MeshArc
Crawl and scrape sites to markdown, then ask what changed between runs
- Pricing
- Freemium
- Platforms
- API, Web
- Runs
- Remotely
- Version
- 0.7.7
- Listing updated
- 3 days ago
About MeshArc
MeshArc is a freemium MCP server for web search and scraping. It runs as a hosted remote server, so there is nothing to install locally.
MeshArc's hosted server puts 21 tools in front of an assistant, grouped into one-off reads, crawls, research agents, monitors and projects. Single pages, up to 500 URLs at once, and PDF or Word files can be returned as text. A long result is delivered as an index with excerpts so it fits a chat turn. Search can use Google, falling back to DuckDuckGo and Bing, and optionally return each hit as markdown.
Its distinguishing feature is memory over time. A project crawls a site on a schedule and compares runs, and monitors rerun a web search or an agent question hourly, daily or weekly and report new, dropped and moved results or changed answer values. An assistant can set up a project from a plain sentence, check the sitemap to find where a blog really lives, and set include and exclude path globs. Misspelled setting names are refused by name.
The hosted endpoint uses OAuth in the browser and is read-only unless you allow changes. A Python SDK is also published.
Install
Run in a terminal
claude mcp add --transport http mesharc https://mcp.mesharc.dev/mcpAdd to Settings → Connectors → Add custom connector
https://mcp.mesharc.dev/mcpAdd to ~/.cursor/mcp.json
{
"mcpServers": {
"mesharc": {
"url": "https://mcp.mesharc.dev/mcp"
}
}
}Add to .vscode/mcp.json
{
"servers": {
"mesharc": {
"type": "http",
"url": "https://mcp.mesharc.dev/mcp"
}
}
}Add to ~/.codeium/windsurf/mcp_config.json
{
"mcpServers": {
"mesharc": {
"serverUrl": "https://mcp.mesharc.dev/mcp"
}
}
}Add to your client's MCP settings (most use this shape)
{
"mcpServers": {
"mesharc": {
"type": "http",
"url": "https://mcp.mesharc.dev/mcp"
}
}
}Tools this server provides (6)
Taken from the project documentation; the running server may differ.
- get_project
- Reads a project, or lists available settings when none is given.
- map_site
- Lists a site's sitemap URLs with a search filter.
- create_project
- Creates a project from a seed URL, schedule and config.
- update_project
- Changes a project's schedule or config.
- start_run
- Starts a crawl run, optionally waiting for it.
- get_job
- Fetches the result of a long-running job.
What it does
- 21 tools in five kinds
- One-off reads, crawls, research agents, monitors and projects.
- Change tracking
- Compare crawls and see what is added, changed or gone.
- Scheduled monitors
- Rerun searches or agent questions hourly, daily or weekly.
- Sitemap mapping
- List a site's sitemap URLs with a search filter.
- Plain-language projects
- Describe a section and schedule and the assistant configures it.
- Document reading
- PDF and .docx files are read as text.
Good for
- Watch competitor documentation for changes
- Crawl docs and find pages mentioning rate limits
- Research a question across several pages with sources
- Track one blog section weekly
Pricing
Freemium, from $29 a month
Free 1,000 credits once; Starter $29/mo, Growth $99/mo, Scale $349/mo.
Prices change. Check mesharc.dev before you buy.
MeshArc FAQ
How do I connect?
Add https://mcp.mesharc.dev/mcp as a custom connector, sign in and approve. No key copy is needed.
Can it change things?
It is read-only unless you allow changes.
What does it cost?
A free tier gives 1,000 credits once; Starter is $29 a month, Growth $99, Scale $349, and Enterprise starts at $1,500.
What happens with long results?
They arrive as an index with excerpts, budgeted across the answer.
Is MeshArc free?
MeshArc has a free plan, with paid plans for more usage or features. Paid plans start at $29 a month.
How do I add MeshArc to Claude Code?
Run this command in your terminal: claude mcp add --transport http mesharc https://mcp.mesharc.dev/mcp
What are the best alternatives to MeshArc?
The closest alternatives to MeshArc are Scrapling MCP Server, Firecrawl MCP Server, SearXNG Search, NeuralVerge and AI-Powered directory.
Alternatives to MeshArc

Scrapling MCP Server
MCP serverMCP server for AI clients to scrape sites with HTTP and stealth browser sessions
Runs locally- 17 tools
- Open source
- 104K GitHub stars
- Web search and scraping

Firecrawl MCP Server
MCP serverMCP server that lets AI agents search, scrape and interact with web pages
- 3 tools
- Remote
- Freemium
- 7.8K GitHub stars
- Web search and scraping

SearXNG Search
MCP serverMCP server for web search and page reading through a SearXNG instance
Runs locally- 3 tools
- Open source
- 1.4K GitHub stars
- Web search and scraping

NeuralVerge
MCP serverStructured, source-tagged business and people data from 300+ sources for agents
- 200 tools
- Remote
- Free trial
- 1 GitHub star
- Web search and scraping

AI-Powered directory
MCP serverSearch AI tools, agents and MCP servers and get install configs from inside your AI assistant.
- 4 tools
- Remote
- Free
- Developer tools

Shopify MCP Server (any store)
MCP serverHosted MCP server that returns any Shopify store's products, prices and stock
Not checked yet- 4 tools
- Remote
- Paid
- E-commerce