Skip to main content
Glama
ilker-tosun

brave-image-mcp

by ilker-tosun
OverviewSchemaRelated ServersScoreDiscussions
JavaScript
Remote

brave-image-mcp

An MCP (Model Context Protocol) server for Brave Image Search API. Search images directly from AI assistants like Claude.

Author: Ilker Tosun License: MIT

Features

  • search_images — Search images with full filter support (country, language, safesearch, spellcheck)

  • search_images_batch — Run multiple image searches in a single call (up to 10 queries)

  • Returns image URLs, thumbnails, dimensions, source pages, and confidence scores

  • Proper error handling for rate limits, invalid keys, and bad parameters

Related MCP server: Brave Search MCP Server

Requirements

Installation

git clone https://github.com/ilker-tosun/brave-image-mcp.git
cd brave-image-mcp
npm install
npm run build

Configuration

Set your API key as an environment variable:

export BRAVE_API_KEY=your_api_key_here

Or add it to your MCP client config (see below).

Usage with Claude Desktop

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "brave-image-mcp": {
      "command": "node",
      "args": ["/absolute/path/to/brave-image-mcp/dist/index.js"],
      "env": {
        "BRAVE_API_KEY": "your_api_key_here"
      }
    }
  }
}

Usage with n8n (MCP Client Node)

  1. Build the project (npm run build)

  2. In n8n, add an MCP Client node

  3. Set transport to stdio

  4. Command: node /absolute/path/to/brave-image-mcp/dist/index.js

  5. Add environment variable: BRAVE_API_KEY=your_api_key_here

Tools

search_images

Search images for a single query.

Parameter

Type

Required

Description

query

string

✅

Search query (max 400 chars, 50 words)

count

number

❌

Results to return (1–200, default: 20)

country

string

❌

2-letter country code or ALL

search_lang

string

❌

Language code (e.g. en, tr)

safesearch

off | strict

❌

Content filter level

spellcheck

boolean

❌

Enable spell checking (default: true)

search_images_batch

Search images for multiple queries at once.

Parameter

Type

Required

Description

queries

string[]

✅

Array of queries (max 10)

count

number

❌

Results per query (1–200, default: 10)

country

string

❌

2-letter country code or ALL

search_lang

string

❌

Language code

safesearch

off | strict

❌

Content filter level

spellcheck

boolean

❌

Enable spell checking

Rate Limits

Plan

Limit

Free

1 req/sec

Pro

20 req/sec

License

MIT © Ilker Tosun

Available Tools

2 tools
search_imagesB

Search for images using the Brave Image Search API. Returns image URLs, thumbnails, dimensions, source pages, and metadata.

ParametersJSON Schema
NameRequiredDescriptionDefault
countNoNumber of results to return (1–200). Default: 20.
queryYesImage search query. Max 400 characters and 50 words.
countryNo2-letter country code (e.g. 'US', 'TR', 'DE') or 'ALL' for worldwide results.
safesearchNo'strict' filters adult content. 'off' allows it (illegal content always blocked).
spellcheckNoEnable spell checking on the query (default: true). If corrected, altered query is shown in results.
search_langNoLanguage code for search results (e.g. 'en', 'tr', 'de').

TDQS

B3.3/5.0
Behavior3/5

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

With no annotations, the description carries full transparency burden. It discloses the output content (URLs, thumbnails, dimensions, source pages, metadata), which is useful. However, it does not explicitly state that the operation is read-only, nor does it mention any rate limits, restrictions, or other behavioral nuances, so it only partially fulfills the transparency requirement.

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 two sentences, front-loaded with the core purpose, and contains no redundant wording. Every word contributes value, making it appropriately concise and well-structured.

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

Completeness3/5

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

The description explains what the tool does and what it returns, which covers basic usage. However, it lacks any mention of the sibling batch tool, how they relate, or when to choose one over the other. Given the existence of 'search_images_batch', this is a notable gap in contextual completeness.

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?

The input schema has 100% coverage with detailed descriptions for all six parameters. The tool description adds no additional parameter semantic information, so the baseline of 3 is appropriate.

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

Purpose4/5

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

The description clearly states the tool searches for images and lists the return data (URLs, thumbnails, dimensions, source pages, metadata). However, it does not distinguish this tool from its sibling 'search_images_batch', so it misses the full specificity of a 5.

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

Usage Guidelines2/5

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

The description gives no guidance on when to use this tool versus the sibling 'search_images_batch'. There is no mention of alternatives or any situational context, leaving the agent without explicit usage direction.

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

search_images_batchA

Search for images using multiple queries in a single call. Runs queries sequentially and returns combined results. Useful for collecting images across several topics at once.

ParametersJSON Schema
NameRequiredDescriptionDefault
countNoNumber of results per query (1–200). Default: 10.
countryNo2-letter country code or 'ALL'.
queriesYesArray of image search queries (max 10).
safesearchNoContent filter level applied to all queries.
spellcheckNoEnable spell checking on all queries.
search_langNoLanguage code for search results.

TDQS

A4.1/5.0
Behavior4/5

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

No annotations are provided, so the description carries the burden. It discloses that queries run sequentially and results are combined, which are meaningful behavioral traits. It does not discuss error handling or rate limits, but for a read-only search tool this is acceptable.

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 two sentences, front-loaded with the main action, and contains no redundant or filler content.

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

Completeness3/5

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

With no output schema and moderate complexity (6 params), the description explains the core behavior but leaves gaps around return format and partial-failure behavior when multiple queries are involved. The schema covers parameter details, but the tool description could more fully describe expected outputs.

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 description coverage is 100%, with every parameter having a description. The tool description adds no parameter-level detail beyond what the schema already provides, so a baseline of 3 is appropriate.

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 identifies the tool as searching for images using multiple queries in a single call, and explicitly distinguishes it from single-query search by emphasizing batch behavior and combined results.

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?

It states the tool is useful for collecting images across several topics at once, implying batch use. However, it does not explicitly mention when not to use it or directly compare with the sibling search_images tool.

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

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. 2 tool updatesv1.0.0
    • First observedsearch_images
    • First observedsearch_images_batch
Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A3.6/5.0
Disambiguation4/5

The two tools are clearly differentiated by batch vs single query, and descriptions explicitly state this. However, since both are image searches, an agent might initially be unsure which to use without reading carefully.

Naming Consistency5/5

Both tools follow the same verb_noun pattern with a descriptive suffix ('batch' for the multi-query variant). The naming is consistent and predictable.

Tool Count3/5

With only two tools, the server feels thin for a general-purpose image search API. While the scope is narrow, a single search tool with a batch flag could have sufficed, making the current count borderline.

Completeness4/5

The core search capability is well covered, including a batch mode for multiple queries. Minor gaps exist, such as missing pagination or filtering options, but for an image search server the essential operations are present.

Maintenance

ActivityInactive
ResponsivenessNo issues

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

  • Brave Search MCP Server

    Shoofio
    A
    license
    Not graded
    quality
    F
    maintenance
    An MCP server that integrates the Brave Search API to provide both web and local search capabilities, with features like pagination, filtering, and smart fallbacks.
    16
    MIT

  • Brave Search MCP

    mikechao
    A
    license
    A
    quality
    D
    maintenance
    An MCP Server implementation that integrates the Brave Search API, providing, Web Search, Local Points of Interest Search, Image Search, Video Search, News Search and LLM Context Search capabilities
    5
    259
    125
    GPL 3.0

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/ilker-tosun/brave-image-mcp'

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