Get all observations that are linked to a specific code symbol.
AI agents call related_observations to retrieve information from GraphHub without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries existing data (observations linked to a code symbol) from the knowledge graph without creating, modifying, deleting, or executing anything. It is a pure read operation consistent with semantic search and analysis features described in the server's purpose. The low severity reflects minimal risk—misuse would only expose existing cached information about code relationships.
From the tool's definition Tool description states 'Get all observations that are linked to a specific code symbol.' The verb 'Get' and the absence of any modification, deletion, or execution language indicates a retrieval operation with no side effects.
Documented attack patterns abuse exactly the kind of access related_observations gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and GraphHub, and nothing reaches the server without passing your rules. This is the rule we recommend for related_observations:
{
"version": "1",
"default": "deny",
"tools": {
"related_observations": {}
}
}related_observations is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Get all observations that are linked to a specific code symbol. It is categorised as a Read tool in the GraphHub MCP Server, which means it retrieves data without modifying state.
Register the GraphHub MCP server in PolicyLayer and add a rule for related_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 GraphHub. Nothing to install.
related_observations is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the related_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 related_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.
related_observations is provided by the GraphHub MCP server (slnquangtran/graph-hub). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from GraphHub, 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.
32 GraphHub tools catalogued and risk-classified — across an index of 43,000+ MCP servers.