Set the default project for this session. Tools use this unless overridden.
AI agents use memory_set_project to create or update resources in Rekal — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Rekal environment.
This tool creates or modifies configuration state (the active project context) reversibly—a user or agent can change the project again or reset it. It is not a Read operation (no mere retrieval), not Execute (no arbitrary code/external ops), not Destructive (reversible), and not Financial. Write is the correct fit.
From the tool's definition 'Set the default project for this session' modifies session state/configuration in the rekal memory system; the tool writes/updates a stored preference that affects downstream behavior.
Documented attack patterns abuse exactly the kind of access memory_set_project gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Rekal, and nothing reaches the server without passing your rules. This is the rule we recommend for memory_set_project:
{
"version": "1",
"default": "deny",
"tools": {
"memory_set_project": {
"limits": [
{
"counter": "memory_set_project_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}memory_set_project 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.
Set the default project for this session. Tools use this unless overridden. It is categorised as a Write tool in the Rekal MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Rekal MCP server in PolicyLayer and add a rule for memory_set_project: 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 Rekal. Nothing to install.
memory_set_project 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 memory_set_project 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 memory_set_project. 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.
memory_set_project is provided by the Rekal MCP server (janbjorge/rekal). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Rekal, 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.
21 Rekal tools catalogued and risk-classified — across an index of 43,000+ MCP servers.