Correct an existing memory with updated information. The original memory is tombstoned and a new corrected version is created, preserving the history. Entity relationships are transferred to the new memory. Args: rid: The memory ID to correct. new_text: The corrected text content. new_importance:...
AI agents use memory_correct 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 modifies existing memory data by creating a corrected version and tombstoning the original. While the original is tombstoned (soft-deleted), history is preserved, making this reversible in principle — closer to Write than Destructive. The blast radius is medium since an AI agent could corrupt memory records by providing incorrect corrections.
From the tool's definition Correct an existing memory with updated information... The original memory is tombstoned and a new corrected version is created, preserving the history.
Documented attack patterns abuse exactly the kind of access memory_correct 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_correct:
{
"version": "1",
"default": "deny",
"tools": {
"memory_correct": {
"limits": [
{
"counter": "memory_correct_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}memory_correct 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.
Correct an existing memory with updated information. The original memory is tombstoned and a new corrected version is created, preserving the history. Entity relationships are transferred to the new memory. Args: rid: The memory ID to correct. new_text: The corrected text content. new_importance: Optional new importance score (0.0 to 1.0). new_valence: Optional new emotional valence (-1.0 to 1.0). correction_note: Optional note explaining why the correction was made. Returns the original and corrected memory IDs. 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_correct: 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_correct 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_correct 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_correct. 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_correct 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.