Inference.sh MCP Server
Run 150+ AI apps — image, video, audio, LLMs, 3D and more. Browse, execute, stream results.
What is the Inference.sh MCP Server?
The Inference.sh MCP server gives AI agents structured, permission-aware access to Inference.sh through the Model Context Protocol. With 0 pre-built actions, agents can read, create, and update Inference.sh data on behalf of authorized users.
Willow ships the Inference.sh MCP server as part of an enterprise control plane. Every call runs behind SSO (Okta, Azure AD), enforces RBAC and least-privilege at runtime, writes to a full audit trail, and integrates with Splunk and Loki for SIEM visibility. Connect from Claude Desktop, Claude Code, Cursor, ChatGPT, VS Code, n8n, or any custom agent. Install once, distribute org-wide, and see exactly how Inference.sh is being used by every AI agent in your stack.
Tools
List Inference.sh data
Create Inference.sh item
Update Inference.sh item
Customize Tools
Edit descriptions, modify arguments, select tools, or add new ones
Edit descriptions
Change arguments
Select tools
Set Up Your Inference.sh MCP Server in Minutes
Add the following configuration to your MCP client. Authentication is handled via OAuth. Compatible with Claude Desktop, Claude Code, Cursor, ChatGPT, VS Code, n8n, and any MCP-compatible agent.
Claude Desktop
{
"mcpServers": {
"willow-ac-inference-sh-mcp": {
"type": "http",
"url": "https://<org>.mcp-s.com/mcp/mcp/ac-inference-sh-mcp"
}
}
}Cursor
{
"mcpServers": {
"willow-ac-inference-sh-mcp": {
"type": "http",
"url": "https://<org>.mcp-s.com/mcp/mcp/ac-inference-sh-mcp"
}
}
}Claude Code
claude mcp add willow-ac-inference-sh-mcp --transport http https://<org>.mcp-s.com/mcp/mcp/ac-inference-sh-mcpn8n
{
"url": "https://<org>.mcp-s.com/mcp/mcp/ac-inference-sh-mcp",
"method": "POST"
}Or click "Install with Willow" above to set up automatically with SSO and RBAC preconfigured.
Enterprise Governance for Inference.sh
Willow adds the layer Inference.sh and every other SaaS doesn't ship out of the box: every call runs behind SSO (Okta, Azure AD), enforces RBAC and least-privilege at runtime, writes to full audit logs, and detects shadow AI usage across your stack. One MCP gateway. Any agent. Every tool.
Inference.sh MCP Server FAQ
What is the Inference.sh MCP server?
The Inference.sh MCP server is a Model Context Protocol implementation that lets AI agents like Claude, Cursor, and ChatGPT read and write Inference.sh data through a standardized interface. Willow hosts and governs this server so enterprises can roll it out without a security review backlog.
How is Willow's Inference.sh MCP server different from the official one?
The official Inference.sh MCP server is scoped to a single user's account and does not include enterprise governance. Willow's version adds SSO, RBAC, audit logging, shadow AI detection, and centralized control over which actions agents can take across the entire org.
Which AI clients work with the Inference.sh MCP server?
Claude Desktop, Claude Code, Cursor, ChatGPT, VS Code with MCP support, n8n, and any custom agent built with OpenAI Agents SDK, LangChain, Vercel AI SDK, or Anthropic SDK.
Is the Inference.sh MCP server secure? How does Willow handle authentication?
Every call runs behind your existing SSO (Okta, Azure AD). Per-user OAuth scopes the agent to exactly what that user can do in Inference.sh, nothing more. No credentials reach the LLM. Every action writes to an audit trail.
Can I limit which Inference.sh actions agents can take?
Yes. Willow lets you scope agents to specific actions, specific projects, or specific environments. Toggle actions on or off in the dashboard, or enforce policy via infrastructure-as-code through GitHub.
How do I detect shadow Inference.sh MCP servers in my org?
Willow's browser extension and discovery service surface unmanaged MCP servers, skills, and AI agents across the org. If a developer installed an unapproved Inference.sh MCP locally, you'll see it.
What does the Inference.sh MCP server cost?
Pricing depends on org size and deployment model (SaaS, dedicated cloud, self-host). See withwillow.ai/pricing or contact sales for a quote.
How do I install the Inference.sh MCP server with Willow?
Install via the Willow Connect Panel in one click, or paste the JSON snippet above into your Claude Desktop, Cursor, or Claude Code config. SSO and RBAC inherit from your existing Willow setup.
Compare Willow MCP Gateway
See how Willow stacks up against other MCP platforms on governance, security, and enterprise readiness.
Related other MCP Servers
Alpic
Alpic MCP server. Governed enterprise integration.
Artidrop
Artidrop MCP server. Governed enterprise integration.
Baselight
Baselight MCP server. Governed enterprise integration.
Bezal — Local Business Intelligence for AI Agents
Bezal — Local Business Intelligence for AI Agents MCP server. Governed enterprise integration.
Your agents are already in the wild.
Give them a Basecamp. Go from AI chaos to AI work, in minutes.