About TGGET Niche Research
TGGET Niche Research is a hosted research service for people assessing mobile app and online-service ideas. It combines measured demand, competitors, app-store reviews, and community signals into reports with rule-based verdicts.
Key features
- 01Measure search demand and sub-niches
- 02Find search-result competitors
- 03Review App Store apps and user complaints
- 04Add demand, review, and community checks
- 05Compare completed research
- 06Track a niche with monthly checks
Use cases
- 01Assess demand for an app idea
- 02Compare several researched business ideas
- 03Review customer complaints in competing apps
- 04Monitor changes in a niche over time
MCP support
The remote Streamable HTTP MCP server exposes research, report, comparison, signal, and niche-tracking tools, along with quota and source resources and a `find_niche` prompt. Calls use a personal access token as a Bearer token.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://tgget.io/mcpclaude mcp add --transport http io-tgget-niche-research https://tgget.io/mcp{"mcpServers":{"io-tgget-niche-research":{"type":"http","url":"https://tgget.io/mcp"}}}Open in Cursor{"servers":{"io-tgget-niche-research":{"type":"http","url":"https://tgget.io/mcp"}}}Open in VS Code{"mcpServers":{"io-tgget-niche-research":{"type":"http","url":"https://tgget.io/mcp"}}}{"mcpServers":{"io-tgget-niche-research":{"serverUrl":"https://tgget.io/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
https://tgget.io/mcpAuth requiredTools
10| Parameter | Type | Required | Description |
|---|---|---|---|
| deep | boolean | No | Deeper scan with more sub-topics and competitor checks. Available on plans that include it (Pro) and to administrators; counted as two researches. |
| text | string | Yes | Search phrase (e.g. "expense tracker") or a description of the idea in your own words, up to 400 characters. |
| locale | enum | No | Language of the conclusions and the final report. Defaults to the interface language of the account. Texts meant for the site and the stores are always written in the language of the market.en |
| country | enum | No | Country to measure demand in, as an ISO 3166-1 alpha-2 code (BR, MX, PT, AR, CO, US, GB, DE, KZ, RU, BY…). App Store apps are looked up in the same country, the report writes prices, channels and copy for it, and sub-topics are measured there too. Omit it to use the country of the phrase's language. The phrase is measured in its own language when the country has it (Spanish in the United States), otherwise in the country's main language, so write it the way people search in that country.AE | AL | AM | AO | AR | AT | AU | AZ | BA | BD | BE | BF | BG | BH | BO | BR | BY | CA | CH | CI | CL | CM | CO | CR | CY | CZ | DE | DK | DZ | EC | EE | EG | ES | FI | FR | GB | GH | GR | GT | HK | HR | HU | ID | IE | IL | IN | IT | JO | JP | KE | KH | KR | KZ | LK | LT | LV | MA | MC | MD | MK | MM | MT | MX | MY | NG | NI | NL | NO | NZ | PA | PE | PH | PK | PL | PT | PY | RO | RS | RU | SA | SE | SG | SI | SK | SN | SV | TH | TN | TR | TW | UA | US | UY | VE | VN | ZA |
| language | enum | No | Language the demand is measured in, when the guess from the phrase is not enough: French in Canada (CA + fr), Italian in Switzerland (CH + it), Spanish in the United States (US + es). It must be one of the languages of `country`; given without `country` it picks the main country of the language (pt: Brazil, nl: Netherlands). Omit it to use the language of the phrase.ar | az | be | bg | bn | bs | cs | da | de | el | en | es | et | fi | fr | he | hi | hr | hu | hy | id | it | ja | ko | lt | lv | mk | ms | nb | nl | pl | pt | ro | ru | sk | sl | sq | sr | sv | th | tl | tr | uk | ur | vi | zh-CN | zh-TW |
Details
From the project READMETGGET Niche Research MCP server
Remote Model Context Protocol server of TGGET, a niche research tool for mobile apps and online services. It lets an AI assistant check an idea against measured data instead of guessing from a description.
Give it a search phrase or a description of an idea in your own words. It returns monthly search demand, sub-niches, competitor sites from search results, App Store apps with what their users complain about, community signals and a final report with a verdict: worth building, needs validation or no niche. The verdict is computed by rules from five measured factors, so the same numbers always give the same answer; the language model only explains it.
- Endpoint:
https://tgget.io/mcp(Streamable HTTP) - Authentication: personal access token, sent as a Bearer token. The server tells what it is and lists its tools without a token; every call needs one
- Name in the MCP Registry:
io.tgget/niche-research - Documentation: tgget.io/docs/api

What you can ask
- "Validate this idea: an app that reminds you to water plants and explains how to care for them."
- "Is there demand for an expense tracker for couples? Who are the competitors?"
- "Research the niche 'invoice generator' and give me the report as Markdown."
- "Compare my last three researches and tell me which idea to start with."
- "Follow the niche of my research about habit trackers and show what changed since last month."
Getting a token
- Create an account at tgget.io or in the Android app and confirm your email. A free account is enough.
- Open Settings, section "API and AI assistants", and create a token. It is shown once.
Tokens expire after a year and are revoked when you change your password or close your sessions. An account holds up to five tokens.
Connecting
Replace <token> with your token. Ready-made files are in examples.
Claude Code
claude mcp add --transport http tgget https://tgget.io/mcp --header "Authorization: Bearer <token>"
Cursor
~/.cursor/mcp.json or .cursor/mcp.json in a project:
{
"mcpServers": {
"tgget": {
"url": "https://tgget.io/mcp",
"headers": { "Authorization": "Bearer <token>" }
}
}
}
VS Code
.vscode/mcp.json:
{
"inputs": [
{ "type": "promptString", "id": "tgget-token", "description": "TGGET access token", "password": true }
],
"servers": {
"tgget": {
"type": "http",
"url": "https://tgget.io/mcp",
"headers": { "Authorization": "Bearer ${input:tgget-token}" }
}
}
}
Codex
~/.codex/config.toml, with the token in the TGGET_TOKEN environment variable:
[mcp_servers.tgget]
url = "https://tgget.io/mcp"
bearer_token_env_var = "TGGET_TOKEN"
Clients that only run local servers
Use the mcp-remote bridge:
{
"mcpServers": {
"tgget": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://tgget.io/mcp", "--header", "Authorization: Bearer <token>"]
}
}
}
Tools
| Tool | What it does | Parameters |
|---|---|---|
start_research | Starts a research from a search phrase or a description of an idea. A phrase is scanned directly; a description is first turned into real search queries and the strongest one is scanned. | text (required), deep, locale |
get_research | Current state and findings: status, headline numbers, ranked candidate phrases, competitor overview, child researches, skipped stages. | id (required) |
get_report | The final niche report: verdict, customer pains, MVP, napkin economics, SEO and ASO plans, name options, landing page draft, distribution channels, validation steps and risks. | id (required), format (markdown or json) |
list_research | The most recent researches of the account, newest first. | limit (1 to 50) |
run_signal | Adds one check to a finished research: competitors for a phrase, demand history, App Store, reviews, community signals, paid search metrics, or a rebuilt report. | id, kind (required), phrase, locale |
compare_research | Puts two to five finished researches side by side and marks the better value of every measure. The marks come from the numbers, not from the language model. | ids (required) |
follow_niche | Starts following the niche of a finished research that has a report: it is scanned anew every month and a digest of what changed is sent to the account. Monthly checks do not spend researches. | research_id (required) |
list_projects | The niches the account follows, with the latest numbers and the date of the next check. | limit (1 to 50) |
get_project | A followed niche with the history of its checks and what changed since the previous one. | id (required) |
update_project | Pauses a followed niche, follows it again or stops following it. | id, status (active, paused or deleted) (required) |
locale sets the language of the conclusions and the report; en is the one available now. The market is chosen by the language of the phrase: search demand is measured in the country of that language. Texts meant for a site or an app store are always written in the language of the market.
Resources and prompt
| Name | What it gives |
|---|---|
tgget://quota | Researches remaining on the plan and when the next one becomes available. |
tgget://sources | Research kinds available right now and what each one costs. |
find_niche (prompt) | Walks the assistant through validating an idea: start, wait, read the evidence, write a verdict. Argument: idea. |
How a research runs
Research runs in the background and takes a few minutes.
- Call
start_research. It returns the research id. - Poll
get_researchevery 20 to 30 seconds untilstatusiscompletedandpendingis0. Findings appear as they arrive. - When the research lists a
report, callget_report.
Limits and privacy
- A research is counted when it starts. Checks added to an existing research with
run_signalare free. - The free plan includes three researches to start and one more every 30 days. Paid plans are on the plans page and are bought in the mobile app; the same account works everywhere.
- A free account follows one niche, Starter two, Pro ten.
- Researches made on the free plan are public: the result may be listed in the open niche catalog. The catalog shows the researched phrase and its findings, never the description you typed. Researches on paid plans stay private.
- The API and the MCP server share a limit of 60 requests per minute.
- Search interest is evidence, not a customer count. Treat the verdict as a starting point for your own validation.
Links
- TGGET: validate an app or online business idea
- Business idea validation
- Niche finder tool
- Open niche catalog
- App ideas with measured demand
- Micro SaaS ideas with measured demand
- Android app on Google Play
- API and MCP documentation
- Contact
This repository holds the documentation and connection examples of the hosted server. The server itself runs at tgget.io.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.