작업 내용을 SQLite 데이터베이스에 저장합니다. 할일 저장 시 context(배경정보)와 content(작업내용)가 필요합니다.
AI agents use add_work_memory to create or update resources in Work Memory MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Work Memory MCP Server environment.
The tool creates or modifies data (work memories) in a SQLite database by persisting task information. This is reversible via the sibling tool delete_work_memory, making it a Write operation rather than Destructive.
From the tool's definition Tool description states it saves work content ('작업 내용을 ... 저장합니다') to a SQLite database, storing tasks with context and content fields. 'Saves' and '저장' (save/store) indicate data creation/modification.
Documented attack patterns abuse exactly the kind of access add_work_memory gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Work Memory MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for add_work_memory:
{
"version": "1",
"default": "deny",
"tools": {
"add_work_memory": {
"limits": [
{
"counter": "add_work_memory_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}add_work_memory 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.
작업 내용을 SQLite 데이터베이스에 저장합니다. 할일 저장 시 context(배경정보)와 content(작업내용)가 필요합니다. It is categorised as a Write tool in the Work Memory MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Work Memory MCP Server MCP server in PolicyLayer and add a rule for add_work_memory: 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 Work Memory MCP Server. Nothing to install.
add_work_memory 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 add_work_memory 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 add_work_memory. 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.
add_work_memory is provided by the Work Memory MCP Server MCP server (moontmsai/work-memory-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Work Memory MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
24 Work Memory MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.