• DATA
  • LISTS
  • REVIEWS
  • LOGS

How to extract contact info with your AI

Connect the Regex Toolkit to your AI client to pull specific data points from raw text. Once connected, your agent handles the heavy lifting of pattern matching.

Ask AI about this page

Short answer

How can I pull emails and phone numbers from my documents using AI?

Your AI uses the Regex Toolkit to scan unstructured text for specific patterns like email addresses or URLs. It then organizes those findings into a structured JSON format. You get a clean list ready for your database or CRM.

Where every piece of data lands.

The outcomes of extraction

The AI processes your raw input and sorts the results into these specific formats.

DATA

Structured JSON arrays

The AI uses extract_pattern to turn text into machine-readable lists. You get clean arrays of emails, phone numbers, or URLs.

LISTS

Cleaned contact lists

Instead of a wall of text, you get a categorized list of every valid contact found. This makes it easy to copy into a spreadsheet.

REVIEWS

Human verification needed

The AI flags any patterns that look suspicious or incomplete. You decide if these edge cases should be included in your final set.

LOGS

Pattern match reports

The agent provides a summary of how many matches it found for each specific pattern. This helps you see what was captured.

The workflow

What your AI does when the text arrives.

The AI moves from raw text to structured data through a series of pattern-matching steps.

  1. Scan text

    Your agent reads through the provided transcript or document to find any strings that match your requested patterns.

    extract_pattern

  2. Isolate matches

    The AI pulls the specific characters that fit the regex criteria, stripping away the surrounding conversational filler.

    extract_pattern

  3. Format results

    The agent takes the raw strings and wraps them in a JSON structure so they are easy to use in other apps.

    extract_pattern

  4. Validate output

    The AI checks the extracted data against the pattern rules to ensure no broken or partial strings are included.

    extract_pattern

Try it

Copy these to start.

Use these prompts to trigger the extraction process immediately.

Starting points

These are opening lines. Swap out the bracketed text for your specific file or channel names.

Regex Toolkit Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_iWHGnBSf4hsPpyRONBGuBJdlaAxPgjzlM6EjoAIv/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — Regex Toolkit capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "regex-toolkit-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_iWHGnBSf4hsPpyRONBGuBJdlaAxPgjzlM6EjoAIv/mcp"
    }
  }
}
Copy into chat04

  • Extract all email addresses from this meeting transcript.

  • Find every URL mentioned in this document and return them as a JSON array.

  • Scan this Slack thread for any phone numbers.

  • Look through the attached PDF and pull out all the website links.

  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Start here

Connect Regex Toolkit once, then ask.

Click the link to connect the MCP to your client. Your login stays encrypted on our side, and you can find the full technical breakdown on the Connector page.

Connect Regex Toolkit to your AI

FAQ

How this task behaves.

  • 01

    Can the AI fix typos in the email addresses it finds?

    No. The AI only extracts the text exactly as it appears in the source. If an email is misspelled in your transcript, it will be extracted with that same misspelling.

  • 02

    Will the AI automatically upload these contacts to my CRM?

    No. The AI only extracts and structures the data. You are responsible for moving that JSON data into your CRM or other tools.

  • 03

    Can I extract custom patterns that aren't emails or URLs?

    Yes. As long as you can describe the pattern or provide the regex logic, your agent can hunt for it.

  • 04

    Does the AI delete the original document after extraction?

    No. The AI only reads the content to perform the extraction. It has no permission to modify or delete your files.

  • 05

    What happens if a phone number is formatted strangely?

    The AI follows the specific pattern you request. If the pattern is too strict, it might miss strangely formatted numbers. If it is too loose, it might grab extra characters.

  • More questions about Regex Toolkit? See everything the Regex Toolkit Connector can do

Connect Regex Toolkit to Claude, Cursor, ChatGPT & more