Get complete graph summary: nodes by type, relationships, and insights (hubs, cycles, orphans).
AI agents call dump_context to retrieve information from Mcp Graph Engine without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and summarizes existing graph data without creating, modifying, deleting, or executing operations. It provides insights into graph topology but produces no side effects. The sibling tools include destructive operations (delete_graph) and executable operations (cypher_query), clearly distinguishing this as a read-only analysis function.
From the tool's definition Tool description states it "Get[s] complete graph summary" with analysis of existing graph structure (nodes, relationships, hubs, cycles, orphans). The verb "Get" and absence of modification language indicate read-only retrieval.
Documented attack patterns abuse exactly the kind of access dump_context gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Mcp Graph Engine, and nothing reaches the server without passing your rules. This is the rule we recommend for dump_context:
{
"version": "1",
"default": "deny",
"tools": {
"dump_context": {}
}
}dump_context 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 complete graph summary: nodes by type, relationships, and insights (hubs, cycles, orphans). It is categorised as a Read tool in the Mcp Graph Engine MCP Server, which means it retrieves data without modifying state.
Register the Mcp Graph Engine MCP server in PolicyLayer and add a rule for dump_context: 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 Mcp Graph Engine. Nothing to install.
dump_context 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 dump_context 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 dump_context. 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.
dump_context is provided by the Mcp Graph Engine MCP server (utilitydelta/mcp-graph-engine). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Mcp Graph Engine, 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.
24 Mcp Graph Engine tools catalogued and risk-classified — across an index of 43,000+ MCP servers.