ai-toolkit is an MCP server with 5 tools an agent can call, among them chat, classify, embed. It answers at https://api.agishub.com/mcp/ai over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 10 of 10 times since 4 September 2026; the last check, on 17 October 2026, succeeded.
AI tools for agents: chat, summarize, classify, entity extraction, embeddings, transcription. x402
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
chat | Ask a general-purpose LLM a question or give it an instruction, with an optional system prompt. No external API key required. Inputs: prompt, system, max_tokens |
classify | Classify a text into exactly one of the candidate labels you provide (e.g. sentiment, topic, intent). Inputs: text, labels |
embed | Turn text into a numeric embedding vector for semantic search, RAG and similarity. Multilingual. Inputs: text |
extract_entities | Extract named entities from text — people, organizations, locations, dates and miscellaneous — returned as structured JSON. Inputs: text |
summarize | Summarize a block of text into a short abstract, with an optional target length. No external API key required. Inputs: text, max_words |
Every block below points at https://api.agishub.com/mcp/ai. Pick your client and copy.
claude mcp add --transport http ai-toolkit https://api.agishub.com/mcp/ai
{
"mcpServers": {
"ai-toolkit": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://api.agishub.com/mcp/ai"]
}
}
}{
"mcpServers": {
"ai-toolkit": {
"url": "https://api.agishub.com/mcp/ai"
}
}
}{
"servers": {
"ai-toolkit": {
"type": "http",
"url": "https://api.agishub.com/mcp/ai"
}
}
}{
"context_servers": {
"ai-toolkit": {
"url": "https://api.agishub.com/mcp/ai"
}
}
}{
"mcpServers": {
"ai-toolkit": {
"serverUrl": "https://api.agishub.com/mcp/ai"
}
}
}{
"mcpServers": {
"ai-toolkit": {
"url": "https://api.agishub.com/mcp/ai"
}
}
}name: ai-toolkit
version: 0.0.1
schema: v1
mcpServers:
- name: ai-toolkit
type: streamable-http
url: https://api.agishub.com/mcp/ai{
"mcpServers": {
"ai-toolkit": {
"httpUrl": "https://api.agishub.com/mcp/ai"
}
}
}{
"mcpServers": {
"ai-toolkit": {
"type": "http",
"url": "https://api.agishub.com/mcp/ai"
}
}
}{
"mcpServers": {
"ai-toolkit": {
"url": "https://api.agishub.com/mcp/ai"
}
}
}goose://extension?url=https%3A%2F%2Fapi.agishub.com%2Fmcp%2Fai&type=streamable_http&id=ai-toolkit&name=ai-toolkit
It answered our last check on 17 October 2026 in 101 ms. Over 10 checks since 4 September 2026 it answered 10. Status here comes from Neuronto's own probes, not from the publisher.
Yes. It is published by agishub.com and served from api.agishub.com, the vendor's own domain: https://api.agishub.com/mcp/ai.
5, as returned by the server's own tools/list on 10 September 2026: chat, classify, embed, extract_entities, summarize.
It answered our last check on 17 October 2026 in 101 ms. Over 10 checks since 4 September 2026 it answered 10.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://api.agishub.com/mcp/ai. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: com.agishub. Endpoint host: api.agishub.com. ARD identifier: urn:air:com.agishub:mcp:ai-toolkit.
First indexed 31 August 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.