Whizbrew MCP
An official MCP server operated by Whizbrew providing access to 901 live marketing data tools. It enables AI agents to retrieve social media profiles, ad library data, app store rankings, and SEO information using a pay-per-call model with no subscription.
Endpoint and access
No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.
https://whizbrew.com/mcpWhat its tools do
10 tools, grouped by the hints the server advertises. Hints are self-declared, not verified behavior.
Can change data (4)
Checks and signals
Each line is separate evidence, not a trust score.
- Passed Endpoint answered the live check ·
- Passed Official MCP Registry namespace is tied to whizbrew.com ·
- Passed Endpoint is on the registry namespace domain ·
- Uptime 100% over 90 days
- Availability 1 of 1 checks passed in 30 days
What you can do with it
- Retrieve TikTok and Instagram social profiles and posts
- Search Meta and TikTok ad libraries for advertiser data
- Get App Store and Google Play rankings and reviews
- Perform SEO and web search for companies and domains
Source and maintenance
Protocol and capabilities
- Server
- whizbrew 0.1.0
- MCP protocol negotiated in check
- 2025-11-25
- Tools
- 10 advertised
- Resources
- Not advertised
- Resource templates
- Not advertised
- Prompts
- Not advertised
{
"tools": {
"listChanged": true
}
}Server-provided instructions
Untrusted server output shown for inspection. It is not Koskamo guidance and is excluded from knowledge search.
Tools
10 advertised
search_tools — Find data tools
Find tools among the 901 marketing data tools of Whizbrew (social profiles, posts and comments, app stores, ad libraries, trends, shops, developer and web data). Ask in plain words, e.g. "tiktok comments of a video". Returns each tool's name, one-line summary, price, group and stats (how often it worked and returned data in real calls of the last 7 days, and its median time). Between equal matches the tool that works more often comes first; a tool our health check found down comes last with its state. Free. Start here.
{
"type": "object",
"properties": {
"group": {
"enum": [
"social",
"appstore",
"ads",
"trends",
"seo",
"dev",
"publishing",
"shops",
"community",
"podcasts",
"music",
"video",
"jobs",
"web",
"email",
"events",
"marketing",
"places",
"company",
"market",
"knowledge",
"software",
"reviews",
"funding",
"raw"
],
"type": "string",
"description": "Only tools of one group"
},
"limit": {
"type": "number",
"default": 8,
"maximum": 25,
"minimum": 1,
"description": "How many tools to return"
},
"query": {
"type": "string",
"description": "What you are looking for, in plain words"
},
"platform": {
"type": "string",
"description": "Only tools of one platform: the part of a tool name before the dot, e.g. tiktok, ig, youtube, appstore"
}
},
"additionalProperties": false
}{
"readOnlyHint": true,
"openWorldHint": false,
"destructiveHint": false
}describe_tools — See how to use tools
The full input schema, output type, price and one example call for 1 to 10 tool names from search_tools. Free.
{
"type": "object",
"required": [
"names"
],
"properties": {
"names": {
"type": "array",
"items": {
"type": "string"
},
"maxItems": 10,
"minItems": 1,
"description": "Tool names, e.g. [\"tiktok.profile\"]"
}
},
"additionalProperties": false
}{
"readOnlyHint": true,
"openWorldHint": false,
"destructiveHint": false
}call_tool — Get data
Runs one catalogue tool that reads data. A call is charged the tool's listed price only when it is a hit (it answered with data). A miss (answered, nothing there) and a failed call are not charged. The answer's meta says which: outcome, price_micros (what was charged) and balance_micros.
{
"type": "object",
"required": [
"tool"
],
"properties": {
"tool": {
"type": "string",
"description": "Tool name from search_tools, e.g. tiktok.profile"
},
"arguments": {
"type": "object",
"description": "The tool's input, as describe_tools shows it"
},
"max_age_s": {
"type": "number",
"description": "Optional. The oldest answer you take, in seconds, for a tool whose repeat calls are answered from the cache (describe_tools shows cache for those). 0 = always read at the source, at the full price. Without it the tool's own maximum age applies; meta.cached, fetched_at and age_s say what you got"
},
"idempotency_key": {
"type": "string",
"description": "Optional. Your own name for this call (up to 200 characters). When a call that was charged is sent again with the same key, tool and arguments within 24 hours, the stored answer comes back free (meta.replay). Use it when you send a call again after a timeout"
},
"max_cost_micros": {
"type": "number",
"description": "Optional. The most this call may cost, in millionths of a dollar (1000000 = $1). A tool priced above it is refused before it runs, free, with its price in the error"
}
},
"additionalProperties": false
}{
"readOnlyHint": true,
"openWorldHint": true,
"destructiveHint": false
}get_balance — Check credit
The prepaid Whizbrew credit of this account.
{
"type": "object",
"properties": {},
"additionalProperties": false
}{
"readOnlyHint": true,
"openWorldHint": false,
"destructiveHint": false
}request_tool — Request missing data
Call this ONLY when search_tools found no tool that fits what the user asked; never when a tool fits. It passes the request to the Whizbrew team, who read every one to see what they can add. Free; no promise and no answer comes back, so tell the user it was passed on and go on by other means. Never put a key or password in it.
{
"type": "object",
"required": [
"request"
],
"properties": {
"request": {
"type": "string",
"description": "What the user asked for, in plain words (up to 1000 characters)"
},
"platform": {
"type": "string",
"description": "The platform or site it is about, if any"
},
"searched": {
"type": "string",
"description": "The search_tools query that found nothing"
}
},
"additionalProperties": false
}{
"readOnlyHint": false,
"openWorldHint": false,
"destructiveHint": false
}report_detour — Report a detour
Call this AFTER you answered when no single tool gave what the user asked and you had to chain several tools, settle for a worse one, or guess (also when you used request_tool and then got there another way). Say what the user wanted, the tools you used instead in order, and why that was worse. The Whizbrew team uses it to add the tool or field that does it in one call. Free; nothing comes back. Never put a key, password or the user's private data in it.
{
"type": "object",
"required": [
"wanted",
"used",
"why"
],
"properties": {
"why": {
"type": "array",
"items": {
"enum": [
"extra_calls",
"missing_fields",
"stale",
"slow",
"had_to_guess",
"partial",
"wrong_data",
"other"
],
"type": "string"
},
"minItems": 1,
"description": "Why that was worse: extra_calls, missing_fields, stale, slow, had_to_guess, partial, wrong_data, other"
},
"used": {
"type": "array",
"items": {
"type": "string"
},
"maxItems": 10,
"minItems": 1,
"description": "The tools you used instead, in the order you called them, e.g. [\"search.web\", \"web.read\"]"
},
"wanted": {
"type": "string",
"description": "What the user asked for, in plain words (up to 500 characters)"
},
"missing": {
"type": "string",
"description": "Optional: what you still could not get"
},
"why_detail": {
"type": "string",
"description": "Optional: a sentence on what was worse"
}
},
"additionalProperties": false
}{
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": false,
"destructiveHint": false
}get_quote — Price a task
A free quote before you spend: which tools do a goal, the calls in order, the price per call and for the quantity you state, and the cash needed beyond the balance. Never spends. The answer ends with `next`: one step you can read to your human.
{
"type": "object",
"required": [
"goal"
],
"properties": {
"goal": {
"type": "string",
"description": "What you want to do, in plain words"
},
"quantity": {
"type": "number",
"default": 1,
"minimum": 1,
"description": "How many calls you expect to make"
},
"budget_usd": {
"type": "number",
"description": "Optional. What your human allows for this task, in US dollars"
}
},
"additionalProperties": false
}{
"readOnlyHint": true,
"openWorldHint": false,
"destructiveHint": false
}start — Where this account stands
Says whether this account is still an agent's (not claimed: it stops after 7 days) or a person's, its balance, and the one next step. An agent without a key starts over HTTP: POST /v1/agent/start (no email). Free.
{
"type": "object",
"properties": {},
"additionalProperties": false
}{
"readOnlyHint": true,
"openWorldHint": false,
"destructiveHint": false
}add_money — Get a card link
Makes a hosted card checkout link for your human to add credit; give them the link, never pay it yourself. With payment_id instead of amount_usd it says how that payment stands (poll every 5 seconds until paid). Making a link is free.
{
"type": "object",
"properties": {
"amount_usd": {
"type": "number",
"description": "How much to add, in US dollars"
},
"payment_id": {
"type": "number",
"description": "A payment made before: answer its status instead of making a link"
}
},
"additionalProperties": false
}{
"readOnlyHint": false,
"openWorldHint": false,
"destructiveHint": false
}claim — Make the account your human's
Two small steps. 1: {email} of your human gives a short link; they open it, confirm the email, and the page shows an 8-letter code. 2: {code} they read to you makes the account theirs for good, with its key and balance. Free.
{
"type": "object",
"properties": {
"code": {
"type": "string",
"description": "Step 2: the 8-letter code the page showed your human"
},
"email": {
"type": "string",
"description": "Step 1: the email that should own the account"
}
},
"additionalProperties": false
}{
"readOnlyHint": false,
"openWorldHint": false,
"destructiveHint": false
}Prompts
Not advertised
Resources
Not advertised
90-day uptime
A lightweight connection check about every six hours, sampled on hosts with many listings. It shows the server answered, not that its tools work.
- 2026-11-19: 4 of 4 checks answered
- 2026-11-20: 3 of 3 checks answered
- 2026-11-21: 4 of 4 checks answered
- 2026-11-22: 1 of 1 checks answered
30-day availability
Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.
- Successful checks
- 1 of 1 (100%)
- Average latency
- 622 ms
- 95th percentile latency
- 622 ms
Maintenance history
Public check and source-refresh events. Editorial and ownership records remain private.
- · probe · passed · 622 ms · metadata changed · 10 tool(s)
Connect from your client
Each snippet registers the same endpoint; pick the client you use.
Claude Code
claude mcp add --transport http whizbrew-mcp https://whizbrew.com/mcpCodex
codex mcp add whizbrew-mcp --url https://whizbrew.com/mcpCursor
{
"mcpServers": {
"whizbrew-mcp": {
"url": "https://whizbrew.com/mcp"
}
}
}Cline
{
"mcpServers": {
"whizbrew-mcp": {
"type": "streamableHttp",
"url": "https://whizbrew.com/mcp",
"disabled": false
}
}
}VS Code
{
"servers": {
"whizbrew-mcp": {
"type": "http",
"url": "https://whizbrew.com/mcp"
}
}
}Gemini CLI
gemini mcp add --transport http whizbrew-mcp https://whizbrew.com/mcpClaude Desktop
https://whizbrew.com/mcpWindsurf
{
"mcpServers": {
"whizbrew-mcp": {
"serverUrl": "https://whizbrew.com/mcp"
}
}
}Let your agent find its tools
Find servers like Whizbrew MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.
Other data and analytics servers
Do you run Whizbrew MCP?
Prove ownership with a DNS record, a well-known file, or your Official MCP Registry entry, and your edits publish immediately. Proofs are re-checked weekly; admins can still hide or remove a listing.