get_project_observations

THE RISK

Low Risk

Why get_project_observations needs a policy

This tool retrieves stored observations from a project's knowledge graph without modifying, deleting, or executing any operations. It is a pure read operation that queries existing data. The low severity reflects that unauthorized access to observations would be a data exposure risk, but the tool itself performs no destructive, financial, or executable actions.

From the tool's definition Tool name 'get_project_observations' and description 'Get all observations saved in the separate file for a given projectId' indicate data retrieval with no modification or side effects.

Documented attack patterns abuse exactly the kind of access get_project_observations gives an agent:

POLICY

How to control get_project_observations

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 get_project_observations:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "get_project_observations": {}
  }
}

get_project_observations is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

Create a free account and register Xgmem — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

CAP THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Xgmem tools

Destructive delete_entities Delete multiple entities and their associated relations from the project knowledge graph Destructive delete_observations Delete specific observations from entities in the project knowledge graph Destructive delete_relations Delete multiple relations from the project knowledge graph Write add_graph_observations Add new observations to existing entities in the project knowledge graph. Write copy_memory Copy memory entities and their relations from one project to another Write create_entities Create multiple new entities in the project knowledge graph Write create_relations Create multiple new relations between entities in the project knowledge graph Write save_project_observations Save observations for a project to a separate file in the format { projectId, observations

All 14 Xgmem tools →

Read tools on other servers

M-Team MCP Server get_torrent_detail YouTube MCP Server search_channel Android Forensics ADB MCP Server parse_browser_history 0xarchive web3_challenge

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Data exfiltration → How read access becomes an exfiltration channel when chained with untrusted content.
MCP token cost → What connecting this server costs in context-window tokens on every request.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about get_project_observations

What does the get_project_observations tool do? +

Get all observations saved in the separate file for a given projectId. It is categorised as a Read tool in the Xgmem MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on get_project_observations? +

Register the Xgmem MCP server in PolicyLayer and add a rule for get_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.

What risk level is get_project_observations? +

get_project_observations is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit get_project_observations? +

Yes. Add a rate_limit block to the get_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.

How do I block get_project_observations completely? +

Set action: deny in the PolicyLayer policy for get_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.

What MCP server provides get_project_observations? +

get_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.

Enforce policy on every Xgmem tool call.

Start from Xgmem, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →