Provide feedback on a recall result for adaptive learning. Call this when you know a returned memory was relevant or irrelevant. After enough feedback (20+), the engine learns optimal scoring weights. Args: rid: The memory ID to provide feedback on. feedback: 'relevant' or 'irrelevant'. query_tex...
AI agents use memory_recall_feedback to create or update resources in Yantrikdb — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Yantrikdb environment.
This tool writes feedback data (relevant/irrelevant signals) to adjust scoring weights in a memory retrieval engine. It modifies system behavior over time but does not delete data, execute code, or involve financial transactions. The blast radius is low — misuse would at worst skew memory ranking/scoring weights, which is a reversible learning adjustment.
From the tool's definition Provide feedback on a recall result for adaptive learning... the engine learns optimal scoring weights
Documented attack patterns abuse exactly the kind of access memory_recall_feedback gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Yantrikdb, and nothing reaches the server without passing your rules. This is the rule we recommend for memory_recall_feedback:
{
"version": "1",
"default": "deny",
"tools": {
"memory_recall_feedback": {
"limits": [
{
"counter": "memory_recall_feedback_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}memory_recall_feedback stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Provide feedback on a recall result for adaptive learning. Call this when you know a returned memory was relevant or irrelevant. After enough feedback (20+), the engine learns optimal scoring weights. Args: rid: The memory ID to provide feedback on. feedback: 'relevant' or 'irrelevant'. query_text: The original query text (optional, helps learning). score_at_retrieval: The score the memory received (optional). rank_at_retrieval: The rank position (optional). Returns confirmation of recorded feedback. It is categorised as a Write tool in the Yantrikdb MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Yantrikdb MCP server in PolicyLayer and add a rule for memory_recall_feedback: 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 Yantrikdb. Nothing to install.
memory_recall_feedback is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the memory_recall_feedback 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 memory_recall_feedback. 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.
memory_recall_feedback is provided by the Yantrikdb MCP server (yantrikos/yantrikdb-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 14 Yantrikdb tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
14 Yantrikdb tools catalogued and risk-classified — across an index of 42,500+ MCP servers.