FineData

io.github.quality-networkPublished by GitHub account quality-networkv0.3.1Updated Oct 24, 2026

FineData web scraping MCP — JavaScript rendering, captcha solving, markdown for AI agents

VerifiedStreamable HTTPWeb executableWeb Search & ScrapingBrowser Automation

Overview

AI-generated overview

FineData MCP lets an AI assistant scrape web pages through the FineData API, with JavaScript rendering, captcha solving, proxies and markdown or JSON output.

What you can do
Fetch and scrape pages synchronously, returning markdown or JSON, with optional JavaScript rendering, stealth and proxy settings and structured extraction. Send POST, PUT, PATCH or DELETE requests through the same scraping pipeline. Run asynchronous scrape jobs and poll, list or cancel them. Batch-scrape up to 100 URLs and check batch progress. Check period token usage.
When to use it
Useful when an assistant needs page content that a plain fetch cannot get: JavaScript-heavy sites, pages behind captchas, or targets needing datacenter, ISP, residential or mobile proxies. Also suited to larger batch or asynchronous collection jobs.
Requirements
Either the remote endpoint with an Authorization bearer API key or OAuth 2.1, or a local stdio process via uvx, pip (finedata-mcp) or npx (@finedata/mcp-server). A FineData API key is required for stdio, set as FINEDATA_API_KEY. Network access to the FineData API.
Before you install
Requests consume paid FineData tokens; stealth and proxy modes cost more than plain requests, and the gateway may override the requested engine or proxy. The API key is a secret passed as FINEDATA_API_KEY or an Authorization bearer header. send_http_request can issue POST, PUT, PATCH and DELETE requests to arbitrary targets, so it can change remote data. Scraped page content and target URLs go to FineData.

Installation

In SourceWeft

  1. Open FineData in the dashboard and add it to a workspace.
  2. Connect the required credentials. They are stored privately and never shown on public pages.
  3. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.quality-network%2Ffinedata-mcp/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config. The client completes OAuth sign-in on first connect.

{
  "mcpServers": {
    "finedata": {
      "type": "http",
      "url": "https://mcp.finedata.ai/mcp"
    }
  }
}

README

FineData MCP Server

MCP (Model Context Protocol) server for FineData web scraping API.

Enables AI agents (Claude, Cursor, GPT, …) to fetch pages that need a full browser and return clean data:

  • JavaScript rendering and browser actions
  • Captcha solving
  • Datacenter / ISP / residential / mobile proxies
  • Markdown or JSON output (markdown by default)
  • AI structured extraction
  • Local stdio or remote Streamable HTTP (+ OAuth 2.1)

Version: 0.3.1

Modes

Start with a plain request. Stealth and proxy modes are available when a page needs a full browser; they consume more tokens than a plain request. Exact rates are in the documentation and via get_usage. Gateway may apply a domain strategy that overrides the requested engine or proxy; trust tokens_used in the response.

Installation

uvx (recommended)

bash
curl -LsSf https://astral.sh/uv/install.sh | shFINEDATA_API_KEY=fd_xxx uvx finedata-mcp

pip

bash
pip install finedata-mcpFINEDATA_API_KEY=fd_xxx finedata-mcp

npx

bash
npx -y @finedata/mcp-server

Cursor

~/.cursor/mcp.json (Windows: %USERPROFILE%\.cursor\mcp.json):

json
{  "mcpServers": {    "finedata": {      "command": "uvx",      "args": ["finedata-mcp"],      "env": {        "FINEDATA_API_KEY": "fd_your_api_key_here"      }    }  }}

Cursor deeplink (after publishing): install via MCP directory / “Add to Cursor”.

Remote (Streamable HTTP)

json
{  "mcpServers": {    "finedata": {      "url": "https://mcp.finedata.ai/mcp",      "headers": {        "Authorization": "Bearer fd_your_api_key_here"      }    }  }}

OAuth 2.1 (Claude.ai / ChatGPT connectors): register via AS at https://api.finedata.ai, consent in the cabinet, then use the access token as Bearer.

Environment

VariableRequiredDefaultDescription
FINEDATA_API_KEYstdio: yes—API key
FINEDATA_API_URLnohttps://api.finedata.aiAPI base
FINEDATA_TIMEOUTno180HTTP client timeout (seconds)
FINEDATA_MCP_HOSTHTTP0.0.0.0Bind host
FINEDATA_MCP_PORTHTTP8080Bind port
FINEDATA_OAUTH_ISSUERremote OAuth—AS URL (gateway)
FINEDATA_MCP_RESOURCE_URLremote OAuth—Public MCP URL
FINEDATA_JWT_SECRETremote OAuth—Verify aud=mcp JWTs

Tools

ToolPurpose
scrape_urlSync scrape with GET, read-only (markdown default)
send_http_requestSync POST / PUT / PATCH / DELETE through the same pipeline
scrape_asyncAsync job, GET (formats=['markdown'] default)
get_job_statusPoll job (markdown, not raw HTML)
cancel_jobCancel job
list_jobsList jobs
batch_scrapeUp to 100 URLs (string or {url,...} objects)
get_batch_statusBatch progress
get_usagePeriod usage via api_tokens_used

Notable parameters: use_antibot, proxy_country, proxy_sticky, proxy_profile_id, auto_retry, stealth modes, formats, only_main_content, extract_*.

Async/batch: no csv/xlsx formats (sync only).

HTTP transport

bash
finedata-mcp --transport http --host 0.0.0.0 --port 8080

Health: GET /health. Protected resource metadata is served at the path-scoped URL for the endpoint — GET /.well-known/oauth-protected-resource/mcp — because FINEDATA_MCP_RESOURCE_URL carries the /mcp path. Clients normally find it from the WWW-Authenticate header on a 401 rather than guessing.

Support

License

MIT

Source: README.md at commit ec88356

Tools

0
This server asks you to sign in, so SourceWeft could not read its tools without an account and has not indexed them. What a connected account sees can depend on that account and its permissions.

Version history

1
  1. v0.3.1LatestSep 16, 2026

Score

85% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts