Skip to main content
Glama
Sign In
google-surf-mcp

google-surf-mcp

by HarimxChoi
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Related Servers

Alternatives to google-surf-mcp

  • Brave Search MCP Server

    Brave Search MCP Serverofficial

    brave
    A
    license
    A
    quality
    B
    maintenance
    An MCP implementation that integrates the Brave Search API, providing comprehensive search capabilities including web, local business, image, video, news searches, and AI-powered summarization.
    8
    60,702 npm
    1,562
    MIT

  • Exa MCP Server

    dsouza-anush
    A
    license
    A
    quality
    D
    maintenance
    Enables AI assistants to perform real-time web searches, company research, content crawling, LinkedIn searches, and deep research tasks using the Exa AI Search API. Can be deployed locally or on Heroku for remote access.
    2
    67,363 npm
    1
    MIT

  • SerpMCP

    AceDataCloud
    A
    license
    B
    quality
    B
    maintenance
    An MCP server that provides structured Google Search capabilities including web, images, news, videos, maps, and local places via the AceDataCloud SERP API. It enables AI clients to perform localized searches and retrieve detailed information from the Google Knowledge Graph.
    11
    326 PyPI
    1
    MIT

Related Servers

  • G-Search MCP

    jae-jae
    A
    license
    B
    quality
    F
    maintenance
    A powerful MCP server that enables parallel Google searching with multiple keywords simultaneously, providing structured results while handling CAPTCHAs and simulating user browsing patterns.
    1
    68 npm
    272
    MIT

  • gsearch

    RayenMlayeh
    A
    license
    Not graded
    quality
    B
    maintenance
    Enables AI agents to run real Google searches through a self-hosted browser on their own IP or a proxy, returning typed JSON with organic results rewritten to their true destination URLs, AI Overviews, People also ask, related searches, and structured block errors. Requires no API key and works over MCP with any client.
    35 PyPI
    8
    MIT

  • google-search-mcp

    esinecan
    A
    license
    A
    quality
    C
    maintenance
    MCP server for Google Search using a logged-in browser profile, delivering personalized, ad-free results with advanced operators and pagination. It also fetches web pages as markdown through the same browser session.
    5
    MIT

  • Google Search MCP Server

    1999AZZAR
    A
    license
    B
    quality
    Not graded
    maintenance
    Provides advanced Google Custom Search functionality, web content extraction, and specialized research tools such as search analytics, multi-site search, and fact checking. Works as an MCP server compatible with any MCP client.
    10
    MIT

  • google-surf-mcp

    tamir-ariunsukh
    A
    license
    A
    quality
    B
    maintenance
    Provides Google search, URL extraction, and academic paper inline extraction without API keys, enabling search and content retrieval from a single MCP server.
    5
    601 npm
    MIT
Deploy Server
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

TDQS

A4.1/5.0

Scored across 7 tools

Disambiguation3/5

Tools have distinguishable roles in principle, but the descriptions spend most of their length telling the agent which sibling NOT to use, which signals genuine overlap: search/search_parallel with extract_mode duplicate extract, and project_memory carries an action=search alias duplicating project_memory_search. The guidance does resolve most cases, but an agent must parse long conditional rules to pick correctly.

Naming Consistency3/5

All names are snake_case, which is consistent at a surface level, but the semantics mix verbs and nouns (extract, health, search vs. project_memory, scholar_search, project_memory_search). The search/search_parallel pair is predictable, yet the overall set doesn't follow one clean verb_noun convention.

Tool Count5/5

Seven tools is well-scoped for a web-discovery plus research-memory server: live search, parallel search, URL extraction, scholarly metadata, project memory read/write, and health each earn a slot. No filler tools and no obvious missing counterpart.

Completeness4/5

The surface covers discovery, ingestion/extraction, citation metadata, durable project memory with retrieval, and diagnostics, which is strong lifecycle coverage. Minor gaps remain around explicit citation/bibliography export and batch URL extraction, though search_parallel's extract_limit largely compensates.

Maintenance

ActivityNo data
ResponsivenessOutdated data

Resources