Data Gleaner
io.github.datagleanerPublished by GitHub account datagleanerv1.1.0Updated Nov 7, 2026
Pay-per-result web data tools: company contacts and emails, leads, China social, apps.
Overview
Remote MCP server exposing fourteen Apify web-scraping tools for company contacts, creator emails, China social media, app store and marketplace data, billed…
- What you can do
- Find company contacts: website emails, phones, socials, team and decision-maker pages, domain lookup, enrichment by domain
- Collect local business leads from Google Maps with emails and named contacts
- Find creator emails from YouTube, TikTok and link-in-bio pages
- Scrape China social platforms: Weibo posts, WeChat Official Account articles, Xiaohongshu notes and profiles
- Scrape Google Play apps and reviews, YouTube comments, and AliExpress product search results
- Read run results through Apify's helper tools (run status, dataset items, key-value records, abort run)
- When to use it
- Useful when an assistant needs to gather public web data at scale — building B2B contact or lead lists, enriching company records, finding creator emails, or monitoring Chinese social platforms and marketplace listings — without writing or hosting scrapers.
- Requirements
- A remote Streamable HTTP endpoint at mcp.apify.com with the Data Gleaner tools selected in the URL. An Apify account: OAuth sign-in (a free account works) or an Authorization header carrying an Apify API token. Runs are billed to that Apify account; the free plan includes monthly usage credit. The token-based Claude Desktop setup uses the mcp-remote bridge, which needs Node.js.
Installation
In SourceWeft
- Open Data Gleaner in the dashboard and add it to a workspace.
- Connect the required credentials. They are stored privately and never shown on public pages.
- 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.datagleaner%2Fdata-gleaner-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.Other MCP clients
Add this to your client's mcpServers config. The client completes OAuth sign-in on first connect.
{
"mcpServers": {
"data-gleaner": {
"type": "http",
"url": "https://mcp.apify.com/?tools=datagleaner/website-contact-details-scraper,datagleaner/team-page-contacts,datagleaner/company-domain-finder,datagleaner/google-maps-leads,datagleaner/youtube-channel-contacts,datagleaner/weibo-scraper,datagleaner/wechat-articles,datagleaner/google-play-scraper,datagleaner/youtube-comments-scraper,datagleaner/xiaohongshu-rednote-scraper,datagleaner/tiktok-contacts,datagleaner/company-enrichment-by-domain,datagleaner/bio-link-email-finder,datagleaner/aliexpress-scraper"
}
}
}README
Data Gleaner MCP server
Fourteen web data tools for AI agents, served as one remote MCP server, led by Company Contact Details & Website Email Finder ($2 per 1,000 sites with an email). Company contacts: website emails, team pages and decision makers, company domain finder, Google Maps leads with emails, company enrichment by domain. Creators: YouTube, TikTok and link-in-bio emails. China social: Weibo, WeChat articles, Xiaohongshu. Also Google Play, YouTube comments and AliExpress. You pay per result returned, nothing to install and nothing to host.
The tools are Data Gleaner Actors on Apify, served through Apify's official hosted MCP server at mcp.apify.com. This repository holds the connection configs and the registry metadata; there is no code to run.
Connect
One URL exposes only the Data Gleaner tools:
Two ways to sign in:
- OAuth (recommended). Paste the URL alone. Your client opens an Apify sign-in on first use; a free Apify account works.
- API token. Send the header
Authorization: Bearer <APIFY_TOKEN>, with a token from console.apify.com/settings/integrations.
Runs are billed to your own Apify account at the prices below. Apify's free plan includes monthly usage credit, which covers a first test.
Want only one tool? Keep just that Actor in the tools= list, for example https://mcp.apify.com/?tools=datagleaner/website-contact-details-scraper.
Claude Code
With a token instead of OAuth, add --header "Authorization: Bearer $APIFY_TOKEN".
Claude Desktop and Claude.ai
Settings, Connectors, Add custom connector: name it Data Gleaner and paste the URL. Claude opens the Apify sign-in.
To use a token instead, put this in claude_desktop_config.json (it runs the mcp-remote bridge, so Node.js must be installed; the header is written without a space after the colon because Claude Desktop on Windows splits arguments at spaces):
Cursor
~/.cursor/mcp.json (or .cursor/mcp.json in a project):
For a token instead of OAuth, add "headers": { "Authorization": "Bearer ${env:APIFY_TOKEN}" } next to url.
VS Code
.vscode/mcp.json:
Drop the headers and inputs blocks to use OAuth.
Other clients
Any client that speaks Streamable HTTP takes the same URL: Windsurf, Cline, ChatGPT connectors, n8n, LangChain, the OpenAI and Anthropic APIs' remote MCP options.
Tools
Each Actor is one tool, named like datagleaner--website-contact-details-scraper. Apify's server also adds its helper tools for reading results (get-actor-run, get-dataset-items, get-key-value-store-record, abort-actor-run). None of the fourteen needs a login to the target site, and all charge only for results returned.
Each Actor also runs with no input, returning a small built-in example of at most five results, so an agent can see the output shape for a few cents at most.
What an agent can ask
- "Find the contact email and phone for these 50 company domains."
- "Who are the CEO and founders of these 200 companies, with LinkedIn pages?"
- "Turn this list of company names into official websites, then find their emails."
- "List dentists in Austin with phone, website, email and the owner's name."
- "Find the emails of the top 100 YouTube channels about home espresso."
- "Pull the last 200 Weibo posts mentioning Xiaomi SU7 with their engagement."
Files
server.json: the entry for the official MCP Registry (io.github.datagleaner/data-gleaner-mcp).glama.json: maintainer claim for Glama.llms-install.md: setup steps for agents such as Cline that install servers from a README.
Support
Open an issue here, or use the Issues tab on any Actor's Apify Store page. Data Gleaner is an independent Apify Store developer; Apify runs the MCP server and the billing.
License
MIT
Source: README.md at commit 34f3563
Tools
0Version history
2- v1.1.0LatestOct 31, 2026
- v1.0.0Oct 10, 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