Developer · Remote MCP server
SandBase
Connect MCP clients to 2,000+ AI models without managing provider API keys.
What the MCP Registry states
The entry as published to the official MCP Registry (read 2026-10-04), latest version.
- Registry name
io.github.sandbaseai/cli- Version
- 0.1.17
- Status
- Active
- Category
- developer
- Transport
- Streamable HTTP
- Published
- 2026-08-27
- Updated
- 2026-08-27
- Publisher
- sandbaseai (GitHub) · 2 servers with pages here
- Namespace
- Namespace verified by the MCP Registry via GitHub (github.com/sandbaseai) · how
- Repository
- github.com/sandbaseai/cli
- Source
- Registry API entry
Remote endpoints
| Transport | URL | Headers declared |
|---|---|---|
| Streamable HTTP | https://sandbase.ai/v1/mcp | Authorization (required, secret) |
Live check
This directory connected to each remote endpoint and asked for its list of tools. The check connects and lists tools only; it doesn't run tools, sign in or test security.
- Reachable
- Yes (HTTP 401)
- Handshake
- Not completed: sign-in required
- Sign-in required
- Yes - HTTP 401
- Checked on
- 2026-10-05
How to connect SandBase
SandBase is a remote MCP server: there is nothing to install. Its endpoint is https://sandbase.ai/v1/mcp, served over Streamable HTTP. In an assistant that accepts remote MCP servers (often under a setting named connectors, integrations or tools), add a new server and give it this URL; in a client configured by file, add it as a remote (HTTP) server with the same URL.
The registry entry declares an HTTP header for the connection: Authorization (required, secret). A secret header usually carries an API key or token issued by the service; clients that accept custom headers set it with the server's URL.
Derived from the registry entry; the live check above only shows whether the endpoint answered. What the server does, and on what terms, is set by its publisher; check its repository or website before giving it access to your accounts or files. How to add an MCP server to an assistant · Before you connect
More from sandbaseai (GitHub)
| Server | Runs |
|---|---|
| SandBase HarnessStdio MCP bridge for SandBase Harness agents, sessions, turns, artifacts, and cancellation. | Local · stdio |
More developer servers
| Server | Runs |
|---|---|
| Salesforce Metadata MCPThe only Salesforce MCP with Agentforce, OmniStudio & DevOps Center tools - 228 total. | Local · stdio |
| SAME - Stateless Agent Memory EnginePersistent memory for AI coding agents. Local-first SQLite + vector search. 17 MCP tools. | Local · stdio |
| Samotpravil MCPMCP server for Samotpravil API - docs, typed tools, Python SDK parity, safety flags. | Local · stdio |
| SampuliFormat-true synthetic test data for 90 countries - IBANs, SWIFT/BIC, IDs, cards, all certified. | Remote & Local · HTTP, stdioLive check: ✓ handshake |
| Sandbox as a ServiceGive an agent a real Linux VM: run commands, move files, expose a preview URL, destroy it. | Local · stdio |
| Sandbox Env MCPPersistent Docker/SSH sandbox for AI agents: shell exec, file ops, audit log. | Local · stdio |
| SandboxAPIExecute code in 8 languages (Python, JS, TS, Go, Java, C++, C, Bash) in gVisor sandboxes. | Remote · HTTPLive check: sign-in required |
| Sandboxd Code RunHosted one-shot code execution: send a snippet plus optional files, get stdout, stderr, exit... | Remote · HTTPLive check: ✓ handshake |