# Agent Data API (remote · agent-data.centorprat.workers.dev)

Memecoin screener, backtests, exit alerts, wallet traces + web search, enrichment, 50+ tools (x402)

- Trust score: 64/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-24

## Components

- remote · `agent-data.centorprat.workers.dev`: 64/100 (this document), [markdown](https://verifymcp.io/servers/bustlll-agent-data-api/agent-data.md), [page](https://verifymcp.io/servers/bustlll-agent-data-api/agent-data)

## Channel facts

- Endpoint: `https://agent-data.centorprat.workers.dev/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.1`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-10-24.

- **Endpoint Security**: 63/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - HTTPS enforcement could not be verified: the plaintext port answered with HTTP 406, which proves neither a plaintext path nor enforcement.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 58/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 4048 tokens (~269/item across 15 items; 15 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability check failed: schema churn in the 1 day we've observed: 20 tool removals, 1 breaking changes, 0 auth/transport breaks, 6 additions.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 15 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 16 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### How do I install the Agent Data API MCP server?

Agent Data API is a hosted endpoint at https://agent-data.centorprat.workers.dev/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http bustlll-agent-data-api 'https://agent-data.centorprat.workers.dev/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "bustlll-agent-data-api": {
      "url": "https://agent-data.centorprat.workers.dev/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "bustlll-agent-data-api": {
      "type": "http",
      "url": "https://agent-data.centorprat.workers.dev/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.bustlll-agent-data-api]
url = "https://agent-data.centorprat.workers.dev/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "bustlll-agent-data-api": {
      "type": "remote",
      "url": "https://agent-data.centorprat.workers.dev/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add bustlll-agent-data-api --url 'https://agent-data.centorprat.workers.dev/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  bustlll-agent-data-api:
    url: "https://agent-data.centorprat.workers.dev/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "bustlll-agent-data-api": {
      "Transport": "http",
      "Url": "https://agent-data.centorprat.workers.dev/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add bustlll-agent-data-api -t streamable-http -u 'https://agent-data.centorprat.workers.dev/mcp'
```

### Other

```json
{
  "mcpServers": {
    "bustlll-agent-data-api": {
      "type": "http",
      "url": "https://agent-data.centorprat.workers.dev/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-10-24 (score 64, +9)

- [security regression] Stability: unverified → fail
- [security regression] A breaking change shipped without a version bump: still 1.0
- [security regression] Tool “check_x402_seller” was removed
- [security regression] Tool “crypto_address_risk” was removed
- [security regression] Tool “list_tools_and_prices” was removed
- [security regression] Tool “memecoin_alerts” was removed
- [security regression] Tool “shopify_stores_search” was removed
- [security regression] Tool “memecoin_token_report” was removed
- [security regression] Tool “memecoin_track_record” was removed
- [security regression] Tool “payments_feed” was removed
- [security regression] Tool “prompt_injection_check” was removed
- [security regression] Tool “recommend_x402_api” was removed
- [security regression] Tool “run_data_tool” was removed
- [security regression] Tool “shopify_store” was removed
- [security regression] Tool “solana_wallet_profile” was removed
- [security regression] Tool “token_launches” was removed
- [security regression] Tool “token_pretrade_check” was removed
- [security regression] Tool “token_safety” was removed
- [security regression] Tool “web_fetch” was removed
- [security regression] Tool “web_search_read” was removed
- [security regression] Tool “x402_payer_profile” was removed
- [security regression] Tool “x402_seller_customers” was removed
- [security improvement] Authorization: unverified → partial
- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “company_enrich” rewrote its description, which is the text the model reads
- [security] Tool “email_verify” rewrote its description, which is the text the model reads
- [security] Tool “memecoin_backtest” rewrote its description, which is the text the model reads
- [security] Tool “memecoin_exit_check” rewrote its description, which is the text the model reads
- [security] Tool “memecoin_holder_trace” rewrote its description, which is the text the model reads
- [security] Tool “memecoin_screen” rewrote its description, which is the text the model reads
- [security] Tool “memecoin_watch” rewrote its description, which is the text the model reads
- [security] Tool “web_read” rewrote its description, which is the text the model reads
- [security] Tool “web_search” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 122 → 269
- [functional regression] “email_verify” added a required parameter “emails”, so existing callers break
- [functional regression] “email_verify” dropped the required parameter “email”
- [functional improvement] Tool coverage: 13% → 100%
- [functional] New tool “address_check”
- [functional] New tool “catalog_read”
- [functional] New tool “data_tool_run”
- [functional] New tool “shopify_lookup”
- [functional] New tool “token_check”
- [functional] New tool “x402_lookup”
- [cosmetic] “company_enrich” added an optional parameter “tier”
- [cosmetic] “memecoin_backtest” added an optional parameter “minVolumeUsd5m”
- [cosmetic] “memecoin_backtest” added an optional parameter “sweep”
- [cosmetic] “memecoin_exit_check” added an optional parameter “notifyAtGainPct”
- [cosmetic] “memecoin_holder_trace” added an optional parameter “tier”
- [cosmetic] “memecoin_watch” added an optional parameter “tier”
- [cosmetic] “web_read” added an optional parameter “format”
- [cosmetic] “web_read” added an optional parameter “html”
- [cosmetic] “web_read” added an optional parameter “raw”
- [cosmetic] “web_read” added an optional parameter “text”
- [cosmetic] “web_search” added an optional parameter “max_chars”
- [cosmetic] “web_search” added an optional parameter “read”
- [cosmetic] “web_search” added an optional parameter “research”
- [cosmetic] “company_enrich” reworded the description of “domain”
- [cosmetic] “memecoin_backtest” reworded the description of “costPctPerSide”
- [cosmetic] “memecoin_backtest” reworded the description of “days”
- [cosmetic] “memecoin_backtest” reworded the description of “entryAt”
- [cosmetic] “memecoin_backtest” reworded the description of “exits”
- [cosmetic] “memecoin_backtest” reworded the description of “strategy”
- [cosmetic] “memecoin_exit_check” reworded the description of “alreadySoldPct”
- [cosmetic] “memecoin_exit_check” reworded the description of “chain”
- [cosmetic] “memecoin_exit_check” reworded the description of “entry”
- [cosmetic] “memecoin_exit_check” reworded the description of “rules”
- [cosmetic] “memecoin_exit_check” reworded the description of “token”
- [cosmetic] “memecoin_holder_trace” reworded the description of “buyers”
- [cosmetic] “memecoin_holder_trace” reworded the description of “depth”
- [cosmetic] “memecoin_holder_trace” reworded the description of “token”
- [cosmetic] “memecoin_screen” reworded the description of “chains”
- [cosmetic] “memecoin_screen” reworded the description of “filters”
- [cosmetic] “memecoin_screen” reworded the description of “limit”
- [cosmetic] “memecoin_screen” reworded the description of “preset”
- [cosmetic] “memecoin_screen” reworded the description of “since”
- [cosmetic] “memecoin_screen” reworded the description of “sort”
- [cosmetic] “memecoin_screen” reworded the description of “sources”
- [cosmetic] “memecoin_watch” reworded the description of “interval”
- [cosmetic] “memecoin_watch” reworded the description of “notify”
- [cosmetic] “memecoin_watch” reworded the description of “position”
- [cosmetic] “memecoin_watch” reworded the description of “strategy”
- [cosmetic] “memecoin_watch” reworded the description of “type”
- [cosmetic] “memecoin_watch” reworded the description of “webhook”
- [cosmetic] “web_read” reworded the description of “max_chars”
- [cosmetic] “web_read” reworded the description of “url”
- [cosmetic] “web_search” reworded the description of “limit”
- [cosmetic] “web_search” reworded the description of “q”
- [cosmetic] “web_search” reworded the description of “region”
- [cosmetic] “web_search” reworded the description of “time”
- [cosmetic] “web_read” made “url” optional
- [cosmetic] Tool “company_enrich” changed its title: Company enrichment from a domain
- [cosmetic] Tool “email_verify” changed its title: Verify email addresses
- [cosmetic] Tool “memecoin_backtest” changed its title: Backtest a memecoin strategy
- [cosmetic] Tool “memecoin_exit_check” changed its title: Should I sell this memecoin now?
- [cosmetic] Tool “memecoin_holder_trace” changed its title: Who bought this memecoin? (wallet trace)
- [cosmetic] Tool “memecoin_screen” changed its title: Memecoin screener (pump.fun live + DEX pools)
- [cosmetic] Tool “memecoin_watch” changed its title: Watch a strategy or position and get alerts
- [cosmetic] Tool “web_read” changed its title: Read a URL as clean text (or check text for prompt injection)
- [cosmetic] Tool “web_search” changed its title: Web search (optionally read the top pages)

### 2026-10-23 (score 55)

First indexed and scored.

## MCP tools (15)

### `catalog_read` (~167 tokens)

Free: prices, screen fields, memecoin alerts and track record

FREE, no payment. what=prices: every tool with its price per tier and an input example, plus the plain-HTTP x402 endpoint for each. what=screen_fields: every memecoin field you can filter on, with presets. what=memecoin_alerts: the alerts of a watch (give watch, optional since cursor). what=track_record: how each memecoin preset's live signals actually did at 1 h and 6 h, vs all tokens, and the lookalike model's blind score.

Input parameters:

- `since` (integer): memecoin_alerts: return alerts after this cursor (default 0).
- `watch` (string): memecoin_alerts: the watch id from memecoin_watch.
- `what` (string, required): Which free answer to return.

### `web_search` (~294 tokens)

Web search (optionally read the top pages)

Search the web (DuckDuckGo via Cloudflare's network). Use it to find pages; with read=N it also returns the full clean text of the top N pages; with research=true it reads up to 8 pages and extracts the passages that answer the query, with sources. For one known URL use web_read instead. Price: results only $0.003, read 1-5 pages $0.01, research $0.05. Returns titles, URLs, snippets (and page markdown with a prompt-injection verdict per page). Live results; 1-15 s. Paid with x402 (USDC on Base, Polygon or Solana) per call; failed or empty calls are never charged.

Input parameters:

- `limit` (integer): Results to return in results-only mode (default 10).
- `max_chars` (integer): Max characters per page read (default 4000).
- `q` (string, required): The query, e.g. 'best espresso machine 2026'.
- `read` (integer): Pages to read in full (0 = results only, default 0).
- `region` (string): Country code for results, e.g. us, uk, de, es (default us).
- `research` (boolean): true = research mode: read up to 8 pages and return key passages ($0.05).
- `time` (string): Only results from this period.

### `web_read` (~234 tokens)

Read a URL as clean text (or check text for prompt injection)

Fetch one public URL and return its main content as clean markdown (title, publish date, word count) plus a prompt-injection verdict; raw=true returns the raw body instead (text or base64). Give `text` instead of `url` to only scan text you already have for prompt injection. To find pages first use web_search. Price: read $0.003, raw $0.002, text scan $0.002. Fetched live via Cloudflare's network; 1-10 s. Paid with x402 (USDC on Base, Polygon or Solana) per call; failed or empty calls are never charged.

Input parameters:

- `format` (string): raw mode only (default auto).
- `html` (string): Optional HTML of that text, to also find hidden instructions.
- `max_chars` (integer): Max characters returned (default 20000).
- `raw` (boolean): true = raw body (no cleanup), default false.
- `text` (string): Instead of url: text to scan for prompt injection.
- `url` (string): Public http(s) URL to read.

### `company_enrich` (~153 tokens)

Company enrichment from a domain

Everything public about a company from its domain: name, description, size hints, address, phones, emails, socials, website platform, email provider and security, SaaS stack. tier=max adds its LinkedIn company page (employees, followers, industry, open jobs) and verifies each email found. For only email checks use email_verify. Price: standard $0.01, max $0.05. Reads the site live; 5-25 s. Paid with x402 (USDC on Base, Polygon or Solana) per call; failed or empty calls are never charged.

Input parameters:

- `domain` (string, required): Company website domain, e.g. stripe.com.
- `tier` (string): Default standard.

### `email_verify` (~140 tokens)

Verify email addresses

Check email addresses without sending mail: syntax, domain and MX records, disposable domains, role accounts, catch-all hints, and a valid / risky / invalid verdict each, plus a summary. Up to 20 addresses cost $0.002 per call; 21-200 addresses are a bulk call at $0.05. For company data use company_enrich. DNS lookups live; under 1 s for 20. Paid with x402 (USDC on Base, Polygon or Solana) per call; failed or empty calls are never charged.

Input parameters:

- `emails` (required): Addresses: a list, or one comma-separated string (max 200).

### `token_check` (~260 tokens)

Token safety and due diligence (EVM and Solana)

Check a token before trading. level=quick: one-line pre-trade verdict for up to 10 tokens ($0.01). level=safety (default): contract / mint safety: honeypot simulation, buy/sell tax, mint and freeze authority, Token-2022 traps, holders, liquidity ($0.01). level=report: memecoin report with rug-risk %, launch structure, snipers, bundles and a plain summary ($0.02). level=max: all of it plus the holder trace of pump.fun / Base tokens, one verdict and every red flag ($0.10). For wallets use address_check; to find tokens use memecoin_screen. Live data (chain, RugCheck, DexScreener); 1-30 s. Signals, not advice. Paid with x402 (USDC on Base, Polygon or Solana) per call; failed or empty calls are never charged.

Input parameters:

- `address` (string, required): Token contract (0x...) or Solana mint. level=quick accepts up to 10, comma separated.
- `chain` (string): Chain of a 0x token (Solana mints are detected). Default ethereum.
- `level` (string): Depth and price (default safety).

### `address_check` (~159 tokens)

Crypto address risk / AML screen

Screen a wallet address (BTC, ETH/EVM, Solana, Tron, XRP, LTC) against OFAC sanctions and scam lists with on-chain context. tier=max adds the chain's own trail: a 2-hop Bitcoin trace with exposure, a Solana wallet's age and trading record, or a Base wallet's USDC counterparties. For tokens use token_check. Price: standard $0.01, max $0.05. Live; 2-20 s. Risk signals, not a legal finding. Paid with x402 (USDC on Base, Polygon or Solana) per call; failed or empty calls are never charged.

Input parameters:

- `address` (string, required): The wallet address.
- `tier` (string): Default standard.

### `memecoin_screen` (~257 tokens)

Memecoin screener (pump.fun live + DEX pools)

Run your own screen over the live market: every pump.fun launch from our real-time stream plus DEX pools on Solana and Base, 120+ fields in 5m-24h windows, 8 presets. Use it to FIND tokens; then token_check to vet one, memecoin_holder_trace to trace its buyers, memecoin_watch to be alerted. Poll with `since`. Data refreshes every 20 s. Price $0.01. Paid with x402 (USDC on Base, Polygon or Solana) per call; failed or empty calls are never charged.

Input parameters:

- `chains` (array): Default both.
- `filters` (object): {field: condition}; added to the preset's filters (yours win).
- `limit` (integer): Max tokens returned (default 20).
- `preset` (string): Optional starting point.
- `since` (string): Cursor from a previous response: only tokens created after it (for polling).
- `sort` (array): Sort keys, e.g. [{"field": "buyers.m5", "dir": "desc"}].
- `sources` (array): pump.fun = bonding curves from our real-time stream; dex = DEX pools. Default both.

### `memecoin_holder_trace` (~212 tokens)

Who bought this memecoin? (wallet trace)

Are a token's early buyers independent or one operator? Follows each early buyer's first funding (up to 2 hops): clusters sharing a funder (exchange hubs excluded), dev-linked and fresh wallets, launch-block bundles, split supply, supply bought and still held, coordination risk %. tier=max: 60 buyers, 2 hops, the creator's other launches and insider rings vs sniper bots. Works for pump.fun tokens (Solana) and Base tokens (0x...). Price: standard $0.02, max $0.10. 5-60 s. Paid with x402 (USDC on Base, Polygon or Solana) per call; failed or empty calls are never charged.

Input parameters:

- `buyers` (integer): Standard tier: early buyers to trace (default 30).
- `depth` (integer): Standard tier: funding hops (default 2).
- `tier` (string): Default standard.
- `token` (string, required): pump.fun mint or Base token 0x...

### `memecoin_backtest` (~440 tokens)

Backtest a memecoin strategy

Replay a screen strategy plus exit rules on every graded pump.fun token we recorded (snapshots at 5/15/30/60 min of age) or on a preset's live signal ledger: win rate, average / median return after fees, exit reasons, per-day results, best and worst trades. Give `sweep` to try every take-profit x stop-loss x hold combination, ranked on older entries and re-scored on the newest 30% (walk-forward). Price: one rule set $0.01, sweep $0.05. Under 2 s. Paid with x402 (USDC on Base, Polygon or Solana) per call; failed or empty calls are never charged.

Input parameters:

- `costPctPerSide` (number): Fees + slippage per side in % (default 2).
- `days` (number): Lookback in days (default 7, max 21).
- `entryAt`: Snapshot age in minutes (5, 15, 30, 60) or "signal" (a preset's live signals). Default 15.
- `exits` (object): Exit rules (same names as memecoin_exit_check).
- `minVolumeUsd5m` (number): Skip tokens with less 5-minute volume at entry (default 500).
- `strategy` (object): A screen strategy. Each filter is {field: condition}. condition = {"min": x, "max": y} for numbers, true/false for booleans, {"in": [...]} / {"notIn": [...]} for strings, {"contains": text} for lists…
- `sweep` (object): Grid to sweep (max 64 combinations).

### `memecoin_exit_check` (~271 tokens)

Should I sell this memecoin now?

Your entry and exit rules applied to the token's real path since you entered: hold / sell X% / exit now, with every rule that fired and the position's gain, peak and drawdown. Includes live-only rules (dev sells, sniper dumps, sell-burst dump detector, liquidity drop). Poll it while you hold, or let memecoin_watch poll for you. Price $0.003. Under 2 s. Signals only: your agent executes the trade. Paid with x402 (USDC on Base, Polygon or Solana) per call; failed or empty calls are never charged.

Input parameters:

- `alreadySoldPct` (number): % of the original position already sold (for tiered take-profits).
- `chain` (string): Optional; detected from the token.
- `entry` (object, required): Give ONE of: marketCapUsd, priceUsd or time (ISO 8601, e.g. 2026-10-24T09:00:00Z).
- `notifyAtGainPct` (array): Watches only: alert once at each gain %, e.g. [50, 100, 200].
- `rules` (object): Exit rules: everything in the backtest exits plus live-only signals.
- `token` (string, required): Token mint / contract.

### `memecoin_watch` (~410 tokens)

Watch a strategy or position and get alerts

Creates a watch (this is the only tool that stores state): we re-run your screen strategy (alert on each new matching token) or your position's exit rules (alert when hold turns into sell / exit, plus gain milestones) on your interval. Read alerts free with catalog_read what=memecoin_alerts, or get them by webhook / Telegram / Discord. tier=standard: 24 h, intervals 5m-1d (positions also 1m), $0.05. tier=max: 7 days, strategies at 1m too, $0.25. Keep the returned watch id secret: it is the key to its alerts. Paid with x402 (USDC on Base, Polygon or Solana) per call; failed or empty calls are never charged.

Input parameters:

- `interval` (string): Check interval (default 5m).
- `notify` (object): Optional delivery of each alert as a message.
- `position` (object): An open position to check.
- `strategy` (object): A screen strategy. Each filter is {field: condition}. condition = {"min": x, "max": y} for numbers, true/false for booleans, {"in": [...]} / {"notIn": [...]} for strings, {"contains": text} for lists…
- `tier` (string): Default standard.
- `type` (string, required): strategy = alert on new matching tokens; position = alert on exit signals.
- `webhook` (string): Optional https URL: each alert is POSTed there.

### `x402_lookup` (~368 tokens)

x402 market intelligence (which API to call, who pays whom)

Answers about the x402 agent-payments market from the whole Bazaar index and Base chain history. action=recommend: which x402 API to call for a need, ranked by fit, price and trust ($0.005). seller_check: is an x402 endpoint / seller trustworthy, its prices and payers ($0.005). payer_profile: a Base wallet's x402 payments, sellers and counterparties up to 3 hops ($0.01). seller_customers: who pays a seller and how much ($0.01). payments_feed: a wallet's payments in time order, with a cursor ($0.003). Bazaar index refreshed every 6 h; chain data real time. Paid with x402 (USDC on Base, Polygon or Solana) per call; failed or empty calls are never charged.

Input parameters:

- `action` (string, required): Which question to answer (sets the price, see above).
- `address` (string): payer_profile / payments_feed: Base wallet 0x...
- `days` (integer): payer_profile / seller_customers: lookback days (default 30).
- `depth` (integer): payer_profile: hops (default 1).
- `limit` (integer): recommend / payments_feed: rows to return.
- `max_price` (number): recommend: max USD per call.
- `need` (string): recommend: the task in plain words, e.g. 'weather forecast for a city'.
- `network` (string): recommend: e.g. base, solana.
- `seller` (string): seller_customers: seller host or payTo address.
- `since` (string): payments_feed: ISO time cursor from the previous response.
- `url` (string): seller_check: endpoint URL, host or payTo address.

### `shopify_lookup` (~267 tokens)

Shopify store technographics

action=store: one Shopify store's apps by category (reviews, email, subscriptions, loyalty...), pixels, theme and catalog hints, gaps and sales pitch angles. action=search: stores from our index of ~19k Shopify stores by app used / not used, missing category, country and keyword (lead lists). Price $0.01 each. Store reads are live (3-15 s); the index is refreshed weekly. Paid with x402 (USDC on Base, Polygon or Solana) per call; failed or empty calls are never charged.

Input parameters:

- `action` (string, required): store = one store by domain; search = find stores in the index.
- `app` (string): search: stores using this app, e.g. Klaviyo.
- `country` (string): search: 2-letter country, e.g. US.
- `domain` (string): store: the store's domain, e.g. allbirds.com.
- `exclude_app` (string): search: stores NOT using this app.
- `limit` (integer): search: rows (default 10).
- `missing` (string): search: stores with no app in this category, e.g. loyalty.
- `q` (string): search: keyword in the store name or products.

### `data_tool_run` (~272 tokens)

Run one of 70 data tools (Maps, jobs, YouTube, ...)

Runs one data tool with its JSON input: Google Maps places with contacts, YouTube videos / transcripts / comments, Indeed, LinkedIn and 13 other job boards, LinkedIn companies, Google News and Trends, Google Ads library, TikTok comments, Pinterest, Airbnb, Redfin, AliExpress, app stores, website contacts and SEO checks, sanctions, clinical trials and more. catalog_read what=prices lists every tool with an input example. Price $0.01 per call (small capped runs). tier=max runs a bigger job for: google-maps-scraper ($0.10), indeed-jobs-scraper ($0.05), linkedin-company-scraper ($0.05), linkedin-jobs-scraper ($0.05), youtube-comments-scraper ($0.05). Runs live on Apify; 10 s-4 min. Paid with x402 (USDC on Base, Polygon or Solana) per call; failed or empty calls are never charged.

Input parameters:

- `input` (object, required): The tool's JSON input (see its example in catalog).
- `tier` (string): max = bigger caps, only for the tools listed above.
- `tool` (string, required): Tool id from catalog_read what=prices, e.g. google-maps-scraper.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/bustlll-agent-data-api/agent-data#diagnostics

## Score history

- 2026-10-24: 64
- 2026-10-23: 55

## Common questions

### What is the Agent Data API MCP server?

Agent Data API is an MCP server listed in the public MCP registry as io.github.Bustlll/agent-data-api. Memecoin screener, backtests, exit alerts, wallet traces + web search, enrichment, 50+ tools (x402). This page covers its hosted endpoint (https://agent-data.centorprat.workers.dev/mcp).

### Is the Agent Data API MCP server safe to use?

Agent Data API scores 64 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Agent Data API MCP server expose?

Agent Data API exposes 15 tools: catalog_read, web_search, web_read, company_enrich, email_verify, and 10 more. Their descriptions and schemas cost roughly 3,904 tokens of context every time the server is loaded.

### Does the Agent Data API MCP server require authentication?

No. We connected to Agent Data API without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the Agent Data API MCP server still maintained?

Agent Data API is still listed as active in the MCP registry. We last reached this channel on 24 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://agent-data.centorprat.workers.dev/mcp
- Website: https://agent-data.centorprat.workers.dev/llms.txt
- Changelog RSS feed: https://verifymcp.io/servers/bustlll-agent-data-api/agent-data.xml
- Changelog JSON feed: https://verifymcp.io/servers/bustlll-agent-data-api/agent-data.json
- HTML version of this page: https://verifymcp.io/servers/bustlll-agent-data-api/agent-data