Search prior decisions and reflections by query text.
AI agents call search_state to retrieve information from Decision State MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a search/query operation to retrieve existing decision state and reflections without creating, modifying, or deleting any data. It is purely informational and read-only in nature, making it the lowest risk category.
From the tool's definition Tool name is 'search_state' and description states it searches prior decisions and reflections by query text, indicating retrieval-only functionality with no modification or side effects.
Attacks that exploit this kind of access
Search prior decisions and reflections by query text. It is categorised as a Read tool in the Decision State MCP MCP Server, which means it retrieves data without modifying state.
Register the Decision State MCP server in PolicyLayer and add a rule for search_state: 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 Decision State MCP. Nothing to install.
search_state 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 search_state 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 search_state. 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.
search_state is provided by the Decision State MCP server (koolercat/mcp-state). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
search_state is one line of Decision State's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →