Changeflow
AI-powered web monitoring. Track any website, get structured change intelligence.
Changeflow MCP Server
Monitor any website and get AI-enriched change intelligence via MCP. Manage sources, search changes, and automate web monitoring from Claude, Harvey, or any MCP client.
Requires a Changeflow API token. Get one from your account settings.
What is Changeflow?
Changeflow is an enterprise web intelligence platform. It monitors web pages, PDFs, RSS feeds, and APIs for changes, then uses AI to tell you what changed, why it matters, and what to do about it. Used by compliance teams, legal researchers, competitive intelligence analysts, and procurement teams at Fortune 500 companies and Am Law 200 firms.
Quick Start
Claude Desktop
Add to your claude_desktop_config.json:
{
"mcpServers": {
"changeflow": {
"command": "npx",
"args": ["changeflow-mcp-server"],
"env": {
"CHANGEFLOW_API_TOKEN": "your_api_token_here"
}
}
}
}
Then ask Claude: "List my Changeflow sources" or "Create a new source to monitor fda.gov/guidance"
Remote (Harvey, OpenAI, Claude Code)
Connect directly to the Streamable HTTP endpoint:
POST https://changeflow.com/mcp
Content-Type: application/json
Accept: application/json, text/event-stream
Authorization: Bearer your_api_token_here
Rate limit: 100 requests per hour.
Tools
list_sources
List all your monitored sources with status, tags, and check frequency.
Parameters:
tag- Filter by taglimit- Max results (default 50, max 200)
get_source
Get full details for a specific source by its share code.
Parameters:
source_id(required) - Share code of the source
get_changes
Search and list recent changes across your monitored sources.
Parameters:
query- Keyword search across change contentsince- ISO 8601 datetype- Filter by type: link (new pages found) or change (page content changed)tag- Filter by source tagsource_id- Filter to a specific sourcelimit- Max results (default 50, max 200)
get_change
Get full details of a single change including AI summary and structured diff.
Parameters:
change_id(required) - Change ID (v_123 for page changes, l_456 for link discoveries)
create_source
Create a new source to monitor.
Parameters:
url(required) - URL to monitorlooking_for- What to watch for, in plain Englishfrequency- Check frequency (e.g. "hourly", "daily", "every 6 hours")tags- Comma-separated tags
check_source
Trigger an immediate check on a source.
Parameters:
source_id(required) - Share code of the source
pause_source / resume_source
Pause or resume monitoring on a source.
Parameters:
source_id(required) - Share code of the source
Getting Your API Token
- Sign up at changeflow.com
- Go to Account > API
- Copy your API token
- Set it as
CHANGEFLOW_API_TOKENenvironment variable
Free Regulatory Intelligence
Looking for free, public regulatory data without authentication? Use the GovPing MCP Server instead. It provides open access to 27,000+ structured regulatory changes.
Links
- Changeflow - Enterprise web intelligence platform
- GovPing - Free regulatory intelligence (powered by Changeflow)
- Pricing - Plans from $99/mo
- API Documentation
Rate Limits
- 100 requests per hour per API token
- Need higher limits? Email [email protected]
License
MIT
相关服务器
Bright Data
赞助Discover, extract, and interact with the web - one interface powering automated access across the public internet.
Render-fetch
Drop-in upgrade to Claude's WebFetch that auto-detects JS-rendered pages and fetches them with Playwright headless browser
Olostep MCP Server
A server for web scraping, Google searches, and website URL lookups using the Olostep API.
Oxylabs
Scrape websites with Oxylabs Web API, supporting dynamic rendering and parsing for structured data extraction.
Parallel Task MCP
Perform Deep Research and Batch Tasks
WebSearch
An advanced web search and content extraction tool powered by the Firecrawl API for web scraping and analysis.
Yahoo Finance
Interact with Yahoo Finance to get stock data, market news, and financial information using the yfinance Python library.
Fetch
Fetch web content as HTML, JSON, plain text, or Markdown.
transcriptor-mcp
An MCP server (stdio + HTTP/SSE) that fetches video transcripts/subtitles via yt-dlp, with pagination for large responses. Supports YouTube, Twitter/X, Instagram, TikTok, Twitch, Vimeo, Facebook, Bilibili, VK, Dailymotion. Whisper fallback — transcribes audio when subtitles are unavailable (local or OpenAI API). Works with Cursor and other MCP host
Fetch
Fetch web content in various formats like HTML, JSON, plain text, and Markdown.
Kakuyomu MCP Server
An MCP server for the Kakuyomu novel posting site, enabling users to search for works, retrieve episode lists, and read content.