# tooltrace.io MCP server

> tooltrace.io MCP server, an MCP server by tooltrace.io, listed from the official MCP registry. Indexed, not reviewed: facts and our own checks, no score or ranking. Web tools for AI agents: scrape pages to Markdown, audit SEO, detect tech stacks, check sitemaps

- Canonical: https://www.anchorterminal.com/tools/tooltrace-mcp-server
- Markdown: https://www.anchorterminal.com/tools/tooltrace-mcp-server.md (~900 tokens)
- Slim: https://www.anchorterminal.com/tools/tooltrace-mcp-server.min.md (~830 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/tools/tooltrace-mcp-server.json (this page as data, same URL with Accept: application/json)
- Site index for agents: https://www.anchorterminal.com/llms.txt (full text: https://www.anchorterminal.com/llms-full.txt)
- API: https://www.anchorterminal.com/api/v1/index.json
- Updated: 2026-10-05

# tooltrace.io MCP server

> Indexed, not reviewed: facts from the official MCP registry and our own checks. No score, grade or rank, and not in the rankings until the panel reviews it. How the index works: https://www.anchorterminal.com/indexed/

- Kind: MCP server, by tooltrace.io (https://tooltrace.io/mcp)
- Category: Web scraping & crawling (https://www.anchorterminal.com/categories/web-scrapers.md)
- Listed because: It's published in the registry under tooltrace.io, a namespace the registry only gives to whoever proves they control that domain.
- What the official MCP registry says: Web tools for AI agents: scrape pages to Markdown, audit SEO, detect tech stacks, check sitemaps

## Facts

- MCP registry: `io.tooltrace/mcp-server` 0.1.3
- Endpoint: https://mcp.tooltrace.io/mcp (streamable HTTP)
- Package: npm `@tooltrace/mcp-server` (stdio)
- Source: https://github.com/ToolTrace-io/mcp-server
- Website: https://tooltrace.io/mcp
- npm downloads a week: 33
- GitHub stars: 0
- Registry entry updated: 2026-09-08

## Tools

- Tools it lists (7, about 2,966 tokens of context, `tools/list` without credentials over MCP 2025-11-25, checked 2026-10-04 22:25 UTC):
  - `tooltrace_extract` (read-only): Extract clean content from a webpage. Returns Markdown, plain text, metadata, links, JSON-LD schema, and content sections. Use this for scraping, RAG…
  - `tooltrace_metadata` (read-only): Extract page metadata: title, description, canonical URL, author, publication date, favicon, Open Graph, and Twitter card fields. Lightweight alternative to…
  - `tooltrace_links` (read-only): Extract all links from a webpage with anchor text, internal/external classification, and normalized URLs.
  - `tooltrace_schema` (read-only): Extract JSON-LD structured data from a webpage. Returns schema.org entities like Article, Product, Organization, FAQ, BreadcrumbList, etc.
  - `tooltrace_seo_audit` (read-only): Run an SEO audit on a webpage. Returns a score (0-100), weighted checks for metadata, headings, images, canonical signals, robots directives, social tags,…
  - `tooltrace_tech_stack` (read-only): Detect the technology stack of a website: CMS, frameworks, JavaScript libraries, analytics, CDN, hosting, fonts, security tools, and more. Returns categorized…
  - `tooltrace_sitemap` (read-only): Inspect a website's sitemap. Discovers sitemap URLs, parses sitemap XML, and returns listed page URLs with last-modified dates and change frequencies.
- How its tools read to an agent (0 errors, 0 warnings, 0 notes, about 2,966 tokens; rules at https://www.anchorterminal.com/check.md; not part of the score):

- JSON: https://www.anchorterminal.com/api/v1/tools/tooltrace-mcp-server.json
- Being indexed says nothing about quality, and nobody can pay for it. Ask for a review: https://www.anchorterminal.com/builders/#claiming