create_memory_from_proposal
Approve a memory proposal and persist it as a normal memory entry.
This record as markdown: /tools/mapi-agent-memory/create-memory-from-proposal.md
What create_memory_from_proposal does on Mapi Agent Memory
AI agents use create_memory_from_proposal to create or update resources in Mapi Agent Memory, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mapi Agent Memory environment.
Why create_memory_from_proposal is rated Medium
This tool creates or modifies data in a reversible manner (memory entries can be reviewed, updated, or removed via other governance mechanisms on this server). While it affects agent behavior by persisting memories, it does not execute arbitrary code, delete data irreversibly, or move money. The 'auditable memory and governance' context suggests the platform provides controls to manage these writes.
From the tool's definition Tool description states 'Approve a memory proposal and persist it as a normal memory entry.' The verb 'persist' indicates data creation/modification. The tool modifies the agent's memory state by converting a proposal into a persistent entry.
Attacks that exploit this kind of access
The rule that runs create_memory_from_proposal safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Mapi Agent Memory, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For create_memory_from_proposal, this is the rule to start with:
create_memory_from_proposal 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.
The button opens the PolicyLayer dashboard: create your workspace, connect Mapi Agent Memory, apply this rule, and every create_memory_from_proposal call is checked against it from then on.
Questions about create_memory_from_proposal
Approve a memory proposal and persist it as a normal memory entry. It is categorised as a Write tool in the Mapi Agent Memory MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mapi Agent Memory MCP server in PolicyLayer and add a rule for create_memory_from_proposal: 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 Mapi Agent Memory. Nothing to install.
create_memory_from_proposal 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 create_memory_from_proposal 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 create_memory_from_proposal. 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.
create_memory_from_proposal is provided by the Mapi Agent Memory MCP server (cabo0m/mapi-agent-memory). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Mapi Agent Memory, and thousands of servers like it.
This server
Across the catalogue