Skip to main content
Glama
khoaofgod

websearch-mcp

by khoaofgod
OverviewSchemaRelated ServersScoreDiscussions
TypeScript
Local

websearch-mcp

An MCP server that hooks into Claude Code and answers queries with full page content, not just snippets.

Flow when Claude calls the websearch tool:

Claude: websearch("PHP send email class")
  → 1. SearXNG search   → top N result URLs (title + url + snippet)
  → 2. BrowserOS        → open each URL as a background tab, read body text (no HTML)
  → 3. fallback         → Playwright (headless Chromium) if present, else plain HTTP fetch
  → 4. return           → [{title, url, text}] back to Claude

"10 tabs at a time": BrowserOS opens up to WEBSEARCH_RESULTS background tabs in one batch and reads them in parallel. Any page that fails (blocked, DNS, 404) is skipped gracefully and reported, with a per-page fallback to Playwright/curl.

Setup

npm install
npm run build

Node 18+. Playwright is optional — if globally installed (npm root -g) the fallback picks it up automatically; otherwise it silently uses plain HTTP fetch.

Related MCP server: SearxNG MCP Server

Register in Claude Code

In the project you want to use it from, copy the template and set your absolute path:

cp .mcp.json.example .mcp.json   # then edit <YOUR_CLONE_DIR>
{
  "mcpServers": {
    "websearch": {
      "command": "node",
      "args": ["<YOUR_CLONE_DIR>/dist/index.js"],
      "env": { "WEBSEARCH_SEARXNG_URL": "http://100.77.7.3:8890/search", "WEBSEARCH_BROWSEROS_URL": "http://127.0.0.1:9002/mcp" }
    }
  }
}

.mcp.json holds a machine-specific absolute path, so it's gitignored here — don't commit it. Configure per-machine from the .mcp.json.example template.

Then in a Claude Code session ask anything, e.g. "Search PHP send email class and summarize the top 3 results."

Config (env vars)

All config is via env vars in the MCP server entry — no code changes to move endpoints.

Var

Default

Meaning

WEBSEARCH_SEARXNG_URL

http://100.77.7.3:8890/search

SearXNG endpoint (JSON format auto-appended)

WEBSEARCH_BROWSEROS_URL

http://127.0.0.1:9002/mcp

BrowserOS MCP (streamable HTTP)

WEBSEARCH_RESULTS

10

Top N results to fetch full text for (max 12)

WEBSEARCH_MAX_PAGE_CHARS

8000

Truncate each page's text to this many chars (context budget)

WEBSEARCH_PAGE_TIMEOUT_MS

25000

Per-page read/navigation timeout

WEBSEARCH_USE_BROWSEROS

1

Use BrowserOS batch extraction

WEBSEARCH_USE_PLAYWRIGHT

1

Fall back to headless Chromium

WEBSEARCH_USE_CURL

1

Last fallback: plain HTTP fetch

Set WEBSEARCH_USE_BROWSEROS=0 to force the Playwright/curl path.

Tool

  • websearch(query, n?) — query string, n = how many top results to read (default WEBSEARCH_RESULTS). Returns JSON: { query, results: [{ title, url, text, source, error? }] }. source is browseros / playwright / curl; error present on failures (e.g. bot-blocked).

Layout

src/
  index.ts               MCP stdio server + websearch tool
  config.ts              env-var config
  searxng.ts             SearXNG JSON search
  text.ts                html-strip / squash / bot-block heuristics
  extraction/
    extractor.ts         orchestrates BrowserOS → playwright → curl
    browseros.ts         MCP *client* to BrowserOS (tabs new/list, read, close)
    playwright.ts        headless Chromium fallback (auto-resolves global install)
    curl.ts              realistic-browser HTTP fetch + cheerio text extraction

Available Tools

1 tool
websearchA

Search the web (SearXNG) and return the full body text of the top N results. Pages are loaded in parallel via BrowserOS, falling back to headless Chromium (Playwright) then plain HTTP fetch. Returns each result as {title, url, text}.

ParametersJSON Schema
NameRequiredDescriptionDefault
nNoHow many top results to fetch full text for (default: WEBSEARCH_RESULTS).
queryYesThe search query, e.g. "PHP send email class".

TDQS

A4.3/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It discloses that pages are loaded in parallel via BrowserOS with fallback to headless Chromium and plain HTTP fetch, and specifies the output format. This gives useful insight into performance and reliability, though it omits potential failure modes or error handling.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is three sentences, front-loaded with the core purpose, followed by implementation details and return format. Every sentence adds value; there is no redundant information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool has moderate complexity, no output schema, and no annotations. The description covers the return format, parallelism, and fallback chain, making it sufficiently complete for an agent to know what to expect. It could mention potential latency, but the core behavior is well specified.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, with both 'query' and 'n' described in the schema. The description adds little beyond the schema, as it only contextualizes 'n' as the count of top results. A baseline of 3 is appropriate because the schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states that this tool searches the web via SearXNG and returns the full body text of the top N results. The verb 'search' and resource 'the web' are specific, and the output structure is defined. Though no sibling tools exist, the description would distinguish it from other search variants.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear context: this is a web search tool that fetches full text for results. It does not explicitly state when to use it over alternatives, but with no sibling tools listed, this is a minor gap. There are no exclusions or prerequisites mentioned.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A4.3/5.0
Disambiguation5/5

Only one tool exists, so there is no possibility of confusing it with another. The tool's purpose is clearly defined as web search, with a detailed description of behavior.

Naming Consistency5/5

With a single tool named 'websearch', there is no inconsistency or mixed conventions. The name is descriptive and matches the server's purpose.

Tool Count3/5

The server has only one tool, which is borderline thin. However, for a focused web search server, a single tool can be appropriate, though it lacks the breadth of a multi-tool search suite.

Completeness4/5

The tool covers the core web search workflow, including fetching top results and body text. Minor gaps may exist such as advanced filtering options, but the essential functionality is present.

Maintenance

ActivityMaintained
ResponsivenessSyncing

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

  • SearxNG MCP Server

    Sacode
    A
    license
    B
    quality
    C
    maintenance
    Provides web search capabilities using SearxNG, allowing AI assistants like Claude to search the web with a privacy-respecting metasearch engine.
    1
    11
    MIT

  • Web Search MCP Server

    mrkrsl
    A
    license
    Not graded
    quality
    D
    maintenance
    Enables comprehensive web searching and content extraction using multiple search engines (Bing, Brave, DuckDuckGo) without API keys. Provides tools for full web searches with content extraction, quick search summaries, and single webpage content retrieval.
    1,119
    MIT

  • web-search-mcp

    Backerss
    F
    license
    Not graded
    quality
    C
    maintenance
    Provides free web search, content fetching, image search, and deep research via SearXNG, no API keys required.

Appeared in Searches

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/khoaofgod/searXNG-WebSearchMCP'

If you have feedback or need assistance with the MCP directory API, please join our Discord server