Sofya is a remote MCP server that gives an AI agent 4 tools, among them extract, fetch, research. It answers at https://mcp.sofya.co/mcp 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.
Web search, fetch, extract, and research for AI agents. Markdown output + AI-synthesized answers.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
extract | Fetch a webpage and extract specific information using AI. Use this when you need structured data from a page (e.g. pricing, specs, contact info) rather than the raw content. Costs 10 credits. If the page has no usable text (empty or JavaSc Inputs: url, prompt |
fetch | Fetch one or more URLs and return their content as clean markdown. Use this to read articles, documentation, blog posts, or any page where you need the complete text, not just a snippet from search. Also supports PDF, DOCX, and other docume Inputs: urls, include_raw_html |
research | Perform comprehensive research on a topic. Decomposes your query into sub-queries, searches and reads multiple sources in parallel, then synthesizes a structured report with citations. Best for open-ended or comparative questions that need Inputs: query, topic, freshness, max_sources |
search | Search the web for current information on any topic. Returns extracted page content, not just snippets. Best for factual lookups, specific questions, or when you need a list of sources. For open-ended questions that need synthesis across ma Inputs: query, search_depth, max_results, include_answer, include_domains, exclude_domains |
Every block below points at https://mcp.sofya.co/mcp. Pick your client and copy.
claude mcp add --transport http sofya https://mcp.sofya.co/mcp
{
"mcpServers": {
"sofya": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://mcp.sofya.co/mcp"]
}
}
}{
"mcpServers": {
"sofya": {
"url": "https://mcp.sofya.co/mcp"
}
}
}{
"servers": {
"sofya": {
"type": "http",
"url": "https://mcp.sofya.co/mcp"
}
}
}{
"context_servers": {
"sofya": {
"url": "https://mcp.sofya.co/mcp"
}
}
}{
"mcpServers": {
"sofya": {
"serverUrl": "https://mcp.sofya.co/mcp"
}
}
}{
"mcpServers": {
"sofya": {
"url": "https://mcp.sofya.co/mcp"
}
}
}name: Sofya
version: 0.0.1
schema: v1
mcpServers:
- name: Sofya
type: streamable-http
url: https://mcp.sofya.co/mcp{
"mcpServers": {
"sofya": {
"httpUrl": "https://mcp.sofya.co/mcp"
}
}
}{
"mcpServers": {
"sofya": {
"type": "http",
"url": "https://mcp.sofya.co/mcp"
}
}
}{
"mcpServers": {
"sofya": {
"url": "https://mcp.sofya.co/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fmcp.sofya.co%2Fmcp&type=streamable_http&id=sofya&name=Sofya
It answered our last check on 17 October 2026 in 376 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 sofya.co and served from mcp.sofya.co, the vendor's own domain: https://mcp.sofya.co/mcp.
4, as returned by the server's own tools/list on 9 September 2026: extract, fetch, research, search.
It answered our last check on 17 October 2026 in 376 ms. Over 10 checks since 4 September 2026 it answered 10.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://mcp.sofya.co/mcp. 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: co.sofya. Endpoint host: mcp.sofya.co. ARD identifier: urn:air:co.sofya:mcp:sofya.
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.