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.
Use cases
- Expose an HTTPS MCP server to Claude without building a local stdio bridge
- Let Enterprise admins pre-approve connectors before users authenticate individually
- Call remote MCP tools from the Messages API using mcp_servers and mcp_toolset blocks
- Integrate third-party SaaS MCP endpoints listed in the Connectors Directory
- Pair Claude Code agents with governed remote tools reachable from Anthropic infrastructure
Key features
- Claude Desktop
- Claude Code
- Claude.ai
- Cowork
- Claude API
Frequently Asked Questions
- Can I use a localhost MCP server?
- Anthropic docs state Claude connects from its cloud to public internet URLs; private VPN or localhost servers will not work even if reachable on your laptop.
- Who can add connectors on Team plans?
- Help Center notes only Owners add connectors org-wide; users then connect individually so Claude respects their credentials.
- Which transports are supported on the API?
- Platform docs list streamable HTTP and SSE for remote servers; stdio-only servers cannot be connected directly via the API connector.
Related
Related
3 Indexed items
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.
Vertex AI Platform MCP Server
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.
ClickHouse Cloud Remote MCP Server
ClickHouse documents a fully managed remote Model Context Protocol server for ClickHouse Cloud at clickhouse.com/docs/cloud/features/ai-ml/remote-mcp. Connect MCP clients to the HTTP endpoint `https://mcp.clickhouse.cloud/mcp` with OAuth 2.0 (browser sign-in with ClickHouse Cloud credentials; no separate API key required per docs). Agents can list databases and tables, inspect schemas, and run scoped read-only SELECT queries; the remote server also exposes richer ClickHouse Cloud integration such as service management, backup monitoring, ClickPipe visibility, and billing data per ClickHouse docs. Enable per service in the Cloud console (Connect → MCP). For self-hosted ClickHouse, ClickHouse maintains the separate open-source mcp-clickhouse project—distinct from this Cloud remote MCP.