Google Cloud documents remote Agent Platform (Vertex AI) Model Context Protocol servers at docs.cloud.google.com/gemini-enterprise-agent-platform/reference/mcp and docs.cloud.google.com/mcp/supported-products. The managed HTTP endpoints include `https://aiplatform.googleapis.com/mcp` plus toolset-specific paths such as `/mcp/generate`, `/mcp/predict`, `/mcp/notebook`, `/mcp/endpoints`, `/mcp/models`, `/mcp/tuning`, `/mcp/evaluation`, and `/mcp/prompts`. Documented toolsets cover generative AI, prediction, Colab Enterprise notebooks, endpoint management, model registry, finetuning, quality evaluation, and prompt management. Authentication uses OAuth 2.0 with IAM per Google Cloud MCP overview; API keys are not accepted on remote Google Cloud MCP servers.
Use cases
- Let agents list models and endpoints before deploying Gemini workloads
- Prototype finetuning and evaluation workflows via MCP toolsets
- Manage Colab Enterprise notebooks from Cursor-connected clients
- Compare remote Vertex AI MCP toolsets against bigquery-mcp for analytics vs ML ops
- Build governed agent apps using Google Cloud MCP IAM and optional Model Armor
Key features
- Claude Desktop
- Cursor
- Gemini CLI
- ChatGPT
Frequently Asked Questions
- Is this the same as BigQuery MCP?
- No—BigQuery MCP uses bigquery.googleapis.com/mcp for SQL analytics; Agent Platform MCP covers models, endpoints, tuning, and evaluation.
- Which endpoint should I use?
- Google Cloud docs list both the root aiplatform.googleapis.com/mcp endpoint and toolset-specific paths like /mcp/generate.
- Can I use an API key?
- Google Cloud remote MCP docs specify OAuth 2.0 with IAM; API keys are not accepted.
Related
Related
3 Indexed items
BigQuery MCP Server
Google Cloud documents a remote BigQuery Model Context Protocol server at docs.cloud.google.com/bigquery/docs/use-bigquery-mcp, enabled when the BigQuery API is enabled. Connect MCP clients to the managed HTTP endpoint `https://bigquery.googleapis.com/mcp` with OAuth 2.0 and IAM (API keys are not accepted). Documented IAM roles include MCP Tool User (`roles/mcp.toolUser`), BigQuery Job User (`roles/bigquery.jobUser`), and BigQuery Data Viewer (`roles/bigquery.dataViewer`). Tools include `execute_sql` and `execute_sql_readonly` per the use guide; `execute_sql_readonly` allows only read-only operations while `execute_sql` is the sole non-read-only tool. Limitations documented: query processing capped at three minutes by default, results limited to 3,000 rows, and Google Drive external tables unsupported for those SQL tools.
Mem0 MCP Server
Mem0 documents a hosted Model Context Protocol server at https://mcp.mem0.ai/mcp that exposes Platform memory tools (`add_memory`, `search_memories`, `get_memories`, `update_memory`, `delete_memory`, `delete_all_memories`, `delete_entities`, `list_entities`, `list_events`, `get_event_status`) to Claude, Claude Code, Codex, Cursor, Windsurf, VS Code, and OpenCode. Setup uses `npx mcp-add` with HTTP transport or manual JSON/TOML client configs; Codex requires `MEM0_API_KEY` as bearer token per docs.mem0.ai/platform/mem0-mcp. The cloud server needs a Mem0 Platform API key from the dashboard and Node.js for the installer—no local vector database required for the hosted path.
Anthropic Remote MCP Connector
Anthropic documents remote Model Context Protocol connectors in Claude Help Center and platform.claude.com docs: users add publicly reachable MCP server URLs so Claude clients (claude.ai, Claude Desktop, Cowork, mobile) connect from Anthropic cloud infrastructure rather than the local machine. Team and Enterprise admins add connectors in Admin settings; individuals enable them under Settings > Connectors. The Messages API MCP connector (beta header anthropic-beta: mcp-client-2025-11-20) accepts mcp_servers entries with type url, name, and https URL, paired with mcp_toolset tools entries; servers must support streamable HTTP/SSE and be internet-accessible to Anthropic IP ranges.