Save observations for a project to a separate file in the format { projectId, observations: [{ entityName, contents: [...] }] }.
AI agents use save_project_observations to create or update resources in Xgmem — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Xgmem environment.
The tool creates or modifies persisted observations data in a file. This is a reversible write operation—observations can be updated or deleted later (as evidenced by sibling tools like delete_observations). It does not execute arbitrary code, delete data irreversibly, or involve financial operations.
From the tool's definition Tool description states it 'Save observations for a project to a separate file', which indicates creating/persisting structured data to disk storage.
Documented attack patterns abuse exactly the kind of access save_project_observations gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Xgmem, and nothing reaches the server without passing your rules. This is the rule we recommend for save_project_observations:
{
"version": "1",
"default": "deny",
"tools": {
"save_project_observations": {
"limits": [
{
"counter": "save_project_observations_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}save_project_observations 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.
Save observations for a project to a separate file in the format { projectId, observations: [{ entityName, contents: [...] }] }. It is categorised as a Write tool in the Xgmem MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Xgmem MCP server in PolicyLayer and add a rule for save_project_observations: 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 Xgmem. Nothing to install.
save_project_observations 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 save_project_observations 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 save_project_observations. 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.
save_project_observations is provided by the Xgmem MCP server (meetdhanani17/xgmem). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Xgmem, 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.
14 Xgmem tools catalogued and risk-classified — across an index of 43,000+ MCP servers.