Skip to main content
Glama

anybrowse

by io.github.kc23go
OverviewDiscussionsAdmin

Server Details

Converts any URL to clean, LLM-ready Markdown using real Chrome browsers

Glama couldn't complete the latest health check. If this server requires authentication, missing or expired test credentials may be the cause. A test profile lets Glama authenticate for health checks and discover tools; it is separate from your personal connections.

If you are the author, claim ownership, then add or update a test profile under Admin → Test Profile.

Status
Unhealthy
Last Tested
Transport
Streamable HTTP
URL
Repository
kc23go/anybrowse
GitHub Stars
5
Server Listing
Anybrowse

TDQS

A4.1/5.0

Scored across 5 tools

Disambiguation5/5

Each tool has a clearly distinct purpose: batch_scrape handles multiple URLs, crawl combines search and scraping, extract returns structured JSON, scrape converts a single URL to markdown, and search returns search results. There is no meaningful overlap that would confuse an agent.

Naming Consistency3/5

Most tools use single-word verbs (scrape, search, crawl, extract), but batch_scrape uses a prefix, creating a mixed convention. While readable, the naming is not uniformly patterned.

Tool Count5/5

With 5 tools, the set is well-scoped for a scraping/search service, covering single-page scraping, batch scraping, structured extraction, web search, and crawl without unnecessary bloat.

Completeness4/5

The tool surface covers the main workflows: search to find URLs, scrape to fetch content, batch_scrape for efficiency, and extract for structured data. A minor gap is the lack of pagination or status tracking, but these are not critical for typical use cases.

Tool Schema Changelog

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

  1. 5 tool updates
    • Addedbatch_scrape
    • Changedcrawl1 field changed
      • addedInput schema / properties / context
        Added value: +{
+  "description": "Optional: what you're trying to accomplish (e.g., 'finding competitors pricing', 'researching market trends'). Helps return more targeted results.",
+  "type": "string"
+}
    • Addedextract
    • Changedscrape1 field changed
      • addedInput schema / properties / context
        Added value: +{
+  "description": "Optional: what you're trying to accomplish (e.g., 'comparing job salaries', 'researching competitors', 'extracting product prices'). Helps anybrowse return more relevant content.",
+  "type": "string"
+}
    • Changedsearch1 field changed
      • addedInput schema / properties / context
        Added value: +{
+  "description": "Optional: what you're trying to accomplish. Helps with result relevance.",
+  "type": "string"
+}
  2. 5 tool updates
    • Removedbatch_scrape
    • Changedcrawl1 field changed
      • removedInput schema / properties / context
        Removed value: -{
-  "description": "Optional: what you're trying to accomplish (e.g., 'finding competitors pricing', 'researching market trends'). Helps return more targeted results.",
-  "type": "string"
-}
    • Removedextract
    • Changedscrape1 field changed
      • removedInput schema / properties / context
        Removed value: -{
-  "description": "Optional: what you're trying to accomplish (e.g., 'comparing job salaries', 'researching competitors', 'extracting product prices'). Helps anybrowse return more relevant content.",
-  "type": "string"
-}
    • Changedsearch1 field changed
      • removedInput schema / properties / context
        Removed value: -{
-  "description": "Optional: what you're trying to accomplish. Helps with result relevance.",
-  "type": "string"
-}
  3. 1 tool update
    • Changedextract3 fields changed
      • changedInput schema / properties / context / description
        Previous value: -"Optional: what you're trying to accomplish"New value: +"Optional: what you're trying to accomplish (helps LLM extraction accuracy)"
      • changedInput schema / properties / schema / additionalProperties / enum
        Previous value: -[
-  "string",
-  "number",
-  "boolean",
-  "array"
-]New value: +[
+  "string",
+  "number",
+  "boolean",
+  "array",
+  "object"
+]
      • changedInput schema / properties / schema / description
        Previous value: -"Field names mapped to types: string, number, boolean, array"New value: +"Field names mapped to type strings. Format: {\"fieldName\": \"string|number|boolean|array|object\"}. Example: {\"title\": \"string\", \"price\": \"number\", \"inStock\": \"boolean\", \"tags\": \"array\"}"
  4. 2 tool updates
    • Addedbatch_scrape
    • Addedextract
  5. 3 tool updates
    • Changedcrawl1 field changed
      • addedInput schema / properties / context
        Added value: +{
+  "description": "Optional: what you're trying to accomplish (e.g., 'finding competitors pricing', 'researching market trends'). Helps return more targeted results.",
+  "type": "string"
+}
    • Changedscrape1 field changed
      • addedInput schema / properties / context
        Added value: +{
+  "description": "Optional: what you're trying to accomplish (e.g., 'comparing job salaries', 'researching competitors', 'extracting product prices'). Helps anybrowse return more relevant content.",
+  "type": "string"
+}
    • Changedsearch1 field changed
      • addedInput schema / properties / context
        Added value: +{
+  "description": "Optional: what you're trying to accomplish. Helps with result relevance.",
+  "type": "string"
+}
  6. 1 tool update
    • Removedscreenshot
  7. 1 tool update
    • Addedscreenshot
  8. 3 tool updates
    • First observedcrawl
    • First observedscrape
    • First observedsearch

Related MCP Connectors

Related MCP Servers

  • skrape

    AmokOrg
    A
    license
    Not graded
    quality
    D
    maintenance
    Converts any webpage into clean, LLM-ready Markdown, removing noise and supporting JavaScript rendering.
    MIT

  • agent-web

    foomworks
    A
    license
    Not graded
    quality
    D
    maintenance
    Converts URLs into clean, LLM-ready markdown, respecting robots.txt and never bypassing anti-bot measures or paywalls.
    MIT
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources