Searchport

io.github.CloudCorpRecordsPublished by GitHub account CloudCorpRecordsv0.1.0Updated Nov 7, 2026

Web, local, news, image, and video search through the Brave Search API.

VerifiedSTDIODesktop onlyLocation & Lifestyle Web Search & Scraping

Server details

Identifier: io.github.CloudCorpRecords/searchport
Transport: STDIO
Runtime: Desktop only
Trust: Verified
Published: Oct 31, 2026

Security note

MCP servers receive tool arguments from a conversation and may perform external actions. Review what a server can do before you enable it, and give it only the access it needs.

The registry verified the GitHub account CloudCorpRecords for this listing. That does not show the account is the product's maker.

SourceWeft's checks cover whether the listing is complete and the endpoint answered; they do not review the server's code or what its tools do.

Add a badge to your README

Show readers this MCP server is listed on SourceWeft. The badge links to this page.

[![Listed on SourceWeft](https://sourceweft.com/badge/mcp/io.github.CloudCorpRecords%2Fsearchport.svg)](https://sourceweft.com/mcp/io.github.CloudCorpRecords%2Fsearchport?utm_source=readme&utm_medium=badge)

Overview

AI-generated overview

Searchport gives an assistant five Brave Search tools — web, local, news, image and video search — through a local stdio MCP server.

What you can do: Search the general web index and get titles, links and excerpts
Find nearby businesses and places with address, phone and rating details
Look up current news stories with sources, summaries and story age
Find images with source pages and direct image links
Find videos with descriptions, durations and sources
When to use it: Use it when an assistant needs live web, news, local business, image or video results and you already have a Brave Search API subscription. It is a single, uniform way to cover all five search kinds from one server.
Requirements: A Brave Search API subscription key supplied in the BRAVE_API_KEY environment variable; the key is sent to the API as the X-Subscription-Token header. Runs locally via npx (Node.js) or the Docker image, and needs network access to the Brave Search API. Desktop only.

Before you install

Requires a paid Brave Search API subscription key; searches fail without BRAVE_API_KEY. Queries and results are sent to the Brave Search API, a third party. The server only reads search results and does not write or delete data.

Installation

In SourceWeft

Open Searchport in the dashboard and add it to a workspace.
Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

searchport

searchport is one doorway to five kinds of Brave search. A single question can be asked against the general web index, local business listings, current news, images, or videos, and every answer comes back in the same shape: a title, the address it lives at, a short excerpt, and one extra line of detail that fits the kind — how long ago a story ran, how long a video plays, where a shop is and how it is rated. It runs from the command line or as an MCP server for agents.

A Brave Search API subscription key is required. Put it in the BRAVE_API_KEY environment variable; the key is sent to the API as the X-Subscription-Token header and never appears in output. When the variable is missing, every search fails with an error that names it.

Install

Or run the container image:

The container defaults to the MCP server (see below). Pass CLI arguments to use it as a CLI instead.

CLI

bash

export BRAVE_API_KEY="your subscription key"
# General web search; --count is results per page (max 20),# --offset pages forward (max 9)searchport web "composting basics"searchport web "composting basics" --count 5 --offset 1
# The other four kinds take the same query and --countsearchport local "bakery near the mission" --count 5searchport news "trail network vote"searchport images "ridge sunrise"searchport videos "trail running form"
# Machine-readable output for any kindsearchport web "composting basics" --json
searchport --version

export BRAVE_API_KEY="your subscription key"
# General web search; --count is results per page (max 20),# --offset pages forward (max 9)searchport web "composting basics"searchport web "composting basics" --count 5 --offset 1
# The other four kinds take the same query and --countsearchport local "bakery near the mission" --count 5searchport news "trail network vote"searchport images "ridge sunrise"searchport videos "trail running form"
# Machine-readable output for any kindsearchport web "composting basics" --json
searchport --version

Exit codes: 0 on success, 1 when a search fails (including a missing BRAVE_API_KEY or an API error), 2 for usage errors.

MCP server

One bin serves both faces. The mcp subcommand starts a stdio MCP server:

MCP client configuration:

json

{  "mcpServers": {    "searchport": {      "command": "npx",      "args": ["-y", "@reneturcios/searchport", "mcp"],      "env": { "BRAVE_API_KEY": "your subscription key" }    }  }}

{  "mcpServers": {    "searchport": {      "command": "npx",      "args": ["-y", "@reneturcios/searchport", "mcp"],      "env": { "BRAVE_API_KEY": "your subscription key" }    }  }}

Tools

Tool	Input	What it returns
`brave_web_search`	`query` (string, required), `count` (number, optional), `offset` (number, optional)	Web results as a numbered text block: title, URL, and excerpt per result.
`brave_local_search`	`query` (string, required), `count` (number, optional)	Local listings: name, URL, and a detail line with address, phone, and rating when the API provides them.
`brave_news_search`	`query` (string, required), `count` (number, optional)	News stories: headline, URL, summary, and the story's age.
`brave_image_search`	`query` (string, required), `count` (number, optional)	Image results: title, source page URL, and the direct image URL.
`brave_video_search`	`query` (string, required), `count` (number, optional)	Video results: title, URL, description, and duration.

Counts are clamped to the API's per-page limit of 20 and offsets to its maximum of 9. An empty result set is reported as such, not as an error; a missing key or a failed API call is reported as a tool error.

Development

bash

npm installnpm run build   # tsc -> dist/npm test        # node test runner over test/*.test.ts, no network (fake fetch fixtures)npm run dev     # run the CLI from source via tsx

npm installnpm run build   # tsc -> dist/npm test        # node test runner over test/*.test.ts, no network (fake fetch fixtures)npm run dev     # run the CLI from source via tsx

License

MIT — see LICENSE.

Source: README.md at commit 197c7f3

Tools

brave_web_search

Run a general web search and return matching pages with titles, links, and excerpts.

Parameterscountqueryrequiredoffset

brave_local_search

Search for nearby businesses and places and return their listing details.

Parameterscountqueryrequired

brave_news_search

Search current news coverage and return matching stories with sources and summaries.

Parameterscountqueryrequired

brave_image_search

Search for images matching a query and return image results with source pages.

Parameterscountqueryrequired

brave_video_search

Search for videos matching a query and return video results with durations and sources.

Parameterscountqueryrequired

Version history

v0.1.0LatestOct 31, 2026

Score

90% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

Reached in the last 30 days25 pts
Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
Tools listedRequired15 pts
DescriptionRequired15 pts
Logo10 pts
Documentation15 pts
License10 pts