Given a high-level user goal, if the goal cannot be fulfilled by a single MCP server,
AI agents call deep_search_planning to retrieve information from 1mcpserver without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs planning and analysis to match user goals against available MCP servers. It retrieves information and reasons about it, but does not create, modify, delete, or execute external operations. The incomplete description ('if the goal cannot be fulfilled...') suggests it returns planning/routing information rather than taking actions.
From the tool's definition Tool name 'deep_search_planning' and description indicating it analyzes user goals and determines whether they can be fulfilled by MCP servers. This is a query/analysis operation with no side effects or data modification.
Documented attack patterns abuse exactly the kind of access deep_search_planning gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and 1mcpserver, and nothing reaches the server without passing your rules. This is the rule we recommend for deep_search_planning:
{
"version": "1",
"default": "deny",
"tools": {
"deep_search_planning": {}
}
}deep_search_planning is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Given a high-level user goal, if the goal cannot be fulfilled by a single MCP server,. It is categorised as a Read tool in the 1mcpserver MCP Server, which means it retrieves data without modifying state.
Register the 1mcpserver MCP server in PolicyLayer and add a rule for deep_search_planning: 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 1mcpserver. Nothing to install.
deep_search_planning is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the deep_search_planning 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 deep_search_planning. 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.
deep_search_planning is provided by the 1mcpserver MCP server (particlefuture/1mcpserver). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 7 1mcpserver tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
7 1mcpserver tools catalogued and risk-classified — across an index of 42,500+ MCP servers.