Update an existing concept in the knowledge graph. Call this after completing a task that changed existing features or components. Only include fields that changed.
AI agents use update_concept to create or update resources in MegaMemory — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MegaMemory environment.
This tool creates or modifies data in the knowledge graph reversibly—updates are not permanent deletions and can be corrected. This fits the Write category. Severity is medium because misconfiguration could corrupt architectural records or decision history relied upon by agents, but the effects are limited to metadata about concepts and can be rectified by subsequent updates.
From the tool's definition Tool name 'update_concept' and description states 'Update an existing concept in the knowledge graph.' This explicitly modifies existing data.
Documented attack patterns abuse exactly the kind of access update_concept gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MegaMemory, and nothing reaches the server without passing your rules. This is the rule we recommend for update_concept:
{
"version": "1",
"default": "deny",
"tools": {
"update_concept": {
"limits": [
{
"counter": "update_concept_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}update_concept 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.
Update an existing concept in the knowledge graph. Call this after completing a task that changed existing features or components. Only include fields that changed. It is categorised as a Write tool in the MegaMemory MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MegaMemory MCP server in PolicyLayer and add a rule for update_concept: 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 MegaMemory. Nothing to install.
update_concept 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 update_concept 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 update_concept. 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.
update_concept is provided by the MegaMemory MCP server (0xk3vin/megamemory). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 9 MegaMemory tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
9 MegaMemory tools catalogued and risk-classified — across an index of 42,500+ MCP servers.