Swift AI MCP Server

by jojapi Your server? Claim it

answering

Swift AI is answering right now. Last checked 14 min ago. It exposes 5 tools.

Swift AI: Access a wide range of AI models⚡, including OpenAI 🤖,DeepSeek 🔍, Claude 🧠, Gemini 🌟, and.

Uptime history 58 days of history · worst day 93%

58 days agonow

100.0%

Uptime 24h

91 of 91 checks

Tools

read from the server

337 ms

Response time

average over 24h

open, no key

Access

streamable-http

What changed 46

Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 12 September 2026. No other catalogue keeps this.

12 Oct 3 tool descriptions were rewritten get_models, post_audio_speech, post_embeddings

10 Oct a tool description was rewritten post_chat_completions

9 Oct a tool description was rewritten post_chat_completions

8 Oct a tool description was rewritten post_chat_completions

7 Oct a tool description was rewritten post_chat_completions

6 Oct a tool description was rewritten post_chat_completions

5 Oct a tool description was rewritten2 times that day post_chat_completions

4 Oct a tool description was rewritten post_chat_completions

3 Oct a tool description was rewritten post_chat_completions

2 Oct a tool description was rewritten post_chat_completions

and 34 more, back to 12 September 2026

Nothing serious here today

Today is the operative word: we check Swift AI every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 14 min ago.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add swift-ai --transport http https://mcp.jojapi.com/swift-ai

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "swift-ai": {
      "url": "https://mcp.jojapi.com/swift-ai"
    }
  }
}

~/.codex/config.toml

[mcp_servers.swift-ai]
url = "https://mcp.jojapi.com/swift-ai"

.cursor/mcp.json

{
  "mcpServers": {
    "swift-ai": {
      "url": "https://mcp.jojapi.com/swift-ai"
    }
  }
}

.vscode/mcp.json

{
  "mcpServers": {
    "swift-ai": {
      "url": "https://mcp.jojapi.com/swift-ai"
    }
  }
}

Available tools 5

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

post

post_audio_speech

Generates audio from the input text. Group: Audio. Billing per call: Credits: metered.

post_chat_completions

Creates a model response for the given chat conversation. Group: Chat. Billing per call: Credits: metered (~3 avg).

post_embeddings

Creates an embedding vector representing the input text. Group: Embeddings. Billing per call: Credits: metered.

post_moderations

Classifies if text is potentially harmful. Group: Moderations. Billing per call: Credits: metered.

models

get_models

Return a list of available models on this API Group: List Models. Billing per call: Credits: metered.

Endpoints

URL	Transport	State	Latency	Checked
https://mcp.jojapi.com/swift-ai	streamable-http	answering	223 ms	14 min ago

Alternatives to Swift AI

same job, measured the same way

Model Council MCP Server

by ivanantigravity-lgtm

Three-model MCP server returning Grok, Gemini, and DeepSeek outputs for Claude.

104 installs/wk local only

Oroute

by netclaus

Auto-route AI requests to 13 models (Claude, GPT, Gemini, Qwen, DeepSeek). 57% cost savings.

51 installs/wk local only

opencode subagents

by sebstaq

Run Claude Code subagents on cheaper opencode models (DeepSeek, opencode Go) with native parity.

946 installs/wk local only

LiteLLM Multi-Model API

by berriai

Access 100+ LLMs with one API: GPT-4, Claude, Gemini, Mistral, and more.

local only

Codeman

by ark0n

Start, prompt and read AI coding agent sessions (Claude Code, Codex, Gemini CLI and more) in Codeman

6 558 installs/wk local only

Deliberation

by antonbabenko

Second opinions in Claude Code and any MCP host from GPT, Gemini, Grok, and 400+ OpenRouter models.

1 842 installs/wk local only

Cool Workflow

by coo1white

Signed, cited, replayable workflows for Claude, Codex, Gemini, DeepSeek, and other agents.

123 installs/wk local only

showagent

by aytzey

Search, resume and convert AI coding sessions (Claude Code, Codex, Gemini, OpenCode, Pi) over MCP.

local only

Swift AI — questions

Answers built from our own checks of this server.

What can Swift AI do?

It exposes 5 tools, read directly from the server on our last check. Among them: get_models, post_audio_speech, post_chat_completions, post_embeddings, post_moderations. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →

Is Swift AI working right now?

We send a real MCP handshake every 15 minutes. Over the last 24 hours 91 of 91 checks got a reply (100.0%), average response time 337 ms. The bar chart above shows every period we have measured.

How do I connect Swift AI?

Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.

Does Swift AI need an API key?

No. Swift AI completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 5 of them are readable on this page. This is what we observed, not what the docs claim.

How fast is Swift AI?

It answers our handshake in 337 ms on average, which is faster than 40% of all working MCP servers we measure. The comparison comes from our own checks across the whole registry, every 15 minutes.