inference.sh

ac.inference.shPublished by sh.inference.acv2.0.1Updated Oct 25, 2026

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

VerifiedStreamable HTTPWeb executableDeveloper ToolsAI & ML

Overview

AI-generated overview

A remote MCP endpoint from inference.sh that lets an assistant run AI models, compose agents, stack knowledge and connect tools through one API.

What you can do
Run AI models through a single hosted API, paying per run rather than by subscription or fixed plan, according to the provider's description. Compose agents and stack knowledge so an assistant can build multi-step AI workflows. Connect tools to those agents and models. The manifest lists no individual tools, so the exact operations available are not documented here.
When to use it
Useful when you want an assistant to call a variety of hosted AI models and agent workflows without managing your own model infrastructure or separate provider integrations.
Requirements
A remote streamable HTTP endpoint at api.inference.sh; no local package or runtime is needed. OAuth authentication is required, so you need an inference.sh account and must complete the OAuth sign-in flow. Network access to the endpoint is required.
Before you install
The service is described as pay per run, so using models and agents may incur charges on your account. OAuth grants the server access under your account, so review the scopes requested during sign-in. The manifest lists no tools, so what data is sent to the provider cannot be verified from this listing.

Installation

In SourceWeft

  1. Open inference.sh in the dashboard and add it to a workspace.
  2. Connect the required credentials. They are stored privately and never shown on public pages.
  3. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/ac.inference.sh%2Fmcp/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config. The client completes OAuth sign-in on first connect.

{
  "mcpServers": {
    "inference-sh": {
      "type": "http",
      "url": "https://api.inference.sh/mcp"
    }
  }
}

Tools

0
This server asks you to sign in, so SourceWeft could not read its tools without an account and has not indexed them. What a connected account sees can depend on that account and its permissions.

Version history

1
  1. v2.0.1LatestSep 16, 2026

Score

56% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts

    Publish an icon in the registry entry.

  • Documentation15 pts

    Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.

  • LicenseNot applicable

    A hosted service is used under its provider's terms, so no license is expected here. This check is left out of the percentage.