# inference.sh (remote · api.inference.sh)

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

- Trust score: 63/100 (medium)
- Change this week: +5
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `api.inference.sh`: 63/100 (this document), [markdown](https://verifymcp.io/servers/ac-inference-sh-mcp/api.md), [page](https://verifymcp.io/servers/ac-inference-sh-mcp/api)

## Channel facts

- Endpoint: `https://api.inference.sh/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `2.0.1`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Endpoint Security**: 57/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 25 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 60/100
  - AI-judged instruction clarity (fair).
  - Tool/resource definitions use about 1249 tokens (~49/item across 25 items; 25 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 88/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 65% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### Claude

```bash
claude mcp add --transport http ac-inference-sh-mcp https://api.inference.sh/mcp
```

### Codex

```toml
[mcp_servers.ac-inference-sh-mcp]
url = "https://api.inference.sh/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "ac-inference-sh-mcp": {
      "type": "remote",
      "url": "https://api.inference.sh/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add ac-inference-sh-mcp --url https://api.inference.sh/mcp --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  ac-inference-sh-mcp:
    url: "https://api.inference.sh/mcp"
```

### Other

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

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-03 (score 63, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-08-01 (score 62, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-31 (score 61, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 60, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-28 (score 59, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-27 (score 58, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-26 (score 57)

First indexed and scored.

## MCP tools (25)

### `app_get` (~37 tokens)

Get App Details

Get detailed app info including input/output schemas and version history

Input parameters:

- `app` (string, required): App ref: namespace/name or namespace/name@version

### `app_list` (~50 tokens)

List Apps

Search and filter available apps on inference.sh

Input parameters:

- `category` (string)
- `cursor` (string)
- `limit` (integer)
- `query` (string): Search by name or description

### `app_run` (~79 tokens)

Run App

Run an app on inference.sh. Creates a task that executes the app with the given input.

Input parameters:

- `app` (string, required): App ref: namespace/name or namespace/name@version
- `function` (string): Function name for multi-function apps
- `infrastructure` (string)
- `input` (object, required): App input matching the app's input schema

### `knowledge_create` (~60 tokens)

Create Knowledge Entry

Create a new knowledge entry (concept, observation, preference, reference, etc.)

Input parameters:

- `content` (string, required): Entry content (markdown)
- `description` (string): Short description
- `name` (string, required): Entry name
- `type` (string)

### `knowledge_delete` (~24 tokens)

Delete Knowledge Entry

Delete a knowledge entry by ID

Input parameters:

- `id` (string, required): Entry ID

### `knowledge_get` (~35 tokens)

Get Knowledge Entry

Get detailed information about a knowledge entry by namespace/name or ID

Input parameters:

- `ref` (string, required): Entry ref: namespace/name or ID

### `knowledge_list` (~43 tokens)

List Knowledge

List your knowledge entries, optionally filtered by type

Input parameters:

- `cursor` (string)
- `limit` (integer)
- `type` (string): Filter by knowledge type

### `knowledge_search` (~48 tokens)

Search Knowledge

Search your knowledge entries by query

Input parameters:

- `cursor` (string)
- `limit` (integer)
- `query` (string, required): Search query
- `type` (string): Filter by type

### `mcp_connect` (~41 tokens)

Connect to MCP Server

Initiate a connection to an MCP server. For OAuth servers, returns an authorization URL to open in a browser.

Input parameters:

- `slug` (string, required): Server slug

### `mcp_disconnect` (~25 tokens)

Disconnect from MCP Server

Remove connection to an MCP server

Input parameters:

- `slug` (string, required): Server slug

### `mcp_get` (~28 tokens)

Get MCP Server Details

Get details about an MCP server including connection status

Input parameters:

- `slug` (string, required): Server slug

### `mcp_list` (~54 tokens)

List MCP Servers

Browse available MCP servers that can be connected to

Input parameters:

- `category` (string): Filter by category
- `cursor` (string)
- `featured` (boolean): Show only featured servers
- `limit` (integer)

### `mcp_run` (~58 tokens)

Call MCP Tool

Call a tool on a connected MCP server. The server must be connected first via mcp_connect.

Input parameters:

- `input` (object): Tool input arguments
- `slug` (string, required): slug/tool format (e.g. 'linear/list_issues')

### `mcp_search` (~39 tokens)

Search MCP Servers

Search available MCP servers by query

Input parameters:

- `cursor` (string)
- `limit` (integer)
- `query` (string, required): Search query

### `mcp_tools` (~54 tokens)

List MCP Server Tools

List available tools on a connected MCP server, or get details for a specific tool

Input parameters:

- `slug` (string, required): Server slug (e.g. 'linear') or slug/tool (e.g. 'linear/list_issues')

### `skill_files` (~33 tokens)

List Skill Files

List supplementary files for a skill (references, scripts, etc.)

Input parameters:

- `ref` (string, required): Skill ref: namespace/name

### `skill_search` (~47 tokens)

Search Skill Store

Search the public skill store

Input parameters:

- `category` (string): Filter by category
- `cursor` (string)
- `limit` (integer)
- `query` (string, required): Search query

### `skill_store` (~52 tokens)

Browse Skill Store

Browse approved skills in the public skill store

Input parameters:

- `category` (string): Filter by category
- `cursor` (string)
- `featured` (boolean): Show only featured skills
- `limit` (integer)

### `skill_upload` (~83 tokens)

Upload Skill

Create or update a skill with SKILL.md content and optional supporting files

Input parameters:

- `allowed_tools` (string): Comma-separated list of allowed tools
- `content` (string, required): SKILL.md body content (markdown)
- `description` (string): Short description
- `files` (array): Supporting files (references, scripts)
- `name` (string, required): Skill name

### `skill_use` (~63 tokens)

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.

Input parameters:

- `ref` (string, required): Skill ref: namespace/name, or github.com/user/repo URL

### `skill_view` (~43 tokens)

View Skill File

View a specific supplementary file from a skill's manifest

Input parameters:

- `path` (string, required): File path within the skill
- `ref` (string, required): Skill ref: namespace/name

### `task_cancel` (~39 tokens)

Cancel Task

Cancel a running or queued task

Input parameters:

- `force` (boolean): Force kill immediately instead of graceful shutdown
- `task_id` (string, required): Task ID

### `task_get` (~26 tokens)

Get Task

Get status and output of a task

Input parameters:

- `task_id` (string, required): Task ID

### `task_list` (~36 tokens)

List Tasks

List your tasks on inference.sh

Input parameters:

- `cursor` (string)
- `limit` (integer)
- `status` (string)

### `task_logs` (~33 tokens)

Get Task Logs

Get execution logs for a task

Input parameters:

- `log_type` (string)
- `task_id` (string, required): Task ID

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/ac-inference-sh-mcp/api#diagnostics

## Score history

- 2026-08-03: 63
- 2026-08-02: 62
- 2026-08-01: 62
- 2026-07-31: 61
- 2026-07-30: 60
- 2026-07-29: 59
- 2026-07-28: 59
- 2026-07-27: 58
- 2026-07-26: 57

## Links

- Remote endpoint: https://api.inference.sh/mcp
- Changelog RSS feed: https://verifymcp.io/servers/ac-inference-sh-mcp/api/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/ac-inference-sh-mcp/api/changelog.json
- HTML version of this page: https://verifymcp.io/servers/ac-inference-sh-mcp/api