inference.sh
run any ai model. compose agents, stack knowledge, connect tools. one api, pay per run.
Install
Add this to your client's MCP configuration (Claude Desktop: claude_desktop_config.json; Cursor: .cursor/mcp.json; VS Code and others use the same "mcpServers" shape).
claude mcp add --transport http inference-sh 'https://api.inference.sh/mcp'
{
"mcpServers": {
"inference-sh": {
"type": "http",
"url": "https://api.inference.sh/mcp"
}
}
}
Frequently asked questions
What is inference.sh?
run any ai model. compose agents, stack knowledge, connect tools. one api, pay per run.
How do I install inference.sh?
It runs as a remote server. In Claude Code: claude mcp add --transport http inference-sh 'https://api.inference.sh/mcp'. For other clients, paste the JSON configuration from this page into their MCP settings.
Does inference.sh need an API key?
Its registry entry lists no required key or secret. Some features may still need an account with the service it connects to.
Who maintains inference.sh?
It is published by ac.inference.sh. AI.tn lists it but does not maintain or endorse it.
From the official MCP Registry. Listing is not an endorsement: review a server's code and permissions before giving it access to your data.