Persist a piece of text as a raw memory under ~/projects/thoughts/dream-memories/agent/YYYY/MM/DD/<source>-<hash12>.md and incrementally reindex it. Use this to record agent observations, decisions, or context worth recalling in a future session. Tier defaults to
AI agents use knowledge_remember to create or update resources in Ralph Hero — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Ralph Hero environment.
The tool writes a new file to disk and updates an index, which is a reversible write operation. It creates persistent memory entries but does not execute code or delete data. Misuse could pollute the memory store with false observations or decisions that influence future agent sessions, hence medium severity.
From the tool's definition Persist a piece of text as a raw memory under ~/projects/thoughts/dream-memories/agent/YYYY/MM/DD/<source>-<hash12>.md and incrementally reindex it
Attacks that exploit this kind of access
Persist a piece of text as a raw memory under ~/projects/thoughts/dream-memories/agent/YYYY/MM/DD/<source>-<hash12>.md and incrementally reindex it. Use this to record agent observations, decisions, or context worth recalling in a future session. Tier defaults to. It is categorised as a Write tool in the Ralph Hero MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Ralph Hero MCP server in PolicyLayer and add a rule for knowledge_remember: 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 Ralph Hero. Nothing to install.
knowledge_remember 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 knowledge_remember 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 knowledge_remember. 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.
knowledge_remember is provided by the Ralph Hero MCP server (ralph-hero-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →