Keyword search across decision text (summary, rationale, implementation_details, tags) using SQLite FTS. Use when you have specific keywords to match. For tag-based filtering without keywords, use get_decisions. For conceptual/semantic search, use semantic_search_engrams. Returns: [{id, summary, ...
AI agents call search_decisions_fts to retrieve information from Engrams without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a search/query operation that retrieves and ranks existing decision records based on keyword matching. It has no side effects, cannot modify data, execute code, or trigger external operations. The tool is strictly informational, consistent with the Read category for data retrieval operations.
From the tool's definition Tool performs "Keyword search" across decision text using SQLite FTS and "Returns: [{id, summary, rationale, tags, ...}] ranked by FTS relevance." No modification, deletion, or execution capabilities are described.
Documented attack patterns abuse exactly the kind of access search_decisions_fts gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Engrams, and nothing reaches the server without passing your rules. This is the rule we recommend for search_decisions_fts:
{
"version": "1",
"default": "deny",
"tools": {
"search_decisions_fts": {}
}
}search_decisions_fts 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.
Keyword search across decision text (summary, rationale, implementation_details, tags) using SQLite FTS. Use when you have specific keywords to match. For tag-based filtering without keywords, use get_decisions. For conceptual/semantic search, use semantic_search_engrams. Returns: [{id, summary, rationale, tags, ...}] ranked by FTS relevance. It is categorised as a Read tool in the Engrams MCP Server, which means it retrieves data without modifying state.
Register the Engrams MCP server in PolicyLayer and add a rule for search_decisions_fts: 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 Engrams. Nothing to install.
search_decisions_fts 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_decisions_fts 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_decisions_fts. 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_decisions_fts is provided by the Engrams MCP server (stevebrownlee/engrams). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Engrams, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
42 Engrams tools catalogued and risk-classified — across an index of 43,000+ MCP servers.