Skip to main content
Glama
sweetcornna

free-search-mcp

by sweetcornna
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Related Servers

Alternatives to free-search-mcp

No user-submitted related servers found.

    Related Servers

    • Lookout

      SylphxAI
      A
      license
      Not graded
      quality
      F
      maintenance
      MCP server enabling local-first web search, fetch, extract, and caching with citeable excerpts, no API key required. Supports research workflows for agents and apps.
      5 npm
      1
      MIT

    • LLM Researcher

      Code-Hex
      F
      license
      Not graded
      quality
      D
      maintenance
      A lightweight MCP server that enables LLMs to search the web via DuckDuckGo, search GitHub code repositories, and extract clean content from web pages in LLM-friendly formats.
      8
      -

    • svipall

      ilien-dev
      A
      license
      A
      quality
      A
      maintenance
      A local-first MCP server that lets AI agents read any webpage as clean Markdown, crawl whole sites within configured limits, search without API keys, and solve supported captchas locally — all without cloud services or third-party keys.
      30
      15
      AGPL 3.0

    • uvxwebsearchmcp

      DanielNMC
      A
      license
      Not graded
      quality
      B
      maintenance
      A zero-config web search and fetch MCP server for LLM agents, featuring multi-backend metasearch, persistent rolling cache, and structured error envelopes for retry-friendly interactions.
      MIT

    • web-docs-mcp

      Aleksandrr
      F
      license
      A
      quality
      B
      maintenance
      A local-first MCP server for web search and documentation fetching, providing free DuckDuckGo search, URL-to-markdown conversion, and library docs from npm, PyPI, crates.io, Go, and GitHub with caching.
      5
      -
    Deploy Server
    Give agents eyes on the webHosted screenshot MCP. Send a URL, get a pixel-perfect image. $0.002 per grab. Works with Claude, Cursor, and Codex.grabbit.liveAd

    TDQS

    A4.8/5.0

    Scored across 11 tools

    Disambiguation5/5

    Each tool serves a clearly distinct purpose: search for discovery, fetch for single URLs, fetch_batch for multiple URLs, read_doc for document parsing/pagination, research for search+read combo, paper_graph for citation graphs, cache_search for local cache search, engines for engine metadata, compare for side-by-side comparison, extract_structured for metadata, and download for file storage. Cross-references between tools clarify boundaries, so misselection is unlikely.

    Naming Consistency4/5

    Tool names are all lowercase with underscores, but the pattern isn't uniform: some are simple verbs (fetch, search, research, compare, download), while others are compound (fetch_batch, read_doc, cache_search, paper_graph, extract_structured, engines). This is still predictable and readable, with no mixing of camelCase or inconsistent verb styles, so it's just a minor deviation from a fully consistent verb_noun pattern.

    Tool Count5/5

    With 11 tools, the server is well-scoped for its purpose (web search, fetching, reading, and research). Each tool earns its place, covering distinct workflows without redundancy. The count is within the ideal 3-15 range, so it feels neither thin nor bloated.

    Completeness5/5

    The tool surface comprehensively covers the domain: discovery (search, research, engines), fetching (fetch, fetch_batch), reading (read_doc, fetch), local cache querying (cache_search), specialized tasks (paper_graph, extract_structured, compare, download), and pagination. There are no obvious gaps—any common search/read/research workflow has a dedicated tool or a clear combination, and even edge cases like metadata extraction and download are handled.

    Maintenance

    ActivityMaintained
    ResponsivenessNo issues

    Resources