// SCAN REPORT

TG_MCP

10 tools. 4 can modify or destroy data without limits.

4 write tools that can modify data. Rate limits recommended.

Last updated: 28 Jun 2026

4 can modify or destroy data

6 read-only

10 tools total

Community server · catalogue entry verified 28/06/2026

How to control TG_MCP ↓

TOOL MAP

What TG_MCP exposes to your agents

Read (6) Write / Execute (4) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous TG_MCP tools

Execute · High run_gsql This tool executes arbitrary GSQL queries whose effects are determined entirely by the query argument provided by the user/agent. Execute · High run_query The tool executes TigerGraph queries with user-supplied parameters, making it Execute rather than Read because the actual effects depend entirely on the query argument passed by the caller. Write · High upsert_edge Upsert operations are Write category because they create or modify data in a reversible manner. Write · Medium upsert_vertex The tool creates or modifies vertex data in the TigerGraph database.

4 of TG_MCP's 10 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control TG_MCP

PolicyLayer is an MCP gateway — it sits between your AI agents and TG_MCP, and nothing reaches the server without passing your rules. These are the rules we recommend:

Rate limit write operations

{
  "upsert_edge": {
    "limits": [
      {
        "counter": "upsert_edge_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "get_installed_query": {
    "limits": [
      {
        "counter": "get_installed_query_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register TG_MCP — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON TG_MCP →

Instant setup, no code required.

FULL CATALOGUE

All 10 TG_MCP tools

EXECUTE 2 tools

Execute run_gsql MCP tool: Run a raw GSQL query. Execute run_query MCP tool: Run a TigerGraph query with parameters.

WRITE 2 tools

Write upsert_edge MCP tool: Insert or update an edge. Write upsert_vertex MCP tool: Insert or update a vertex.

READ 6 tools

Read get_installed_query MCP tool: List all installed GSQL queries. Read get_schema MCP tool: Get TigerGraph schema. Read get_udf MCP tool: Get UDF files. Read get_vertex MCP tool: Retrieve a vertex by type and ID. Read list_all_algorithm MCP tool: List available built-in algorithms. Read show_query MCP tool: Show the content of a GSQL query.

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about TG_MCP

How do I prevent bulk modifications through TG_MCP? +

The TG_MCP server has 2 write tools including upsert_edge, upsert_vertex. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach TG_MCP.

How many tools does the TG_ MCP server expose? +

10 tools across 3 categories: Execute, Read, Write. 6 are read-only. 4 can modify, create, or delete data.

How do I enforce a policy on TG_MCP? +

Register the TG_ MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every TG_MCP tool call.

Deterministic rules across all 10 TG_MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON TG_MCP →

Instant setup, no code required.

10 TG_MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.