Add new observations to existing entities in the project knowledge graph.
AI agents use add_graph_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 adds observations (creates new data) but does not delete, overwrite, or execute arbitrary code. It is reversible through deletion tools (delete_observations). The risk is medium because an agent could spam irrelevant or false observations into the graph, degrading data quality and consuming storage, but the impact is limited to the local knowledge store with no external side effects or financial…
From the tool's definition Tool description states 'Add new observations to existing entities' — this creates or appends new data to the knowledge graph without deleting or overwriting existing records.
Documented attack patterns abuse exactly the kind of access add_graph_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 add_graph_observations:
{
"version": "1",
"default": "deny",
"tools": {
"add_graph_observations": {
"limits": [
{
"counter": "add_graph_observations_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}add_graph_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.
Add new observations to existing entities in the project knowledge graph. 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 add_graph_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.
add_graph_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 add_graph_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 add_graph_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.
add_graph_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.