MCP servers › ai.marketbrew › marketbrew

MCP server · registry snapshot 2026-10-23 · last tested 2026-10-23

ai.marketbrew/marketbrew

Read-only Market Brew search engine modeling and AI visibility data via OAuth. — the publisher's description

1 of 2 record checks metRead-only · tools listed 2026-10-23Topic: search-and-web-data · AI-classifiedversion 1.0.0streamable HTTP70 tools

Summary

ai.marketbrew/marketbrew is a remote MCP server listed in the official MCP registry at version 1.0.0. On 2026-10-23 ProtocolProbe connected to it in read-only mode and read its inventory: 70 tools, 0 resources and 0 prompts.

Record checks

1 of 2 record checks met · 7 do not apply

met: Registry entry is active and says how to run it
not met: Source repository link opens
not applicable: Repository is not archived
not applicable: Code pushed to the repository in the 90 days before our check
not applicable: Repository publishes a security policy (SECURITY.md)
not applicable: Package names its licence with a standard (SPDX) identifier
not applicable: The version the registry lists can be installed and is not withdrawn
not applicable: npm package carries build provenance (attestation)
not applicable: No known critical or high advisory in the package or its dependencies

Not ranked by downloads: a remote server publishes no download figure
Not ranked by stars: no public GitHub repository

From public records, not a safety rating. Each check with its reason

Key facts

Runs: remote (hosted by the publisher)
Transport: streamable HTTP
Sign-in: none needed to open a session
Tools: 70
Described as changing data: 0 of 70 toolsAI-classified
Topic: search-and-web-dataAI-classified
Last tested: 2026-10-23

Add to your client

How fresh this is

Live-tested: yes, a real session (not a text-only review)
Last tested: 2026-10-23
Mode: read-only (no tool calls)
Latest version: 1.0.0, published 2026-10-04 (registry, as of the 2026-10-23 snapshot)
First listed version: 2026-10-04 (earliest version still in the registry; older removed versions would be earlier)
Registry data: snapshot 2026-10-23
Package and repository: checked 2026-10-22
Engine: mcp-runtime-engine@0.1.0 · sdk@1.32.0

Changes since the last refresh

New in the registry: not in the list of 2026-10-04, listed on 2026-10-23 with version 1.0.0 (published 2026-10-04).

Source: the official MCP Registry list on 2026-10-04 and on 2026-10-23.

What it is

What does this server offer?

Observed inventory

70tools

0resources

0prompts

None of its 70 tools are described as changing anything.

get_account_management_snapshotreads or searches
“Use this when the user asks to get the internal account-management snapshot.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
Takes no inputs.
preview_account_management_commandreads or searches
“Use this when an admin asks what an account-management change would do.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
- bodyobjectrequired“Account command to preview without execution.”
check_ask_widget_healthreads or searches
“Use this when the user asks to check Ask Widget availability.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
- askWidgetIdstring or numberrequired
get_ask_chat_sessionreads or searches
“Use this when the user asks to get Ask chat session state.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
2 inputs, 1 required
- askWidgetIdstring or numberrequired
- queryobject“Optional filters: websiteHost (hostname) and conversationId (numeric conversation ID).”
get_ask_conversationreads or searches
“Use this when the user asks to get an Ask conversation.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
2 inputs, 2 required
- askWidgetIdstring or numberrequired
- conversationIdstring or numberrequired
list_ask_conversationsreads or searches
“Use this when the user asks to list Ask conversations.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
2 inputs, 1 required
- askWidgetIdstring or numberrequired
- queryobject“Optional filters: websiteHost (hostname).”
get_ask_widgetreads or searches
“Use this when the user asks to get an Ask Widget.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
- idstring or numberrequired
list_ask_widgetsreads or searches
“Use this when the user asks to list Ask Widgets.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
Takes no inputs.
count_ask_widget_conversationsreads or searches
“Use this when the user asks to count Ask Widget conversations.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input
- queryobject“Optional filters: startDate and endDate as ISO-8601 dates (YYYY-MM-DD).”
lookup_chunk_overlayreads or searches
“Use this when the user asks to look up chunk overlay data for a live URL.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input
- queryobject“Required filter: url (the full live webpage URL).”
count_content_boostersreads or searches
“Use this when the user asks to count Content Boosters.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input
- queryobject“Optional filters: websiteId, serverHost, title, status, sortBy, sortDir, offset, and pageSize.”
get_content_booster_metricsreads or searches
“Use this when the user asks to get Content Booster metrics.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input
- queryobject“Optional filters: websiteId, serverHost, title, status, sortBy, sortDir, offset, and pageSize.”

Show 58 more tools

get_content_boosterreads or searches
“Use this when the user asks to get a Content Booster.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
- idstring or numberrequired
list_content_booster_assetsreads or searches
“Use this when the user asks to list Content Booster assets.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
- idstring or numberrequired
get_content_booster_assetreads or searches
“Use this when the user asks to get a Content Booster asset.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
- assetIdstring or numberrequired
list_content_boostersreads or searches
“Use this when the user asks to list Content Boosters.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input
- queryobject“Optional filters: websiteId, serverHost, title, status, sortBy, sortDir, offset, and pageSize.”
get_current_crewreads or searches
“Use this when the user asks which Market Brew Crew is currently linked or selected.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
Takes no inputs.
count_crewreads or searches
“Use this when the user asks to count visible Crew accounts.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input
- queryobject“Optional filters: customerId, crewIds (comma-separated numeric Crew IDs), websiteId, serverHost, startDate, and endDate.”
list_crew_websitesreads or searches
“Use this when the user asks for current or licensed websites.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input
- queryobject“Optional filters: customerId, crewIds (comma-separated numeric Crew IDs), websiteId, serverHost, startDate, and endDate.”
get_crewon 2 other serversreads or searches
“Use this when the user identifies a specific Crew by business name, email, or numeric ID.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
- crewReferencestring or numberrequired
list_customer_licensesreads or searches
“Use this when the user asks to list customer licenses.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
- crewstring or numberrequired
get_customer_licensereads or searches
“Use this when the user asks to get a customer license.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
2 inputs, 2 required
- crewstring or numberrequired
- licenseIdstring or numberrequired
get_ai_visibility_historyreads or searches
“Use this when the user asks for historical AI mentions or AI search volume for a licensed website, including case-study growth.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
3 inputs, 2 required
- crewstring or numberrequired
- websitestring or numberrequired
- queryobject“Required filter: platform (CHAT_GPT or GOOGLE).”
list_deep_crawl_seedsreads or searches
“Use this when the user asks to list Full Site Intelligence crawl seeds.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
2 inputs, 1 required
- websitestring or numberrequired
- queryobject“Optional filters: active, unresolvedError, responseCode, outcome, url, attemptedAfter, attemptedBefore, minConsecutiveFailures, sort, ascending, offset, and pa…”
get_deep_crawl_seedreads or searches
“Use this when the user asks to get a crawl seed.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
2 inputs, 2 required
- websitestring or numberrequired
- seedIdstring or numberrequired
summarize_deep_crawl_seed_errorsreads or searches
“Use this when the user asks to summarize unresolved crawl seed errors.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
- websitestring or numberrequired
export_deep_crawl_seedsreads or searches
“Use this when the user asks to export crawl seed inventory.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
3 inputs, 1 required
- websitestring or numberrequired
- offsetinteger“Character offset into the export.”
- maxCharsinteger“Maximum export characters to return.”
export_deep_crawl_seed_errorsreads or searches
“Use this when the user asks to export crawl seed error history.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
3 inputs, 1 required
- websitestring or numberrequired
- offsetinteger“Character offset into the export.”
- maxCharsinteger“Maximum export characters to return.”
list_deep_crawl_seed_attemptsreads or searches
“Use this when the user asks to list crawl seed attempt history.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
3 inputs, 2 required
- websitestring or numberrequired
- seedIdstring or numberrequired
- queryobject“Optional filters: offset and pageSize.”
export_deep_crawl_seed_attemptsreads or searches
“Use this when the user asks to export crawl seed attempt history.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
4 inputs, 2 required
- websitestring or numberrequired
- seedIdstring or numberrequired
- offsetinteger“Character offset into the export.”
- maxCharsinteger“Maximum export characters to return.”
list_deep_crawl_inventory_versionsreads or searches
“Use this when the user asks to list retained crawl inventory versions.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
- websitestring or numberrequired
get_deep_crawl_importreads or searches
“Use this when the user asks to get crawl seed import progress.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
2 inputs, 2 required
- websitestring or numberrequired
- importIdstring or numberrequired
get_deep_crawl_schedulereads or searches
“Use this when the user asks to get explicit crawl schedule.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
- websitestring or numberrequired
list_knowledge_basesreads or searches
“Use this when the user asks to list Knowledge Bases.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input
- queryobject“Optional filters: name (partial match), pageSize, and offset.”
count_knowledge_basesreads or searches
“Use this when the user asks to count Knowledge Bases.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
Takes no inputs.
get_knowledge_baseon 1 other serverreads or searches
“Use this when the user asks to get a Knowledge Base.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
- idstring or numberrequired
get_launchpad_statsreads or searches
“Use this when the user asks to get Launchpad content-gap statistics.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input
- queryobject“Optional filters: websiteId or serverHost.”
list_launchpad_keyword_gapsreads or searches
“Use this when the user asks to list Launchpad keyword gaps.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input
- queryobject“Optional filters: websiteId, serverHost, keyword, source, maxSimilarity, sortBy, sortDir, offset, and pageSize.”
list_launchpad_prompt_gapsreads or searches
“Use this when the user asks to list Launchpad prompt gaps.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input
- queryobject“Optional filters: websiteId, serverHost, prompt, source, maxSimilarity, sortBy, sortDir, offset, and pageSize.”
list_license_definitionsreads or searches
“Use this when the user asks to list license definitions.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
Takes no inputs.
get_license_definitionreads or searches
“Use this when the user asks to get a license definition.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
- licenseDefinitionSummarystring or numberrequired
get_license_definition_form_fieldsreads or searches
“Use this when the user asks to get license-definition form fields.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
- licenseDefinitionSummarystring or numberrequired
get_listen_monitorreads or searches
“Use this when the user asks to get a Listen keyword monitor.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
- idstring or numberrequired
count_listen_monitorsreads or searches
“Use this when the user asks to count Listen keyword monitors.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input
- queryobject“Optional filters: websiteId or serverHost.”
list_listen_monitorsreads or searches
“Use this when the user asks to list Listen keyword monitors.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input
- queryobject“Optional filters: websiteId or serverHost.”
list_listen_runsreads or searches
“Use this when the user asks to list runs for a Listen keyword monitor.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
- idstring or numberrequired
list_listen_run_artifactsreads or searches
“Use this when the user asks to list artifacts extracted during a Listen run.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
- runIdstring or numberrequired
get_search_metricsreads or searches
“Use this when the user asks to get Search API metrics.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input
- queryobject“Optional filters: customerId, crewIds (comma-separated numeric Crew IDs), websiteId, serverHost, startDate, and endDate.”
get_search_widget_sessionreads or searches
“Use this when the user asks to get Search Widget session state.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
2 inputs, 1 required
- searchWidgetIdstring or numberrequired
- queryobject“Optional filters: websiteHost (hostname).”
list_search_widget_historyreads or searches
“Use this when the user asks to list Search Widget query history.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
2 inputs, 1 required
- searchWidgetIdstring or numberrequired
- queryobject“Optional filters: websiteHost (hostname).”
get_search_widget_historyreads or searches
“Use this when the user asks to get Search Widget query history detail.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
2 inputs, 2 required
- searchWidgetIdstring or numberrequired
- searchHistoryIdstring or numberrequired
list_taskson 66 other serversreads or searches
“Use this when the user asks to list current Ranking Sensor tasks.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input
- queryobject“Optional filters: websiteId, webpageId, boostFactorId, serverHost, workspaceId, rankingSensorId, snapshotId, startDate, endDate, taskTitle, sortBy, sortDir, of…”
get_taskon 93 other serversreads or searches
“Use this when the user asks to get a Ranking Sensor task.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
- taskIdstring or numberrequired
list_task_childrenreads or searches
“Use this when the user asks to list child tasks.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
2 inputs, 1 required
- taskIdstring or numberrequired
- queryobject“Optional filters: websiteId, webpageId, boostFactorId, serverHost, workspaceId, rankingSensorId, snapshotId, startDate, endDate, taskTitle, sortBy, sortDir, of…”
get_task_historyreads or searches
“Use this when the user asks to get one task's calculation history.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
2 inputs, 1 required
- taskIdstring or numberrequired
- queryobject“Optional filters: websiteId, webpageId, boostFactorId, serverHost, workspaceId, rankingSensorId, snapshotId, startDate, endDate, taskTitle, sortBy, sortDir, of…”
list_task_historyon 1 other serverreads or searches
“Use this when the user asks to list historical Ranking Sensor tasks.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input
- queryobject“Optional filters: websiteId, webpageId, boostFactorId, serverHost, workspaceId, rankingSensorId, snapshotId, startDate, endDate, taskTitle, sortBy, sortDir, of…”
list_top_tasksreads or searches
“Use this when the user asks to list prioritized optimization tasks.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input
- queryobject“Optional filters: websiteId, serverHost, workspaceId, startDate, endDate, taskTitle, sortBy, sortDir, offset, and pageSize.”
get_top_task_metricsreads or searches
“Use this when the user asks to get top-task metrics.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input
- queryobject“Optional filters: websiteId, serverHost, workspaceId, startDate, endDate, taskTitle, sortBy, sortDir, offset, and pageSize.”
get_flight_plan_metricsreads or searches
“Use this when the user asks to get Flight Plan metrics.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input
- queryobject“Optional filters: customerId, crewIds (comma-separated numeric Crew IDs), websiteId, serverHost, startDate, and endDate.”
get_ranking_sensor_metricsreads or searches
“Use this when the user asks to get Ranking Sensor metrics.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input
- queryobject“Optional filters: customerId, crewIds (comma-separated numeric Crew IDs), websiteId, serverHost, startDate, and endDate.”
get_task_metricsreads or searches
“Use this when the user asks to get task workload metrics.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input
- queryobject“Optional filters: customerId, crewIds (comma-separated numeric Crew IDs), websiteId, serverHost, startDate, and endDate.”
get_crawl_metricsreads or searches
“Use this when the user asks to get crawl activity metrics.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input
- queryobject“Optional filters: customerId, crewIds (comma-separated numeric Crew IDs), websiteId, serverHost, startDate, and endDate.”
get_usage_metricson 1 other serverreads or searches
“Use this when the user asks to get aggregate system usage metrics.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input
- queryobject“Optional filters: customerId, crewIds (comma-separated numeric Crew IDs), websiteId, serverHost, startDate, and endDate.”
get_usage_metric_historyreads or searches
“Use this when the user asks to get usage metric history.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input
- queryobject“Optional filters: crewIds (comma-separated numeric Crew IDs), metricKeys, startDate, endDate, and scale (daily or monthly).”
list_usage_reportsreads or searches
“Use this when the user asks to list usage reports.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
Takes no inputs.
get_usage_reporton 2 other serversreads or searches
“Use this when the user asks to get a usage report definition.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
- idstring or numberrequired
get_usage_report_historyreads or searches
“Use this when the user asks to get usage report history.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
2 inputs, 1 required
- idstring or numberrequired
- queryobject“Optional filters: crewIds, startDate, endDate, sectionIds, metricKeys, and scale (daily or monthly).”
dataforseo_backlink_summaryreads or searches
“Use this when a team member asks for a domain's backlink and referring-domain totals.”
Publisher declares: read-only yes · destructive no · idempotent no · open-world yes
1 input, 1 required
- targetstringrequired“Domain or subdomain without a URL scheme or path.”
dataforseo_ranked_keywordsreads or searches
“Use this when a team member asks which Google keywords a domain ranks for.”
Publisher declares: read-only yes · destructive no · idempotent no · open-world yes
4 inputs, 1 required
- targetstringrequired“Domain or subdomain without a URL scheme or path.”
- locationCodeinteger“DataForSEO location code; defaults to United States.”
- languageCodestring“Two-letter language code.”
- limitinteger
dataforseo_google_serpreads or searches
“Use this when a team member asks for current Google search results for a keyword.”
Publisher declares: read-only yes · destructive no · idempotent no · open-world yes
3 inputs, 1 required
- keywordstringrequired
- locationCodeinteger“DataForSEO location code; defaults to United States.”
- languageCodestring“Two-letter language code.”

Each quoted sentence is the first sentence of the publisher’s own description. The kind of tool and the “changes data” mark are our AI model’s reading of that description, not something we tested: two differently worded runs had to agree, otherwise no label is shown, and nobody has checked them by hand. A tool without the “changes data” mark is described as only reading, searching or calculating, or the two runs did not agree. No tool was called. Read the publisher’s full description before relying on it. “Publisher declares” lists the hints the server itself sends with the tool (MCP annotations: read-only, destructive, idempotent, open-world); they are the publisher's claims, not checked by us. Inputs are the parameters in the tool's own input schema: name, declared type, whether it is required, and the first sentence of its description. Read 2026-10-23.

How well are its tools described?

Features #4 and #5

How clearly this server's own tool descriptions say what a tool does, and how consistent its tool list is. The first part is an AI model's yes/no reading of each description; the second part is counted. We do not turn it into a grade.

Descriptions

AI reading of each description

Says what the tool does: 100% of 70 tools
Says what it returns: 100% of 70 tools
States limits, defaults or errors: 1% of 70 tools
Says when to use it: 100% of 70 tools
Items covered per tool: 3.0 of 4 on average

Counted from the listing

Parameters with a description: 51% of 93
Tools with a description: 100% of 70
Typical description length: 130 characters

The tool set

Counted from the listing

Tools: 70
Size of the list: about 13,229 tokens for an agent to load (characters ÷ 4)
Naming: 70 of 70 names use snake_case

AI reading: easy to mix up

No pair found.

The AI items cover 70 of 70 tools: for a tool where two differently worded runs disagreed, that item is left out. They were not checked by hand, and no tool was called. “Easy to mix up” means two tools whose names or descriptions overlap without saying how they differ; the AI found none, comparing tools within groups of 40. We do not rate whether the tool set is complete or whether side effects are spelled out, because our AI reading of those was not reliable enough.

How do I add it to my client?

Config from the registry entry

From the remote endpoint (Streamable HTTP)

We connected to this URL on 2026-10-23 (a read-only session: no tool was called).

Add to CursorAn install link in the format Cursor documents, holding the Cursor config below.

Claude Desktop or claude.ai

Settings → Connectors → Add custom connector, then paste:
https://brew.marketbrew.ai/mcp

Cursor · .cursor/mcp.json in a project, or ~/.cursor/mcp.json

{
  "mcpServers": {
    "marketbrew": {
      "url": "https://brew.marketbrew.ai/mcp"
    }
  }
}

VS Code · .vscode/mcp.json

{
  "servers": {
    "marketbrew": {
      "type": "http",
      "url": "https://brew.marketbrew.ai/mcp"
    }
  }
}

VS Code (command line) · Bash or zsh terminal (macOS, Linux)

code --add-mcp '{"name":"marketbrew","type":"http","url":"https://brew.marketbrew.ai/mcp"}'

Claude Code

claude mcp add --transport http marketbrew https://brew.marketbrew.ai/mcp

Try it in the MCP Inspector · runs on your machine, opens in your browser · Node 22.19+

npx @modelcontextprotocol/inspector@2.11.0 --server-url https://brew.marketbrew.ai/mcp --transport http

The server runs on the operator's infrastructure; it may ask you to sign in when you first connect.
The MCP Inspector lists the server's tools, resources and prompts; a tool you call there runs for real.

Built from the server's registry entry with each client's documented format (checked 2026-10-14; the Cursor link and the VS Code command 2026-10-19; the MCP Inspector command 2026-10-21). Values in < > are yours to fill in; this page never contains a key. Where the server needs a setting the entry does not declare, it can still fail to start.

Does the registry listing match what we found?

Feature #6

The registry verifies a package once, when it is published, and does not re-check it. A difference below is about the listing, not a judgement of the publisher.

Registry says	We found	Result	Source · date
Remote endpoint brew.marketbrew.ai/mcp	Session opened	matches	our test · 2026-10-23
No credential declared as required	Opened a session without any credential	matches	our test · 2026-10-23

Choosing

Record checks

Public records · not a safety rating

1 of 2 record checks met · 7 do not apply

Not ranked by downloads: a remote server publishes no download figure
Not ranked by stars: no public GitHub repository

MetRegistry entry is active and says how to run itActive, with a package or a remote address.
Not metSource repository link opensThe registry entry gives no repository link.
Does not applyRepository is not archivedNo public GitHub repository to read.
Does not applyCode pushed to the repository in the 90 days before our checkNo public GitHub repository to read.
Does not applyRepository publishes a security policy (SECURITY.md)No public GitHub repository to read.
Does not applyPackage names its licence with a standard (SPDX) identifierRemote server: it ships no package.
Does not applyThe version the registry lists can be installed and is not withdrawnRemote server: it ships no package.
Does not applynpm package carries build provenance (attestation)Remote server: it ships no package.
Does not applyNo known critical or high advisory in the package or its dependenciesRemote server: it ships no package.

Read from public records only: the registry entry, npm/PyPI, GitHub and advisory databases, checked 2026-10-22. No tool was called. Only “met” and “not met” are counted, so the total differs between servers; a check that does not apply or that we could not run is listed, never counted against it. It is not a safety rating. How each check works · Leaderboards

Common questions about ai.marketbrew/marketbrew

Answered from the data above

Does ai.marketbrew/marketbrew need an API key or sign-in?

It opened a session without any credential on 2026-10-23. The registry entry declares no required credential; no declaration is not a guarantee.

Has ai.marketbrew/marketbrew been security tested?

Partly. 3 of the 15 checks that apply to it were exercised. We connected and read what the server declares, but did not call its tools: ProtocolProbe calls no server's tools for anything it publishes. This is our choice, not a block by the server. No security verdict is published before verification.

What can ai.marketbrew/marketbrew do?

It lists 70 tools. In our AI model's reading of their descriptions (two runs had to agree, nobody checked it by hand), they include tools that read or search. We did not call any tool, so this describes the text, not the behaviour.

Can ai.marketbrew/marketbrew change or delete data?

None of its 70 tools is described as changing anything (our AI model's reading of the descriptions; nobody checked it by hand). We did not call any tool.

Found this page useful?

Anonymous · no sign-in

A quick, anonymous reaction — no account, no email. One per kind from your browser. The tally updates when the page is next refreshed, and it is only a rough count, never a safety rating or a measured number of people.

Similar servers

Same topic · AI-read

com.browser-use/browser-usealso has tools that reads or searchescompare with this one
io.github.upstash/context7Context7also has tools that reads or searchescompare with this one
io.github.bytedance/mcp-server-browseralso has tools that reads or searchescompare with this one
io.github.screenpipe/screenpipe-mcpscreenpipealso has tools that reads or searchescompare with this one
io.github.KKKKhazix/aihotAIHOTalso has tools that reads or searchescompare with this one
io.github.firecrawl/firecrawl-mcp-serverFirecrawl MCP Serveralso has tools that reads or searchescompare with this one

Active servers whose topic is also “search-and-web-data” and that have at least one tool of the same kind; most kinds in common first, then most GitHub stars. The topic and the tool kinds are an AI model's reading of the publishers' descriptions, not checked by hand. Similar is not a recommendation.

Compare with another server

Side by side: registry entry, our read-only session, the tools and the 18 classification fields. Same values as each page; no score.

Security testing

What did we test, and what did we leave out?

18 checks · features #1, #2

Not probed (we call no server's tools)

We connected and read what the server declares, but did not call its tools: ProtocolProbe calls no server's tools for anything it publishes. This is our choice, not a block by the server. No security score is given; a check we did not run is never counted as passed.

The 18 checks at a glanceour test · 2026-10-23

Inventory: exercised
Hidden instructions: exercised
Real execution: not run · our policy
Secret leak: not run · nothing to check it against
Internal addresses: not run · our policy
Unconfirmed changes: not run · our policy
Bad input: not run · our policy
Model requests: not run · nothing to check it against
Sensitive questions: not run · nothing to check it against
Folder boundary: not run · our policy
Log leaks: not run · nothing to check it against
Hidden content: not run · nothing to check it against
Fake assistant turns: not applicable
Token passthrough: not applicable
Token audience: not applicable
Sign-in redirect: not run · our policy
Consent handling: not testable from outside
Sign-in metadata: exercised

3 exercised12 not run (reason given)3 not applicable

Each check ends in exactly one state: exercised, not run (with the reason), or not applicable (with the reason). 3 of the 15 checks that apply to it were exercised. We do not publish security-check outcomes for named servers.

Exercised · 3

1Inventory
tool-listReads the declared tools, resources and prompts.exercised
2Hidden instructions
description-poisoningLooks for hidden instructions in tool descriptions.exercised
18Sign-in metadata
oauth-url-schemeChecks the published sign-in metadata for unsafe URLs.exercised

Not run, with the reason · 12

3Real execution
real-executionCalls a tool and checks what really happens.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy
4Secret leak
canary-leakPlants a fake secret and checks whether it leaks.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
5Internal addresses
ssrfChecks whether a tool can be steered to internal addresses.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy
6Unconfirmed changes
write-without-confirmationChecks whether tools that change data act without asking.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy
7Bad input
error-handlingSends bad input and watches how the server answers.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy
8Model requests
samplingChecks whether the server asks the client's model to act for it.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
9Sensitive questions
elicitation-sensitive-dataChecks whether the server asks users for sensitive data.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
10Folder boundary
root-boundaryChecks whether the server reaches outside the folders it was given.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy
11Log leaks
logging-side-channelChecks whether log messages carry data they should not.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
12Hidden content
audience-hidingChecks resources that hide content from the user.This check needs content the server returns, and nothing was read or called.not run · nothing to check it against
16Sign-in redirect
open-redirectChecks the sign-in redirect for abuse.Testing the sign-in redirect means sending probes to the operator's sign-in service, which we do not do.not run · our policy
17Consent handling
confused-deputyChecks consent handling when one service acts for another.Depends on the operator's own consent screen, which differs per server and cannot be tested from outside.not testable from outside

Does not apply to this server · 3

13Fake assistant turns
fake-assistant-turnChecks prompts that pose as the assistant's own words.The server exposes no prompts.not applicable
14Token passthrough
token-passthroughChecks whether the server forwards a user's token to other services.The server opened a session without sign-in, so there is no token flow to check.not applicable
15Token audience
token-audience-validationChecks whether tokens meant for another service are accepted.The server opened a session without sign-in, so there is no token flow to check.not applicable

Source: our own test, 2026-10-23, mcp-runtime-engine@0.1.0. Which checks count and why follows our published scoring model.

What happened during the test?

Feature #8

The steps in order, as the test record holds them.

0 msStarted a read-only session with the server's remote endpoint
1,902 msConnected after 0 redirects. No credential was sent or needed.
Read the inventory: 70 tools, 0 resources, 0 prompts.
10,631 msFinished: 3 checks exercised.

Reference

How is it classified?

18 fields

One value per field, each with its source. Fields written by AI models are marked. A field with no value says why.

TopicAI-classified

search-and-web-data

AI-classified · 2026-10-23

Pricing modelAI-classified

no value

The pages we read do not state how the product is priced.

Programming language

does not apply

no existing GitHub repository (server declares no repository link, so there is nothing to fetch)

Hosting type

remote (hosted by the publisher)

registry · 2026-10-23

MCP capability

tools

our test · 2026-10-23

Transport

streamable HTTP

registry · 2026-10-23

Required credentials

none declared

registry · no declaration is not a guarantee

Package registry

does not apply

remote-only server: no package is shipped, so there is no package registry

Freshness

0–30 days

registry updatedAt · 2026-10-23

Lifecycle status

active

registry · 2026-10-23

License class

does not apply

remote-only server: ships no package, so there is nothing to look up in a package registry

Integrity hash

does not apply

remote-only server: ships no package, so there is nothing to look up in a package registry

Signature / provenance

does not apply

remote-only server: ships no package, so there is nothing to look up in a package registry

Dependency advisories

does not apply

ships no package, so there are no dependencies to audit

Popularity

does not apply

remote-only server: ships no package, so there is nothing to look up in a package registry

Publisher signals

not stated

no readable GitHub owner to describe

Maintenance

does not apply

server declares no repository link, so there is nothing to fetch

Environment

the publisher's infrastructure

where it runs, from the hosting type

“Not stated” means the source did not state it; “does not apply” means it does not apply to this kind of server; “our limit” means our own lookup failed. A linked value opens the directory filtered to the same value.

Cite or correct this page

Sources and corrections

Suggested citation

ProtocolProbe. “ai.marketbrew/marketbrew: MCP server record.” Data checked 2026-10-23. https://protocolprobe.com/mcp/servers/ai.marketbrew/marketbrew

Figures are valid for the date shown. Our facts on this page are CC BY 4.0: reuse them with a link and the check date. Quoted text (the publisher’s descriptions, website quotes, tool names) is not ours to license.

As JSON: this record in the API · API documentation.

Badge for your README

[![ProtocolProbe](https://protocolprobe.com/api/v1/badge/ai.marketbrew/marketbrew)](https://protocolprobe.com/mcp/servers/ai.marketbrew/marketbrew)

It shows this server's record-check count: facts from public records, no tool called. It is not a security rating or a pass. It links here and updates after each data reload.

Something wrong, or is this yours?

If a fact here is wrong, tell us and we will re-check it. If you operate this server, you can run our checks on it yourself with the free self-test command; we call no server’s tools ourselves for anything shown here.

Write to hello@protocolprobe.com · corrections log · methodology