Summary
Connects Claude to Brave's independent search index, letting you query web results without relying on Google or Bing infrastructure. Part of the Pipeworx gateway ecosystem, which bundles 250+ data sources behind a single MCP endpoint. You can either add just the Brave Search server or connect to the full Pipeworx gateway for broader access. Supports streamable HTTP transport and includes an ask_pipeworx tool that lets you make natural language queries instead of calling specific tool names. Useful when you need fresh web search capabilities and want to avoid the major search duopoly, or when you're already using Pipeworx for other integrations.
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →Tools
Public tool metadata for what this MCP can expose to an agent.
8 tools
brave_web_searchPerforms web searches using the Brave Search API and returns comprehensive search results with rich metadata. To chain into local-POI enrichment, pass `result_filter=locations` and feed the resulting `locations.results[].id` values into `brave_local_search`. To chain into the...15 params
Performs web searches using the Brave Search API and returns comprehensive search results with rich metadata. To chain into local-POI enrichment, pass `result_filter=locations` and feed the resulting `locations.results[].id` values into `brave_local_search`. To chain into the...
Parameters* required
countintegerNumber of results to return (max 20; default 20).default: 20
countrystring2-letter country code (ISO 3166-1 alpha-2). Defaults to US.default: US
extra_snippetsbooleanReturn up to 5 extra alternate snippets per result. Premium plans only.
freshnessstringFilter results by recency. Use pd (past day), pw (past week), pm (past month), py (past year), or a YYYY-MM-DDtoYYYY-MM-DD range.
goggles_idstringGoggles ID for re-ranked results. See https://search.brave.com/help/goggles.
offsetintegerPagination offset (max 9, in units of `count`).default: 0
qstringSearch query (max 400 characters and 50 words).
result_filterstringComma-separated list of result types to include. Available values: discussions, faq, infobox, news, query, summarizer, videos, web, locations. Use `locations` to chain into `brave_local_pois`.
safesearchstringFilter level for adult content.one of
off · moderate · strictdefault: moderatesearch_langstring2-letter language code for the search. Defaults to en.default: en
spellcheckbooleanWhether to spellcheck the query.default: true
summarybooleanSet to true to request a summarizer key in the response. Pair with `brave_summarizer` to fetch the AI-generated summary text. Pro AI tier required.
text_decorationsbooleanWhether to include decoration markers (e.g. highlighting) in result strings.default: true
ui_langstringUser interface language for the response, in the form <lang>-<country> (e.g. en-US).default: en-US
unitsstringMeasurement system used in result content.one of
metric · imperialbrave_news_searchSearches for news articles using Brave's News Search API. Use it when you need current news, breaking updates, or articles about specific topics.10 params
Searches for news articles using Brave's News Search API. Use it when you need current news, breaking updates, or articles about specific topics.
Parameters* required
countintegerNumber of results to return (max 20; default 20).default: 20
countrystring2-letter country code (ISO 3166-1 alpha-2). Defaults to US.default: US
freshnessstringFilter results by recency. Use pd (past day), pw (past week), pm (past month), py (past year), or a YYYY-MM-DDtoYYYY-MM-DD range.
offsetintegerPagination offset (max 9, in units of `count`).default: 0
qstringSearch query (max 400 characters and 50 words).
safesearchstringFilter level for adult content.one of
off · moderate · strictdefault: moderatesearch_langstring2-letter language code for the search. Defaults to en.default: en
spellcheckbooleanWhether to spellcheck the query.default: true
text_decorationsbooleanWhether to include decoration markers (e.g. highlighting) in result strings.default: true
ui_langstringUser interface language for the response, in the form <lang>-<country> (e.g. en-US).default: en-US
brave_image_searchPerforms an image search using the Brave Search API. Helpful when you need pictures of people, places, things, graphic-design ideas, or art inspiration. Counts of up to 100 are supported.6 params
Performs an image search using the Brave Search API. Helpful when you need pictures of people, places, things, graphic-design ideas, or art inspiration. Counts of up to 100 are supported.
Parameters* required
countintegerNumber of results (max 100; default 50).
countrystring2-letter country code (ISO 3166-1 alpha-2). Defaults to US.default: US
qstringSearch query (max 400 characters and 50 words).
safesearchstringFilter level for adult content.one of
off · moderate · strictdefault: moderatesearch_langstring2-letter language code for the search. Defaults to en.default: en
spellcheckbooleanWhether to spellcheck the query.default: true
brave_video_searchSearches for videos using Brave's Video Search API. Returns structured video results with metadata.9 params
Searches for videos using Brave's Video Search API. Returns structured video results with metadata.
Parameters* required
countintegerNumber of results to return (max 20; default 20).default: 20
countrystring2-letter country code (ISO 3166-1 alpha-2). Defaults to US.default: US
freshnessstringFilter results by recency. Use pd (past day), pw (past week), pm (past month), py (past year), or a YYYY-MM-DDtoYYYY-MM-DD range.
offsetintegerPagination offset (max 9, in units of `count`).default: 0
qstringSearch query (max 400 characters and 50 words).
safesearchstringFilter level for adult content.one of
off · moderate · strictdefault: moderatesearch_langstring2-letter language code for the search. Defaults to en.default: en
spellcheckbooleanWhether to spellcheck the query.default: true
ui_langstringUser interface language for the response, in the form <lang>-<country> (e.g. en-US).default: en-US
brave_local_searchBrave Local Search API returns enriched information (address, phone, hours, rating) for location-search results. Access requires the Brave Search API Pro plan; currently US-only. Two-step flow: first call `brave_web_search` with `result_filter=locations` to obtain `locations.r...4 params
Brave Local Search API returns enriched information (address, phone, hours, rating) for location-search results. Access requires the Brave Search API Pro plan; currently US-only. Two-step flow: first call `brave_web_search` with `result_filter=locations` to obtain `locations.r...
Parameters* required
idsarrayOne or more location IDs returned by a prior `brave_web_search` with `result_filter=locations`. Up to 20 IDs per call.
search_langstring2-letter language code for the search. Defaults to en.default: en
ui_langstringUser interface language for the response, in the form <lang>-<country> (e.g. en-US).default: en-US
unitsstringMeasurement system.one of
metric · imperialbrave_llm_contextRetrieves pre-extracted, relevance-ranked web content using Brave's LLM Context API, optimized for AI agents, LLM grounding, and RAG pipelines. Unlike a traditional web search that returns links and short descriptions, this tool returns the actual substance of matching pages —...14 params
Retrieves pre-extracted, relevance-ranked web content using Brave's LLM Context API, optimized for AI agents, LLM grounding, and RAG pipelines. Unlike a traditional web search that returns links and short descriptions, this tool returns the actual substance of matching pages —...
Parameters* required
context_threshold_modestringMode used to determine the inclusion threshold for content.one of
disabled · strict · lenient · balanceddefault: balancedcountintegerMaximum number of search results considered to select the LLM context data. Default 20, max 50.default: 20
countrystring2-letter country code (ISO 3166-1 alpha-2). Defaults to US.default: US
enable_localbooleanWhether to enable local recall.
enable_source_metadatabooleanEnable source metadata enrichment (site_name, favicon) in the sources attribute.
freshnessstringFilter results by recency. Use pd, pw, pm, py, or YYYY-MM-DDtoYYYY-MM-DD.
maximum_number_of_snippetsintegerMaximum number of snippets (chunks of text) to include in LLM context. Default 50, max 256.default: 50
maximum_number_of_snippets_per_urlintegerMaximum number of snippets to include per URL. Default 50, max 100.default: 50
maximum_number_of_tokensintegerApproximate maximum number of tokens to include in context. Default 8192, max 32768.default: 8192
maximum_number_of_tokens_per_urlintegerMaximum number of tokens to include per URL. Default 4096, max 8192.default: 4096
maximum_number_of_urlsintegerMaximum number of different URLs to include in LLM context.
querystringThe user's search query. Max 400 characters and 50 words.
search_langstring2-letter language code for the search. Defaults to en.default: en
spellcheckbooleanWhether to spellcheck the query.default: true
brave_place_searchSearches Brave's Place Search API. A single call may populate any combination of `results` (POIs), `cities`, `addresses`, `streets`, and `location` (the resolved search area), depending on the query shape. Use for POIs near coordinates or a named area, browsing general POIs (o...13 params
Searches Brave's Place Search API. A single call may populate any combination of `results` (POIs), `cities`, `addresses`, `streets`, and `location` (the resolved search area), depending on the query shape. Use for POIs near coordinates or a named area, browsing general POIs (o...
Parameters* required
countintegerNumber of results (max 50, default 20).default: 20
countrystring2-letter country code (ISO 3166-1 alpha-2). Defaults to US.default: US
geolocstringOptional geolocation token used to refine results.
latitudenumberLatitude of the geographical coordinates to search around (-90 to 90). Typically paired with `longitude`.
locationstringLocation string used as an alternative to lat/long. US: '<city> <state> <country>' (e.g. 'san francisco ca united states'). Non-US: '<city> <country>' (e.g. 'tokyo japan'). Capitalization and comma...
longitudenumberLongitude of the geographical coordinates to search around (-180 to 180). Typically paired with `latitude`.
querystringQuery string. Shape influences the response: POI-like queries return `results`; ambiguous city names return `cities`; address-/street-shaped queries with a geographic anchor return `addresses` and/...
radiusnumberBias toward results closer to the supplied coordinates, in meters. NOT a hard cutoff.
safesearchstringFilter level for adult content.one of
off · moderate · strictdefault: moderatesearch_langstring2-letter language code for the search. Defaults to en.default: en
spellcheckbooleanWhether to spellcheck the query.default: true
ui_langstringUser interface language for the response, in the form <lang>-<country> (e.g. en-US).default: en-US
unitsstringUnits of measurement for distance values.one of
metric · imperialdefault: metricbrave_summarizerRetrieves AI-generated summaries of web search results. Two-step flow: first call `brave_web_search` with `summary=true` to obtain `summarizer.key`, then pass it here. Pro AI tier required.2 params
Retrieves AI-generated summaries of web search results. Two-step flow: first call `brave_web_search` with `summary=true` to obtain `summarizer.key`, then pass it here. Pro AI tier required.
Parameters* required
entity_infobooleanWhether to include extra entity-info fields with citation metadata.
keystringSummarizer key returned by a prior `brave_web_search` with `summary=true`.
@pipeworx/brave-search
Brave Search MCP — independent web index with AI-friendly licensing.
Part of Pipeworx — an MCP gateway connecting AI agents to 1476+ live data sources.
Tools
web_search(q, count?, offset?, country?, search_lang?, safesearch?, freshness?)news_search(q, count?, offset?, country?, search_lang?, freshness?)
Auth
- Platform key: gateway env
PLATFORM_BRAVE_KEY. - BYO:
?_apiKey=<key>after registering at https://brave.com/search/api/ (free 2k/mo, 1 req/sec).
Data source
https://api.search.brave.com/res/v1/ — header X-Subscription-Token.
Quick Start
Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
{
"mcpServers": {
"brave-search": {
"url": "https://gateway.pipeworx.io/brave-search/mcp"
}
}
}
What this endpoint actually serves
tools/list at https://gateway.pipeworx.io/brave-search/mcp returns the tools in the table
above plus the shared Pipeworx meta-tools — ask_pipeworx,
discover_tools, search_within, remember/recall and the rest of the
gateway-wide set. So the tool count you see is larger than this table: a
single-pack endpoint currently lists roughly 30 shared tools alongside the
pack's own. The connection's initialize response states its exact scope, and
is the authoritative answer for a given day.
This is deliberate, not multiplexing by accident. The meta-tools are what let a
scoped connection answer a question this pack does not cover — via
ask_pipeworx, which routes across the whole catalog — without you adding a
second MCP server. There is currently no way to mount a pack endpoint without
them; if the extra schemas cost you more context than the routing is worth,
connect to the full gateway once rather than to several pack endpoints.
Or connect to the full Pipeworx gateway to get every pack's tools listed directly, instead of just this one's:
{
"mcpServers": {
"pipeworx": {
"url": "https://gateway.pipeworx.io/mcp"
}
}
}
Both URLs reach the same gateway and the same 1476+ data sources. The
only difference is which pack's tools are listed directly; ask_pipeworx
reaches all of them from either one.
Using with ask_pipeworx
Instead of calling tools directly, you can ask questions in plain English — this works on the pack endpoint above as well as on the full gateway:
ask_pipeworx({ question: "your question about Brave Search data" })
The gateway picks the right tool and fills the arguments automatically.
More
License
MIT
Featured
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
