AI agents use update_project to create or update resources in Forgetful — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Forgetful environment.
The tool updates project data, which is a reversible modification typical of Write operations. No description provided, but the naming pattern and sibling tools (create_project, delete_project) strongly suggest this performs non-destructive data modification. Severity is medium because unintended project updates could corrupt or disrupt stored knowledge, but the action is reversible via subsequent updates.
From the tool's definition Tool name 'update_project' indicates modification of project data. Server context shows this is a knowledge base storage system with tools for creating and deleting projects, suggesting 'update_project' modifies existing project records reversibly.
Documented attack patterns abuse exactly the kind of access update_project gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Forgetful, and nothing reaches the server without passing your rules. This is the rule we recommend for update_project:
{
"version": "1",
"default": "deny",
"tools": {
"update_project": {
"limits": [
{
"counter": "update_project_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}update_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.
update_project. It is categorised as a Write tool in the Forgetful MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Forgetful MCP server in PolicyLayer and add a rule for update_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 Forgetful. Nothing to install.
update_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 update_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 update_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.
update_project is provided by the Forgetful MCP server (scottrbk/forgetful). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 59 Forgetful tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
59 Forgetful tools catalogued and risk-classified — across an index of 42,500+ MCP servers.