NameCatcher
NameCatcher provides tools to evaluate, compare, and price collectible Telegram usernames using real Fragment marketplace data.
score_name: Score a single username (0–100), get a quality band (premium/strong/medium/weak), a fair price estimate in GRAM, and a positioning thesis explaining why the name works and for whom.compare_names: Submit up to 20 candidate usernames at once and receive them ranked by namability score — ideal for choosing the best name for a brand, bot, channel, or investment portfolio.check_fragment_ask: Compare a Fragment marketplace asking price against the name's estimated fair value; a fair/ask ratio ≥ 1.2 signals the lot is priced below its class valuation, helping you spot underpriced deals.
Enables evaluation and comparison of collectible Telegram usernames, including scoring, fair price estimation, and pre-purchase checks against Fragment market data.
Provides username valuation and market analysis for Telegram usernames on the TON blockchain, leveraging Fragment market data for investment decisions.
NameCatcher — username intelligence for AI agents
Score and value collectible Telegram usernames: namability score (0–100) validated against 111k+ real Fragment sales, fair price estimation in GRAM, and positioning theses. Free public API — no key, no wallet, no setup.
Three ways to plug in, thinnest first:
Layer | For | Install |
any agent that can | nothing | |
Claude Code / skills-compatible agents |
| |
Claude Desktop/Code, any MCP client |
|
Built by NameCatcher — the Telegram mini app for username investors: mint catching, market analytics, portfolio, value passports.
Quick try
curl -s "https://api-namecatcher.rocketname.com/public/score/wearlab?lang=en" | jq{
"username": "wearlab",
"score": 67,
"band": "strong",
"fair_price_ton": 400,
"thesis": "A crisp fusion of \"wear\" and \"lab\" …",
"lang": "en",
"analysis_url": "https://t.me/NameCatcherBot?startapp=name_wearlab__pub_api",
"fragment_url": "https://fragment.com/username/wearlab"
}Related MCP server: TON Data MCP Server
API reference
One endpoint, no auth:
GET https://api-namecatcher.rocketname.com/public/score/{name}?lang={en|ru}Parameters
Param | In | Required | Description |
| path | yes | Username without |
| query | no |
|
Response fields
Field | Type | Description |
| string | Canonical (lowercase) username |
| int 0–100 | Namability — quality of the name as a brandable asset. Market-validated: names scoring 90+ sell for a multiple of 80–89 names |
| string |
|
| number | null | Class-based fair price estimate in GRAM (length × score class) |
| string | null | Short positioning summary (why the name works, for whom). Present only for names already analyzed — |
| string | Language the thesis was returned in |
| string | Full breakdown in the NameCatcher mini app |
| string | The name's page on Fragment (live market status, buy/bid) |
Errors
Status | Body | Meaning |
400 |
| Not a valid username string |
400 |
| Valid string, but not scorable as a collectible (e.g. too short) |
429 |
| Over 60 req/min per IP — wait |
429 |
| Over 1,000 req/day per IP |
Rate limits
60 requests/min and 1,000 requests/day per IP. Generous for agent workflows (evaluating and comparing dozens of names); not enough for bulk scraping — that's intentional. Need more for a legitimate use case? Ping @BrandEvangelist.
curl cookbook
# Score one name (Russian thesis)
curl -s "https://api-namecatcher.rocketname.com/public/score/morya?lang=ru" | jq '{score, band, fair_price_ton}'
# Compare candidates: pick the best of three
for n in pulsefit traintrack fitwave; do
curl -s "https://api-namecatcher.rocketname.com/public/score/$n" | jq -c '{username, score, band}'
done | sort -t: -k2 -rn
# Pre-purchase check: is a 300 GRAM ask below class valuation?
curl -s "https://api-namecatcher.rocketname.com/public/score/vault" \
| jq '{score, fair_price_ton, below_class: (.fair_price_ton / 300 >= 1.2)}'Agent Skill
The names/ton-usernames skill teaches an agent the full workflow: single-name evaluation, candidate comparison, and pre-purchase checks against Fragment asks.
npx skills add productmap/namecatcher-skills --skill ton-usernames
# or manually:
cp -r names/ton-usernames ~/.claude/skills/A PR adding this skill to the official ton-org/skills is open.
MCP server
A thin stdio bridge over the same API — for Claude Desktop, Claude Code, and any MCP client. No key needed. Published on npm as namecatcher-mcp (GitHub install npx -y github:productmap/namecatcher-skills also works).
Remote endpoint (Streamable HTTP) — same three tools, zero install:
https://mcp-namecatcher.rocketname.com/mcpclaude mcp add --transport http namecatcher https://mcp-namecatcher.rocketname.com/mcpClaude Code:
claude mcp add namecatcher -- npx -y namecatcher-mcpClaude Desktop / other MCP clients (mcpServers config):
{
"mcpServers": {
"namecatcher": {
"command": "npx",
"args": ["-y", "namecatcher-mcp"]
}
}
}Tools
Tool | Description | Arguments |
| Score one username: namability, band, fair price, thesis |
|
| Score up to 20 candidates and rank them by score |
|
| Compare a Fragment asking price to the class valuation → fair/ask ratio + verdict |
|
Environment: NAMECATCHER_API_ORIGIN (optional) — override the API origin.
Notes for builders
The score measures naming quality, deterministic per model version — safe to cache
It is not demand for a specific lot: always check the live Fragment price before money decisions
Pairs naturally with TON wallet tooling (@ton/mcp): evaluate → then buy
Links
🤖 Bot & mini app: @NameCatcherBot
🛒 Username market: fragment.com
🧩 TON MCP ecosystem: mcp.ton.org
License
MIT
Available Tools
3 toolscheck_fragment_askA
Pre-purchase check: compare a Fragment asking price against the name's class valuation (fair price). Returns the fair/ask ratio — ratio >= 1.2 means the lot is priced below its class valuation.
Inputs: name (required), ask_ton (required).
compare_namesA
Score several username candidates (max 20) and rank them by score. Use when choosing between name options for a brand, bot, channel or investment.
Inputs: names (required), lang.
score_nameA
Score a Telegram username as an asset: namability 0-100 (validated against real Fragment sales), quality band, fair price estimate in GRAM, and a positioning thesis when available. Use when the user asks whether a username is good, what it is worth, or before buying/minting it.
Inputs: name (required), lang.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 3 tools
Each tool serves a distinct, non-overlapping purpose: one compares ask prices, one ranks multiple candidates, and one evaluates a single name. No ambiguity.
All tool names follow a consistent verb_noun pattern in snake_case, using verbs like check, compare, and score.
Three tools is appropriate for a focused server that handles Telegram username valuation and comparison. Not too few or too many.
Covers core valuation and comparison operations. Lacks direct buy/mint actions, but these are not valuation tasks. Minor gap in lifecycle coverage.
Maintenance
Related MCP Connectors
RiskDataApi — Solana token risk scoring for AI agents. Safety score, insider clusters, honeypot.
Solana rug and scam checker for AI agents: token risk score, wallet and drainer-link scans, Pro watchlists. Free tier; agents can self-pay for Pro in USDC.
Blockchain analytics API for AI agents. Smart Money signals, wallet profiling, token analytics.
Blockchain analytics API for AI agents. Smart Money signals, wallet profiling, token analytics.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceBittensor subnet intelligence — mineability scores, 1-click deploy scripts, momentum scoring, whale flows, institutional tracking for all 128 subnets. 18 API endpoints. Free tier.-
- FlicenseAqualityDmaintenanceTON Data MCP Server — real-time blockchain data for AI agents. Provides wallet balances, token prices, STON.fi liquidity pools, market overview, transactions, and network state. 6 MCP tools, free tier, Docker-ready.6-
- AlicenseNot gradedqualityDmaintenanceScore brand names across domain availability, USPTO trademark conflict, social handle availability (12+ platforms), SEO strength, and AI findability (GEO) in a single call. Pay-per-call via the x402 micropayment protocol (USDC on Base + Solana) — no signup, no API keys.MIT
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to check and rank startup name candidates by domain availability, trademark conflicts, and social handle availability, with optional name generation and scoring profiles.53 PyPI4MIT