Data Gleaner

What Data Gleaner does

Data Gleaner MCP server provides fifteen web data tools for the Search & Data Extraction category. The tools cover contact discovery, company research, travel pricing, China social platforms, and website extraction. They are implemented as Data Gleaner Actors on Apify and exposed through Apify's hosted MCP service rather than through code in this repository.

Contact and lead-generation tools can find emails and other published contact details from company websites, team pages, YouTube channels, link-in-bio pages, mobile and desktop app listings, Shopify apps, researcher sources, YC founders, and SEC Form D funding records. Company enrichment accepts domains and returns available organization details such as profiles, contact information, and founding dates.

The remaining tools cover Google Hotels prices, Weibo posts, Bilibili videos and comments, and sitemap URLs. The actors do not require a login to the target websites according to the supplied documentation.

How it works

The remote endpoint uses a tools= query parameter to select the Data Gleaner Actors exposed to an MCP client. The repository supplies connection configurations and registry metadata; it does not contain a local server implementation to execute.

Each selected Actor appears as an MCP tool with a name such as datagleaner--google-hotels-scraper. Apify also provides helper operations for checking runs and reading their outputs, including actor-run status, dataset items, key-value records, and run cancellation. Results are returned from Apify and charges apply to the connected account based on the actor's pricing model. The documentation states that billing is based on results returned, with misses free for the tools whose prices are described that way.

Setup and configuration

Data Gleaner MCP server can be connected by pasting the hosted URL into a client that supports Streamable HTTP. OAuth is the recommended option: the client opens Apify sign-in on first use, and a free Apify account can be used for an initial test. Alternatively, send Authorization: Bearer <APIFY_TOKEN> using a token created in Apify account settings.

The README gives configuration examples for Claude Code, Claude Desktop, Claude.ai, Cursor, and VS Code. It also identifies Windsurf and Cline as compatible with the same endpoint. To expose fewer tools, remove Actors from the tools= list and keep only the desired names. Claude Desktop's token-based example uses the mcp-remote bridge and therefore requires Node.js.

Tools and capabilities

The fifteen Actors include:

• Website contact details and company email discovery
• Company enrichment by domain
• Team and leadership page contacts
• YouTube channel and link-in-bio contact discovery
• App developer and Shopify app developer contacts
• Shopify partner and agency contacts
• Researcher email discovery
• YC founder and newly funded company leads from SEC Form D
• Google Hotels price collection
• Weibo and Bilibili extraction
• Sitemap URL extraction

The individual tools use different inputs and result pricing. Examples in the documentation range from per-website or per-company charges to per-person, per-app, per-channel, or per-profile charges. Consult the relevant Actor configuration for exact input fields and current pricing.

Limitations and notes

Data Gleaner MCP server is remote, so there is no local application to install or host. Requests depend on Apify availability, account authentication, and available account credit. OAuth avoids a local token configuration, while token-based setups require the token to be supplied through the MCP client's headers or environment configuration.

The repository documentation does not describe guaranteed coverage, refresh intervals, or result accuracy for individual sources. Contact tools are based on publicly available information; the team-page tool is specifically described as returning published emails and not guessing missing addresses. Review legal, privacy, and site-use requirements before using returned data.