Skip to main content
Glama
Sign In

Sofya

by co.sofya
OverviewDiscussionsAdmin

Server Details

Web search, fetch, extract, and research for AI agents. Markdown output + AI-synthesized answers.

The last two health checks of this connector failed. 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
Uptime
92.9% over 80 days
OAuth
Works in Glama
Last Tested
Transport
Streamable HTTP
URL
Repository
sofya-co/sofya-mcp
GitHub Stars
2
Server Listing
sofya-mcp
ChatGPT
–
Claude
–

TDQS

A4.6/5.0

Scored across 4 tools

Disambiguation4/5

The four tools all deal with web content, but their intended scopes are mostly distinct: fetch for full known-URL content, extract for a specific answer from one page, search for discovery, and research for multi-source synthesis. Some overlap exists between extract and search with include_answer, though cost and output shape make the choice reasonably clear.

Naming Consistency5/5

All tool names are single lowercase action verbs: extract, fetch, research, search. The convention is consistent and predictable across the set.

Tool Count5/5

Four tools is well-scoped for a read-only web retrieval/research server. Each tool covers a distinct retrieval mode and earns its place without bloating the surface.

Completeness4/5

The set covers the core workflow of searching, fetching, extracting from a known page, and synthesizing multi-source research. Minor gaps remain around structured extraction or crawling/batch extraction across many pages, but agents can work around these with fetch and search.

Tool Schema Changelog

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

  1. 2 tool updates
    • Changedresearch1 field changed
      • addedInput schema / properties / topic / enum
        Added value: +[
+  "general",
+  "news"
+]
    • Changedsearch2 fields changed
      • addedInput schema / properties / search_depth / enum
        Added value: +[
+  "snippets",
+  "basic"
+]
      • addedInput schema / properties / topic / enum
        Added value: +[
+  "general",
+  "news"
+]
  2. 4 tool updates
    • First observedextract
    • First observedfetch
    • First observedresearch
    • First observedsearch

Related MCP Connectors

Related MCP Servers

  • PowerSearch MCP

    theobjectivedad
    A
    license
    Not graded
    quality
    C
    maintenance
    Helps AI agents search the public web and fetch content with anti-bot measures, returning clean markdown outputs suitable for citation.
    2
    Apache 2.0

  • Tavily MCP

    pipeworx-io
    A
    license
    Not graded
    quality
    B
    maintenance
    Enables AI agents to perform LLM-optimized web searches, retrieve recent news articles with full text, and extract clean readable content from URLs. It returns synthesized answers, ranked cited sources, and page text suitable for grounding RAG workflows.
    228 npm
    MIT

  • contextfetch-mcp

    lachy3433
    A
    license
    A
    quality
    D
    maintenance
    Web search and any page as LLM-ready Markdown for AI agents, pruned to the passages relevant to the query, plus research, crawl and site maps. Free keyless tier.
    11
    471 npm
    MIT
Try in Browser
Let your AI agent see the webWeb-to-screenshot MCP for Claude, Cursor and Codex. No cookie banners. Free to start.snap-render.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources