mcpField
S
Sofya

Sofya

Remote
sofya.coSearch2Updated 3w ago

About Sofya

Sofya is an MCP service for AI agents that searches, fetches, extracts, and researches web content, with Markdown output and cited synthesized reports. It can be used as a hosted remote server or run locally via npm.

Key features

  1. 01Searches the web and retrieves page content
  2. 02Fetches URLs as Markdown
  3. 03Extracts structured information with AI
  4. 04Researches sources in parallel with citations
  5. 05Supports hosted and local operation

Use cases

  1. 01Find recent web information and retrieve full pages
  2. 02Fetch documents and organize their contents
  3. 03Compile a cited research report from multiple sources

MCP support

Sofya exposes four read-only tools for search, fetch, extract, and research to MCP clients. Clients can connect to `https://sofya.co/mcp` or run the local server over stdio.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://mcp.sofya.co/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

All endpoints
Streamable HTTPhttps://mcp.sofya.co/mcpAuth required

Tools

Details

From the project README

sofya-mcp

npm version

MCP server for Sofya - web search, fetch, extract, and deep research for AI agents, exposed over the Model Context Protocol.

Use it either way:

  • Hosted (no install): connect your client to https://sofya.co/mcp with your API key as a Bearer token. This is the server listed in the MCP registry as co.sofya/sofya.
  • Local: run this sofya-mcp package over stdio. It is a thin wrapper around the Sofya REST API with the same tools.

All four tools are read-only. Eligible GitHub accounts get 2,000 free credits a month.

Tools

ToolWhat it doesCost
searchSearch the web and get extracted page content (not just snippets). Supports news topic, domain filters, freshness, and optional AI-synthesized answer.1-2 credits (+10 for include_answer)
fetchFetch up to 10 URLs as clean markdown. Also handles PDF, DOCX, XLSX, PPTX, EPUB, and more.2 credits / URL
extractFetch a page and pull specific structured info using AI.10 credits
researchDecompose a question into sub-queries, read many sources in parallel, and synthesize a cited report.50 credits

Hosted server (VS Code / Copilot and others)

Get an API key at sofya.co (keys look like ay_live_...), then point your client at the hosted endpoint.

VS Code / GitHub Copilot (.vscode/mcp.json):

{
  "servers": {
    "sofya": {
      "type": "http",
      "url": "https://sofya.co/mcp",
      "headers": { "Authorization": "Bearer ay_live_..." }
    }
  }
}

Claude Code:

claude mcp add --transport http sofya https://sofya.co/mcp --header "Authorization: Bearer ay_live_..."

Cursor (~/.cursor/mcp.json):

{
  "mcpServers": {
    "sofya": {
      "url": "https://sofya.co/mcp",
      "headers": { "Authorization": "Bearer ay_live_..." }
    }
  }
}

Then ask your agent things like "search for the latest Node.js LTS release notes", "fetch this PDF and summarize it", or "research how the EU AI Act treats open-weight models". Full API docs: sofya.co/docs.

Local server (npm)

Prerequisites
  • Node.js 18+
  • A Sofya API key - get one at sofya.co (keys look like ay_live_...)
Quick start

Run it directly with npx - no install needed:

SOFYA_API_KEY=ay_live_... npx -y sofya-mcp
Configuration
Claude Code
claude mcp add sofya --env SOFYA_API_KEY=ay_live_... -- npx -y sofya-mcp
Claude Desktop / Cursor / Windsurf / VS Code

Add this to your MCP config (e.g. claude_desktop_config.json, or .cursor/mcp.json):

{
  "mcpServers": {
    "sofya": {
      "command": "npx",
      "args": ["-y", "sofya-mcp"],
      "env": {
        "SOFYA_API_KEY": "ay_live_..."
      }
    }
  }
}
Codex

Add it with the Codex CLI:

codex mcp add sofya --env SOFYA_API_KEY=ay_live_... -- npx -y sofya-mcp

Or edit ~/.codex/config.toml directly. Note Codex puts environment variables in a nested [mcp_servers.<name>.env] table:

[mcp_servers.sofya]
command = "npx"
args = ["-y", "sofya-mcp"]

[mcp_servers.sofya.env]
SOFYA_API_KEY = "ay_live_..."

Then run /mcp inside Codex to confirm the server is connected.

Environment variables
VariableRequiredDefaultDescription
SOFYA_API_KEYyes-Your Sofya API key (ay_live_...).
SOFYA_BASE_URLnohttps://sofya.coOverride the Sofya API base URL.

CLI flags --api-key and --base-url take precedence over the env vars. Run npx sofya-mcp --list-tools to print the tool schemas, or --help for options.

Development

git clone https://github.com/sofya-co/sofya-mcp.git
cd sofya-mcp
npm install          # also builds via the prepare script
npm run build        # compile TypeScript to build/
npm run watch        # recompile on change
npm run inspector    # debug with @modelcontextprotocol/inspector

The server is a single file, src/index.ts. Tool definitions mirror Sofya's hosted MCP server exactly (same names, parameters, and defaults).

License

MIT - see LICENSE.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.