Create a temporary working memory with expiration
AI agents use create_working_memory to create or update resources in AGI MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your AGI MCP Server environment.
This tool creates new data structures (working memory entries) in a mutable store, which is a Write operation. It does not retrieve data (Read), execute arbitrary code (Execute), permanently destroy data (Destructive), or move money (Financial). The temporary, auto-expiring nature prevents this from being Destructive.
From the tool's definition Tool description states it 'Create[s] a temporary working memory' which is a create operation that modifies state by adding new working memory entries.
Documented attack patterns abuse exactly the kind of access create_working_memory gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and AGI MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for create_working_memory:
{
"version": "1",
"default": "deny",
"tools": {
"create_working_memory": {
"limits": [
{
"counter": "create_working_memory_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
} create_working_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.
Create a temporary working memory with expiration. It is categorised as a Write tool in the AGI MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the AGI MCP Server MCP server in PolicyLayer and add a rule for create_working_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 AGI MCP Server. Nothing to install.
create_working_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 create_working_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 create_working_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.
create_working_memory is provided by the AGI MCP Server MCP server (quixiai/agi-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from AGI 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 AGI MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.