Keyword search across ALL custom data entries (values, categories, and keys) using SQLite FTS. Optionally narrow results to a single category with category_filter. Use when you have specific keywords to find in custom data. For exact category+key lookup without search, use get_custom_data. For gl...
AI agents call search_custom_data_value_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 tool retrieves and queries data without side effects. The FTS (full-text search) mechanism is read-only—it searches existing entries and returns ranked results. There is no mention of modifying, deleting, or executing operations. The optional category_filter parameter narrows the query scope but does not change the fundamental read-only nature.
From the tool's definition Tool description states it performs "Keyword search" and "search" across custom data entries. Returns results in array format. No create, update, delete, or execute operations are performed.
Documented attack patterns abuse exactly the kind of access search_custom_data_value_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_custom_data_value_fts:
{
"version": "1",
"default": "deny",
"tools": {
"search_custom_data_value_fts": {}
}
}search_custom_data_value_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 ALL custom data entries (values, categories, and keys) using SQLite FTS. Optionally narrow results to a single category with category_filter. Use when you have specific keywords to find in custom data. For exact category+key lookup without search, use get_custom_data. For glossary-only search, use search_project_glossary_fts. For conceptual search across all entity types, use semantic_search_engrams. Returns: [{category, key, value, ...}] 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_custom_data_value_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_custom_data_value_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_custom_data_value_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_custom_data_value_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_custom_data_value_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.