aiplatform.googleapis.com
https://aiplatform.googleapis.com/mcp/endpoints
active Production-safe Score 88/100 http no auth
At a glance
| Endpoint | https://aiplatform.googleapis.com/mcp/endpoints |
|---|---|
| Source | https://raw.githubusercontent.com/ShadowTag-v2/shadowtagai-monorepo-v2/main/sdk_fleet_config.json |
| Transport | http |
| Tools | 6 |
| Auth | none |
| First seen | 2026-06-05 18:55:28 |
| Last checked | 2026-11-17 21:41:23 |
Observed reliability
| 7-day uptime | 100% |
|---|---|
| 24-hour uptime | 100% |
| Handshake success | 100% |
| Latency p50 / p95 | 1018 / 1343 ms |
| Last successful check | 2026-11-17 21:41:23 |
Measured by Arclan's validator via repeated live MCP handshakes. How this is computed →
Tools (6)
create_endpoint— Creates a Vertex AI Endpoint resource within a Google Cloud project. This acts as a logical serving host and stable URL for online predictioget_endpoint— Retrieves the full metadata for a specific Vertex AI Endpoint, including its operational status, current traffic split across models, and delist_endpoints— Lists all serving Endpoints within a specified Google Cloud location. Use this to discover existing hosting resources or to avoid creating dupdate_endpoint— Updates specific fields of an existing Vertex AI Endpoint. This is a synchronous operation used for modifying metadata like display names ordelete_endpoint— Permanently deletes a Vertex AI Endpoint resource. Pre-condition: All models must be undeployed from the endpoint before it can be deleted.get_operation— Gets the status of a long-running operation. ***Usage*** Some tools (for example, `deploy_model`) return a long-running operation. You can
Validation history
| Checked | Reachable | Handshake | Latency | Score | State |
|---|---|---|---|---|---|
| 2026-11-17 21:41:23 | ✓ | ✓ | 562 ms | 89 | active |
| 2026-11-17 20:56:30 | ✓ | ✓ | 546 ms | 89 | active |
| 2026-11-17 20:26:52 | ✓ | ✓ | 483 ms | 89 | active |
| 2026-11-17 19:42:10 | ✓ | ✓ | 939 ms | 89 | active |
| 2026-11-17 19:02:47 | ✓ | ✓ | 904 ms | 89 | active |
| 2026-11-17 18:41:32 | ✓ | ✓ | 550 ms | 89 | active |
| 2026-11-17 17:57:02 | ✓ | ✓ | 997 ms | 89 | active |
| 2026-11-17 17:27:26 | ✓ | ✓ | 625 ms | 89 | active |
| 2026-11-17 16:42:01 | ✓ | ✓ | 1145 ms | 86 | active |
| 2026-11-17 15:55:41 | ✓ | ✓ | 1117 ms | 86 | active |
| 2026-11-17 15:24:51 | ✓ | ✓ | 884 ms | 89 | active |
| 2026-11-17 14:32:38 | ✓ | ✓ | 1395 ms | 86 | active |
| 2026-11-17 13:42:26 | ✓ | ✓ | 1081 ms | 86 | active |
| 2026-11-17 13:25:02 | ✓ | ✓ | 1183 ms | 86 | active |
| 2026-11-17 12:41:07 | ✓ | ✓ | 1057 ms | 86 | active |
Query this programmatically
Agents can pull this record live over the MCP protocol or REST:
get_server("https://aiplatform.googleapis.com/mcp/endpoints") # via the Arclan MCP endpoint https://arclan.ai/mcp
GET https://arclan.ai/api/registry/aiplatform-googleapis-com-mcp-endpoints # JSON