AI Wave vs SandBase CLI
A side-by-side look at the AI Wave and SandBase CLI MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose AI Wave for aggregators work as a local process; choose SandBase CLI for aggregators over a hosted endpoint. You can also run both side by side in one mcpServers block.
Which MCP server should you choose?
Choose AI Wave when
- You need dedicated capabilities in the Aggregators domain.
- You prefer a local stdio subprocess transport.
- You have the keys it needs:
AIWAVE_API_KEY. - You want tools like
list_model_changes, get_model, search_models.
Choose SandBase CLI when
- You need dedicated capabilities in the Aggregators domain.
- You prefer a remote HTTP/SSE transport.
- Its auth model fits you: other.
- You want tools like
sandbase_discover, sandbase_inspect, sandbase_run.
Feature & specification comparison
Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Aggregators | Aggregators |
| Quality signal | 52/100 · Good | 61/100 · Good |
| Install command | Confirmed | Confirmed |
| Transport | Local subprocess (stdio) | Remote HTTP/SSE |
| Auth | Not declared | other |
| Pricing | Not declared | Free |
| Required env vars | AIWAVE_API_KEY | None listed |
| Verified owner | Community listing | Community listing |
| GitHub stars | 0 | 186 |
| Directory activity | 0 views 0 installs 0 upvotes | 11 views 0 installs 0 upvotes |
| Tools | 3 | 7 |
| Full listing | View AI Wave | View SandBase CLI |
Tools & capabilities
AI Wave tools 3
list_model_changesWhat changed since I last checked? Poll with `since`, feed back `latest`.get_modelPrice, context and catalog status for one model (OpenRouter or Hugging Face id).search_modelsWhich models fit this budget and context, ordered by current attention?
SandBase CLI tools 7
sandbase_discoverSearch all 2,000+ available AI models and APIs — freesandbase_inspectGet input schema, current price, and a ready-to-run template — freesandbase_runExecute a model or API endpoint — free for data APIs, paid for modelssandbase_run_getPoll status/result of an async run (video gen, etc.) — freesandbase_runsList your recent runs with their cost — freesandbase_accountCheck account balance — freesandbase_run_cancelCancel an Agent Service run — free
Ready-to-paste client configs
Paste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.
AI Wave
{
"mcpServers": {
"ai-wave": {
"command": "npx",
"args": [
"-y",
"@elopstudio/ai-wave-mcp"
],
"env": {
"AIWAVE_API_KEY": "YOUR_AIWAVE_API_KEY_HERE"
}
}
}
}
SandBase CLI
{
"mcpServers": {
"sandbase-cli": {
"url": "https://tensorblock.co/mcp/servers/github-sandbaseai-cli-c4e113db"
}
}
}
Frequently asked questions
AI Wave is categorized under Aggregators and uses a local stdio subprocess. SandBase CLI belongs to Aggregators and uses a remote HTTP/SSE transport. Pick AI Wave for aggregators work and SandBase CLI for aggregators.
Copy the mcpServers block from the config section on this page into your client's config (for example claude_desktop_config.json or ~/.cursor/mcp.json), then fully restart the client.
AI Wave has no declared pricing — check the project's own site. SandBase CLI is listed as free. Auth: other. If a server needs environment variables such as API keys, define them under the env key in your client's MCP config.
Yes. MCP clients support multiple servers: add ai-wave and sandbase-cli as separate keys in the same mcpServers object, and your assistant will call tools from either one.
On AllMCPs, AI Wave has a quality signal of 52/100 (Good) with 0 views, 0 installs and 0 GitHub stars. SandBase CLI has 61/100 (Good) with 11 views, 0 installs and 186 GitHub stars.