Import graph from DOT, CSV, GraphML, or JSON. Merges into existing graph.
AI agents use import_graph to create or update resources in Mcp Graph Engine — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Graph Engine environment.
This tool creates or modifies the graph by importing and merging external graph data into the existing structure. This is a Write operation because it changes the graph state in a reversible manner. The severity is medium because importing malicious graph structures could introduce problematic relationships or cycles, but the operation itself is reversible (data can be removed).
From the tool's definition Tool performs "Import graph" that "Merges into existing graph", which modifies the graph structure by adding/combining data from external sources.
Documented attack patterns abuse exactly the kind of access import_graph 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 import_graph:
{
"version": "1",
"default": "deny",
"tools": {
"import_graph": {
"limits": [
{
"counter": "import_graph_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
} import_graph 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.
Import graph from DOT, CSV, GraphML, or JSON. Merges into existing graph. It is categorised as a Write tool in the Mcp Graph Engine MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mcp Graph Engine MCP server in PolicyLayer and add a rule for import_graph: 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.
import_graph 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 import_graph 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 import_graph. 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.
import_graph 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.