ai.keenable/web-search (MCP Server)

This MCP server provides live web search and clean-markdown page fetch over the Keenable web index. It is hosted at a Streamable HTTP endpoint and exposes two tools for discovering web pages and retrieving their content in a cleaned markdown form. Tool availability and hosting details are defined in the server readme excerpt.

🛠️ Key Features

Live web search over the Keenable web index
Clean-markdown page fetch
Hosted endpoint: https://api.keenable.ai/mcp
Tools: search_web_pages, fetch_page_content
Keyless by default: 1,000 requests/hour; optional API key lifts the cap

🚀 Use Cases

Search for relevant web pages using search_web_pages
Fetch and process page content using fetch_page_content
Use from clients that connect to the hosted MCP endpoint URL

⚡ Developer Benefits

Hosted server simplifies client setup by pointing to the URL
Thin npm wrapper (@keenable/mcp) exists for stdio command integrations

⚠️ Limitations

Keyless usage is rate-limited to 1,000 requests/hour
Optional API key is required to lift the cap

Keenable MCP

MCP server for live web search and clean-markdown page fetch over the Keenable web index.

Hosted endpoint: https://api.keenable.ai/mcp (Streamable HTTP)
Tools: search_web_pages, fetch_page_content
Keyless by default (1,000 requests/hour). An optional API key lifts the cap.

The server is hosted, so most clients just point at the URL. For clients (or config paths) that only accept a stdio command there is a thin npm wrapper (@keenable/mcp) that bridges to the same endpoint.

Tools

Tool	Description
`search_web_pages`	Live web search. Args: `query` (required), plus optional `mode`, `site`, `published_after` / `published_before`, `acquired_after` / `acquired_before`.
`fetch_page_content`	Fetch a URL and return clean markdown. Args: `url` (required), optional `max_chars` (default 50000).

Use it

Remote (recommended)

Clients with remote MCP support — Cursor, Cline, VS Code, and Claude Desktop's Custom Connectors UI — connect to the URL directly:

json

{
  "mcpServers": {
    "keenable": {
      "type": "streamable-http",
      "url": "https://api.keenable.ai/mcp"
    }
  }
}

Stdio (e.g. Claude Desktop's `claude_desktop_config.json`)

For clients or config paths that only accept a stdio command, run the wrapper with npx:

json

{
  "mcpServers": {
    "keenable": {
      "command": "npx",
      "args": ["-y", "@keenable/mcp"]
    }
  }
}

That is all you need for keyless use.

API key (optional)

Keenable is keyless by default. To lift the hourly rate limit, pass a key.

Remote:

json

{
  "mcpServers": {
    "keenable": {
      "type": "streamable-http",
      "url": "https://api.keenable.ai/mcp",
      "headers": { "X-API-Key": "YOUR_KEY" }
    }
  }
}

Stdio:

json

{
  "mcpServers": {
    "keenable": {
      "command": "npx",
      "args": ["-y", "@keenable/mcp"],
      "env": { "KEENABLE_API_KEY": "YOUR_KEY" }
    }
  }
}

How the wrapper works

@keenable/mcp is a small stdio bridge: it connects to the hosted server over Streamable HTTP and forwards every tool the server exposes. There is no search logic in this package; the index and tools live behind https://api.keenable.ai/mcp. Environment variables:

KEENABLE_API_KEY — optional API key, sent as X-API-Key.
KEENABLE_MCP_URL — override the endpoint (defaults to https://api.keenable.ai/mcp).

License

MIT

query	string	required	Natural language search query. Should be a semantically rich description of the ideal page, not just keywords.
site	string	optional	Restrict results to a specific site (e.g. "techcrunch.com")
acquired_after	string	optional	Filter results to pages acquired/indexed after this date (YYYY-MM-DD)
acquired_before	string	optional	Filter results to pages acquired/indexed before this date (YYYY-MM-DD)
published_after	string	optional	Filter results to pages published after this date (YYYY-MM-DD)
published_before	string	optional	Filter results to pages published before this date (YYYY-MM-DD)
snippet_max_length	integer	optional	Maximum length (characters) of the snippet returned per result. When omitted, a default length is used.
mode	string	optional	Search mode: 'pro' (default) for enhanced results

ai.keenable/web-search

ai.keenable/web-search (MCP Server)

🛠️ Key Features

🚀 Use Cases

⚡ Developer Benefits

⚠️ Limitations

Topics

search_web_pages

fetch_page_content

Keenable MCP

Tools

Use it

Remote (recommended)

Stdio (e.g. Claude Desktop's `claude_desktop_config.json`)

API key (optional)

How the wrapper works

Links

License

Install

Configuration

Related servers

url	string	required	The URL to fetch. Example: "https://example.com"
max_chars	integer	optional	Maximum number of characters of content to return. Longer content is truncated. Defaults to 50000 when omitted.
live	boolean	optional	Fetch live content. Defaults to false.

ai.keenable/web-search (MCP Server)

🛠️ Key Features

🚀 Use Cases

⚡ Developer Benefits

⚠️ Limitations

Topics

search_web_pages

fetch_page_content

Keenable MCP

Tools

Use it

Remote (recommended)

Stdio (e.g. Claude Desktop's claude_desktop_config.json)

API key (optional)

How the wrapper works

Links

License

Install

Configuration

Related servers

Stdio (e.g. Claude Desktop's `claude_desktop_config.json`)