# inference.sh MCP server

run any ai model. compose agents, stack knowledge, connect tools. one api, pay per run.

## Links
- Registry page: https://www.getdrio.com/mcp/ac-inference-sh-mcp

## Install
- Endpoint: https://api.inference.sh/mcp
- Auth: Not captured

## Setup notes
- Remote endpoint: https://api.inference.sh/mcp

## Tools
- app_get (Get App Details) - Get detailed app info including input/output schemas and version history Endpoint: https://api.inference.sh/mcp
- app_list (List Apps) - Search and filter available apps on inference.sh Endpoint: https://api.inference.sh/mcp
- app_run (Run App) - Run an app on inference.sh. Creates a task that executes the app with the given input. Endpoint: https://api.inference.sh/mcp
- knowledge_create (Create Knowledge Entry) - Create a new knowledge entry (concept, observation, preference, reference, etc.) Endpoint: https://api.inference.sh/mcp
- knowledge_delete (Delete Knowledge Entry) - Delete a knowledge entry by ID Endpoint: https://api.inference.sh/mcp
- knowledge_get (Get Knowledge Entry) - Get detailed information about a knowledge entry by namespace/name or ID Endpoint: https://api.inference.sh/mcp
- knowledge_list (List Knowledge) - List your knowledge entries, optionally filtered by type Endpoint: https://api.inference.sh/mcp
- knowledge_search (Search Knowledge) - Search your knowledge entries by query Endpoint: https://api.inference.sh/mcp
- mcp_connect (Connect to MCP Server) - Initiate a connection to an MCP server. For OAuth servers, returns an authorization URL to open in a browser. Endpoint: https://api.inference.sh/mcp
- mcp_disconnect (Disconnect from MCP Server) - Remove connection to an MCP server Endpoint: https://api.inference.sh/mcp
- mcp_get (Get MCP Server Details) - Get details about an MCP server including connection status Endpoint: https://api.inference.sh/mcp
- mcp_list (List MCP Servers) - Browse available MCP servers that can be connected to Endpoint: https://api.inference.sh/mcp
- mcp_run (Call MCP Tool) - Call a tool on a connected MCP server. The server must be connected first via mcp_connect. Endpoint: https://api.inference.sh/mcp
- mcp_search (Search MCP Servers) - Search available MCP servers by query Endpoint: https://api.inference.sh/mcp
- mcp_tools (List MCP Server Tools) - List available tools on a connected MCP server, or get details for a specific tool Endpoint: https://api.inference.sh/mcp
- skill_files (List Skill Files) - List supplementary files for a skill (references, scripts, etc.) Endpoint: https://api.inference.sh/mcp
- skill_search (Search Skill Store) - Search the public skill store Endpoint: https://api.inference.sh/mcp
- skill_store (Browse Skill Store) - Browse approved skills in the public skill store Endpoint: https://api.inference.sh/mcp
- skill_upload (Upload Skill) - Create or update a skill with SKILL.md content and optional supporting files Endpoint: https://api.inference.sh/mcp
- skill_use (Use Skill) - Fetch a skill's assembled SKILL.md content. Tries the inference.sh store first, falls back to GitHub. Returns the full skill content for the agent to consume. Endpoint: https://api.inference.sh/mcp
- skill_view (View Skill File) - View a specific supplementary file from a skill's manifest Endpoint: https://api.inference.sh/mcp
- task_cancel (Cancel Task) - Cancel a running or queued task Endpoint: https://api.inference.sh/mcp
- task_get (Get Task) - Get status and output of a task Endpoint: https://api.inference.sh/mcp
- task_list (List Tasks) - List your tasks on inference.sh Endpoint: https://api.inference.sh/mcp
- task_logs (Get Task Logs) - Get execution logs for a task Endpoint: https://api.inference.sh/mcp

## Resources
Not captured

## Prompts
Not captured

## Metadata
- Owner: ac.inference.sh
- Version: 2.0.1
- Runtime: Streamable Http
- Transports: HTTP
- License: Not captured
- Language: Not captured
- Stars: Not captured
- Updated: Jul 27, 2026
- Source: https://registry.modelcontextprotocol.io