Semantic recall of the most relevant stored fragments. Uses SimHash fingerprint distance + multi-dimensional scoring with feedback loop (fragments that previously led to successful outputs are boosted). Args: query: The search query top_k: Number of results to return
AI agents call recall_relevant to retrieve information from Entroly Context Engine without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and searches stored code fragments based on semantic similarity. It is a read-only operation that queries indexed data and returns results without side effects. The feedback loop mentioned only affects internal ranking/boosting of fragments, not external state. No data is modified, deleted, or executed—only retrieved and ranked.
From the tool's definition Tool description indicates 'Semantic recall of the most relevant stored fragments' using 'SimHash fingerprint distance + multi-dimensional scoring'. The function signature shows only retrieval parameters: query and top_k.
Documented attack patterns abuse exactly the kind of access recall_relevant gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Entroly Context Engine, and nothing reaches the server without passing your rules. This is the rule we recommend for recall_relevant:
{
"version": "1",
"default": "deny",
"tools": {
"recall_relevant": {}
}
}recall_relevant 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.
Semantic recall of the most relevant stored fragments. Uses SimHash fingerprint distance + multi-dimensional scoring with feedback loop (fragments that previously led to successful outputs are boosted). Args: query: The search query top_k: Number of results to return. It is categorised as a Read tool in the Entroly Context Engine MCP Server, which means it retrieves data without modifying state.
Register the Entroly Context Engine MCP server in PolicyLayer and add a rule for recall_relevant: 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 Entroly Context Engine. Nothing to install.
recall_relevant 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 recall_relevant 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 recall_relevant. 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.
recall_relevant is provided by the Entroly Context Engine MCP server (juyterman1000/entroly). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Entroly Context Engine, 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.
52 Entroly Context Engine tools catalogued and risk-classified — across an index of 43,000+ MCP servers.