AI agents use upsert_vertex to create or update resources in TG_MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your TG_MCP environment.
The tool creates or modifies vertex data in the TigerGraph database. This is a Write operation because it performs insertion or update (reversible changes), not deletion. Severity is medium because unauthorized vertex modifications could corrupt data integrity and affect downstream queries, but the scope is limited to single vertices rather than bulk destructive operations.
From the tool's definition Tool description states 'Insert or update a vertex' — explicit write operations on database entities. TigerGraph vertices are core data structures; modification affects stored state reversibly.
Attacks that exploit this kind of access
MCP tool: Insert or update a vertex. It is categorised as a Write tool in the TG_MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the TG_ MCP server in PolicyLayer and add a rule for upsert_vertex: 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 TG_MCP. Nothing to install.
upsert_vertex 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 upsert_vertex 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 upsert_vertex. 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.
upsert_vertex is provided by the TG_ MCP server (muzain187/tg_mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →