Skip to main content
Glama
ToolTrace MCP Server

ToolTrace MCP Server

Official

ToolTrace MCP Server

Give AI agents a complete web intelligence toolkit. This Model Context Protocol server connects Claude Code, Claude Desktop, Cursor, VS Code, Codex, Windsurf and any other MCP client to the ToolTrace API.

One tool per ToolTrace endpoint: scrape any page to clean Markdown, read metadata and JSON-LD, extract links, run on-page SEO audits, detect a site's tech stack, and check XML sitemaps. Free tier included, no card required.

Setup guide: tooltrace.io/mcp

Tools

Tool

Description

tooltrace_extract

Extract clean Markdown, text, metadata, links, JSON-LD, and sections from any webpage

tooltrace_metadata

Get page title, description, canonical URL, Open Graph, and Twitter card fields

tooltrace_links

Extract all internal and external links with anchor text

tooltrace_schema

Extract JSON-LD structured data (Article, Product, FAQ, etc.)

tooltrace_seo_audit

Run an SEO audit with scored checks and recommendations

tooltrace_tech_stack

Detect CMS, frameworks, analytics, CDN, hosting, and more

tooltrace_sitemap

Inspect and parse XML sitemaps

Related MCP server: mcp-web-search

Two ways to connect

Hosted, for clients that take a connector URL. Nothing to install or update:

https://mcp.tooltrace.io/mcp
claude mcp add --transport http tooltrace https://mcp.tooltrace.io/mcp \
  --header "Authorization: Bearer your-api-key"

Also listed on Smithery.

Local, over stdio, for clients that run a process. Use this when your client does not speak HTTP, or when you would rather your API key never left your own machine. That is the quick start below.

Both expose the same tools and bill the same credits.

Quick start

1. Get a free API key

Sign up at tooltrace.io/signup. The free plan includes 1,000 credits per month.

2. Install

npm install -g @tooltrace/mcp-server

3. Configure your MCP client

Claude Desktop (~/Library/Application Support/Claude/claude_desktop_config.json):

{
  "mcpServers": {
    "tooltrace": {
      "command": "tooltrace-mcp",
      "env": {
        "TOOLTRACE_API_KEY": "your-api-key"
      }
    }
  }
}

Claude Code:

claude mcp add tooltrace tooltrace-mcp -e TOOLTRACE_API_KEY=your-api-key

Cursor (.cursor/mcp.json):

{
  "mcpServers": {
    "tooltrace": {
      "command": "tooltrace-mcp",
      "env": {
        "TOOLTRACE_API_KEY": "your-api-key"
      }
    }
  }
}

VS Code (.vscode/mcp.json):

{
  "servers": {
    "tooltrace": {
      "command": "tooltrace-mcp",
      "env": {
        "TOOLTRACE_API_KEY": "your-api-key"
      }
    }
  }
}

Codex (~/.codex/config.toml):

[mcp_servers.tooltrace]
command = "tooltrace-mcp"
env = { TOOLTRACE_API_KEY = "your-api-key" }

Windsurf (mcp_config.json):

{
  "mcpServers": {
    "tooltrace": {
      "command": "tooltrace-mcp",
      "env": {
        "TOOLTRACE_API_KEY": "your-api-key"
      }
    }
  }
}

Any other MCP client: run tooltrace-mcp over stdio and set the TOOLTRACE_API_KEY environment variable. Full per-client setup guide at tooltrace.io/mcp.

Run with npx (no install)

TOOLTRACE_API_KEY=your-api-key npx @tooltrace/mcp-server

Usage examples

Once connected, your AI agent can:

  • "Extract the main content from this blog post as Markdown"

  • "What technologies does competitor.com use?"

  • "Run an SEO audit on our landing page"

  • "Get all the links from this documentation page"

  • "Extract the JSON-LD schema from this product page"

  • "Check the sitemap for this website"

Rendering modes

All tools support a render parameter:

  • never: Fast static fetch, 1 credit. Best for server-rendered pages.

  • auto (default): Starts static, renders in browser if needed. 1 or 5 credits.

  • always: Full browser rendering, 5 credits. For JavaScript-heavy SPAs.

Development

git clone https://github.com/ToolTrace-io/mcp-server.git
cd mcp-server
npm install
npm run build
TOOLTRACE_API_KEY=your-key node dist/index.js

License

MIT

Available Tools

7 tools
tooltrace_extractAInspect

Extract clean content from a webpage. Returns Markdown, plain text, metadata, links, JSON-LD schema, and content sections. Use this for scraping, RAG ingestion, or content analysis.

Inputs: url (required), mode, render, include, +2 more.

tooltrace_metadataAInspect

Extract page metadata: title, description, canonical URL, author, publication date, favicon, Open Graph, and Twitter card fields. Lightweight alternative to full extraction.

Inputs: url (required), render, wait_until, wait_for_selector.

tooltrace_schemaAInspect

Extract JSON-LD structured data from a webpage. Returns schema.org entities like Article, Product, Organization, FAQ, BreadcrumbList, etc.

Inputs: url (required), mode, render, wait_until, +1 more.

tooltrace_seo_auditAInspect

Run an SEO audit on a webpage. Returns a score (0-100), weighted checks for metadata, headings, images, canonical signals, robots directives, social tags, schema, and content length, with evidence and recommendations.

Inputs: url (required), render, wait_until, wait_for_selector.

tooltrace_sitemapAInspect

Inspect a website's sitemap. Discovers sitemap URLs, parses sitemap XML, and returns listed page URLs with last-modified dates and change frequencies.

Inputs: url (required), render.

tooltrace_tech_stackBInspect

Detect the technology stack of a website: CMS, frameworks, JavaScript libraries, analytics, CDN, hosting, fonts, security tools, and more. Returns categorized detections with confidence levels.

Inputs: url (required), render, wait_until, wait_for_selector.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.9/5.0

    Scored across 7 tools

    Disambiguation4/5

    Each tool targets a distinct website analysis concern (sitemap, content, metadata, links, schema, SEO audit, tech stack), and descriptions clarify specialized use cases. The main ambiguity is that tooltrace_extract includes metadata, links, and schema, potentially overlapping with the dedicated extraction tools, but explicit 'lightweight' and 'specific' intent reduces confusion.

    Naming Consistency5/5

    All tools follow a consistent 'tooltrace_<feature>' pattern using snake_case, making the naming predictable and uniform. Although one tool uses a verb (extract) while others use nouns, the pattern is consistent and no mixing of conventions exists.

    Tool Count5/5

    Seven tools is well within the ideal 3-15 range for a website analysis server. Each tool serves a distinct, useful function without redundancy or unnecessary bloat.

    Completeness4/5

    The server covers the core website analysis workflow: discovery (sitemap), content extraction, metadata, links, structured data, SEO auditing, and tech stack detection. Minor gaps like a dedicated robots.txt checker or performance metrics are absent, but agents can accomplish primary tasks without significant workarounds.

    Maintenance

    ActivityStale
    ResponsivenessOutdated data

    Related MCP Connectors

    Related MCP Servers