# SandBase (remote · api.sandbase.ai)

Connect MCP clients to 2,000+ AI models without managing provider API keys.

- Trust score: 75/100 (medium)
- Change this week: +4
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- remote · `api.sandbase.ai`: 75/100 (this document), [markdown](https://verifymcp.io/servers/sandbaseai-cli/v1-mcp-2.md), [page](https://verifymcp.io/servers/sandbaseai-cli/v1-mcp-2)
- npm · `@sandbaseai/cli`: 45/100, [markdown](https://verifymcp.io/servers/sandbaseai-cli/sandbaseai-cli.md), [page](https://verifymcp.io/servers/sandbaseai-cli/sandbaseai-cli)

## Channel facts

- Endpoint: `https://api.sandbase.ai/v1/mcp`
- Transports: `streamable-http`
- Auth: `required (not validated)`
- Version: `0.3.10`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-21.

- **Endpoint Security**: 83/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation is enforced on tool calls, but the challenge carries no valid RFC 9728 metadata, so a client cannot discover where to get a token.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 62/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 1263 tokens (~180/item across 7 items; 7 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 33/100
  - Stability observed for 10 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 91/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 72% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.
  - An AI judge read all 8 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 60/100
  - Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28.

## Install

### How do I install the SandBase MCP server?

SandBase is a hosted endpoint at https://api.sandbase.ai/v1/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http sandbaseai-cli 'https://api.sandbase.ai/v1/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "sandbaseai-cli": {
      "url": "https://api.sandbase.ai/v1/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "sandbaseai-cli": {
      "type": "http",
      "url": "https://api.sandbase.ai/v1/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.sandbaseai-cli]
url = "https://api.sandbase.ai/v1/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "sandbaseai-cli": {
      "type": "remote",
      "url": "https://api.sandbase.ai/v1/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add sandbaseai-cli --url 'https://api.sandbase.ai/v1/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  sandbaseai-cli:
    url: "https://api.sandbase.ai/v1/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "sandbaseai-cli": {
      "Transport": "http",
      "Url": "https://api.sandbase.ai/v1/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add sandbaseai-cli -t streamable-http -u 'https://api.sandbase.ai/v1/mcp'
```

### Other

```json
{
  "mcpServers": {
    "sandbaseai-cli": {
      "type": "http",
      "url": "https://api.sandbase.ai/v1/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-21 (score 75, +1)

No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-19 (score 74, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-17 (score 73, +1)

No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-15 (score 72, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-13 (score 71, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-12 (score 70, 0)

- [functional improvement] Stability: unverified → 0.03

### 2026-11-11 (score 70)

First indexed and scored.

## MCP tools (7)

### `sandbase_run_cancel` (~49 tokens)

Cancel Service Run

Request cancellation of an Agent Service run; inspect its status afterward.

Input parameters:

- `idempotency_key` (string, required)
- `run_id` (string, required)
- `service_id` (string, required)

### `sandbase_discover` (~231 tokens)

Discover

Find a model, API, or Agent Service for the task. Call this proactively before writing a scraper, before a generic web fetch for structured data, before telling the user something is inaccessible, and whenever you need image/video/music/speech generation, social media data, search results, web scraping, product/company/people data, embeddings, or a specific third-party model. Supports keyword search (q), type filtering (llm/api/multimodal/embedding/service), and vendor filtering. Discovery is not billed; start here.

Input parameters:

- `limit` (integer): Maximum results to return (default 20, max 100).
- `q` (string): Short description of what you need (e.g. 'twitter posts', 'text to video', 'gpt-4o', '小红书'). At most 4096 UTF-8 bytes and 64 tokens after normalization.
- `type` (string): Filter by capability type; use service to discover Agent Services.
- `vendor` (string): Filter by vendor slug (e.g. 'openai', 'twitter', 'anthropic').

### `sandbase_inspect` (~79 tokens)

Inspect

Inspect a model, API, or Agent Service: input schema, available pricing, and an execution template. Service names are svc_ IDs. Always inspect before running.

Input parameters:

- `name` (string, required): Model name (e.g. 'openai/gpt-4o'), tool name, or Agent Service ID (svc_...) from discover results.

### `sandbase_run` (~148 tokens)

Run

Execute a model, API, or Agent Service. Sync models return the result directly; async models (image/video/audio jobs) return status running with a run_id — poll sandbase_run_get for the output. Services require arguments.idempotency_key and optionally input; reuse the same key and input on retries. Service acceptance is not completion: poll sandbase_run_get with service_id and run_id. Omit the MCP task parameter for Services.

Input parameters:

- `arguments` (object, required): Input matching the inspected schema. For Services: {idempotency_key: string, input?: string}.
- `name` (string, required): Model name, tool name, or Agent Service ID (svc_...) to execute.

### `sandbase_run_get` (~111 tokens)

Get Run Result

Get async run status and results. For Agent Services supply both service_id and run_id; succeeded, failed, and cancelled are terminal. Session items are paginated: use cursor for subsequent pages; items_available=false means retry output retrieval. Model runs use completed or failed.

Input parameters:

- `cursor` (string): Session items continuation cursor.
- `limit` (integer)
- `run_id` (string, required): The run ID returned by sandbase_run.
- `service_id` (string): Required for Agent Service runs.

### `sandbase_runs` (~96 tokens)

List Runs

List recent model/API calls, or supply service_id to list runs of an Agent Service.

Input parameters:

- `limit` (integer): Number of recent runs to return (default 10, max 50).
- `model` (string): Filter by model name (e.g. 'openai/gpt-4o').
- `offset` (integer)
- `service_id` (string): List runs of this Agent Service instead of model predictions.

### `sandbase_account` (~27 tokens)

Account

Check your SandBase account balance. This call is not billed. Use before expensive operations.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/sandbaseai-cli/v1-mcp-2#diagnostics

## Score history

- 2026-11-21: 75
- 2026-11-20: 74
- 2026-11-19: 74
- 2026-11-18: 73
- 2026-11-17: 73
- 2026-11-16: 72
- 2026-11-15: 72
- 2026-11-14: 71
- 2026-11-13: 71
- 2026-11-12: 70
- 2026-11-11: 70

## Common questions

### What is the SandBase MCP server?

SandBase is an MCP server listed in the public MCP registry as io.github.sandbaseai/cli. Connect MCP clients to 2,000+ AI models without managing provider API keys. This page covers its hosted endpoint (https://api.sandbase.ai/v1/mcp).

### Is the SandBase MCP server safe to use?

SandBase scores 75 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the SandBase MCP server expose?

SandBase exposes 7 tools: sandbase_run_cancel, sandbase_discover, sandbase_inspect, sandbase_run, sandbase_run_get, and 2 more. Their descriptions and schemas cost roughly 741 tokens of context every time the server is loaded.

### Does the SandBase MCP server require authentication?

Yes. SandBase asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.

### Is the SandBase MCP server still maintained?

SandBase is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What did VerifyMCP test on the SandBase MCP server?

VerifyMCP ran 13 checks on SandBase, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- Remote endpoint: https://api.sandbase.ai/v1/mcp
- Authorisation metadata: https://api.sandbase.ai/.well-known/oauth-protected-resource/v1/mcp
- Repository: https://github.com/sandbaseai/cli
- Changelog RSS feed: https://verifymcp.io/servers/sandbaseai-cli/v1-mcp-2.xml
- Changelog JSON feed: https://verifymcp.io/servers/sandbaseai-cli/v1-mcp-2/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/sandbaseai-cli/v1-mcp-2.json
- HTML version of this page: https://verifymcp.io/servers/sandbaseai-cli/v1-mcp-2
