISCOVER_SETUP_FILE and ensure listed servers are registered; optional "file" param to override path).. It is categorised as a Destructive tool in the Agent Discover MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Add a rule in your Intercept YAML policy under the tools section for registry. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Agent Discover MCP server.
registry is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the registry rule in your Intercept 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 Intercept policy for registry. 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.
registry is provided by the Agent Discover MCP server (agent-discover). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Open source. One binary. Zero dependencies.
npx -y @policylayer/intercept