# Agent402.Tools — pay-per-call web tools (remote · agent402.tools)

500+ pay-per-call tools + skill packs. USDC + USDG on 12 chains, or free via proof-of-work.

- Trust score: 77/100 (medium)
- Change this week: +8
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `agent402.tools`: 77/100 (this document), [markdown](https://verifymcp.io/servers/mikeypetrillo-agent402/agent402.md), [page](https://verifymcp.io/servers/mikeypetrillo-agent402/agent402)
- npm · `agent402-mcp`: 46/100, [markdown](https://verifymcp.io/servers/mikeypetrillo-agent402/agent402-mcp.md), [page](https://verifymcp.io/servers/mikeypetrillo-agent402/agent402-mcp)

## Channel facts

- Endpoint: `https://agent402.tools/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.12.4`

## 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 2026-08-03.

- **Endpoint Security**: 80/100
  - 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 is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - 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**: 78/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 2343 tokens (~137/item across 17 items; 17 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 99/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 97% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add --transport http mikeypetrillo-agent402 https://agent402.tools/mcp
```

### Codex

```toml
[mcp_servers.mikeypetrillo-agent402]
url = "https://agent402.tools/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "mikeypetrillo-agent402": {
      "type": "remote",
      "url": "https://agent402.tools/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add mikeypetrillo-agent402 --url https://agent402.tools/mcp --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  mikeypetrillo-agent402:
    url: "https://agent402.tools/mcp"
```

### Other

```json
{
  "mcpServers": {
    "mikeypetrillo-agent402": {
      "type": "http",
      "url": "https://agent402.tools/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.

### 2026-08-03 (score 77, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-08-01 (score 76, +1)

No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-31 (score 75, +3)

- [functional] MCP protocol: Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.
- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 72, +1)

- [security] Tool “get_payment_info” rewrote its description, which is the text the model reads
- [security] Tool “search_tools” rewrote its description, which is the text the model reads
- [security] Tool “call_tool” rewrote its description, which is the text the model reads
- [functional] New prompt “macro-dashboard”
- [functional] New tool “top_x402_sellers”
- [functional] New tool “about_agent402”

### 2026-07-29 (score 71, +1)

- [security] Tool “search_tools” rewrote its description, which is the text the model reads
- [security] Tool “get_payment_info” rewrote its description, which is the text the model reads
- [security] Tool “call_tool” rewrote its description, which is the text the model reads

### 2026-07-28 (score 70, +1)

- [security] Tool “get_payment_info” rewrote its description, which is the text the model reads

### 2026-07-27 (score 69, 0)

- [functional improvement] Stability: unverified → 0.03
- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-26 (score 69)

First indexed and scored.

## MCP tools (17)

### `search_tools` (~370 tokens)

Search the Agent402 tool catalog

BROWSE the catalog: keyword search over Agent402's 527 pay-per-call web tools, returning a LIST of candidates to compare (its counterpart find_tool resolves a task to ONE ready-to-run pick - search explores, find decides). Categories: live market data (stock-quote at $0.003), encoding, crypto, text, time, math, validation, unit conversions, network, browser, PDF, search, memory. 222 pure-CPU tools run free here (proof-of-work - no wallet needed); the rest need a USDC wallet. There is also an OpenAI-compatible LLM gateway at https://agent402.tools/v1 - flat per-call (chat nano $0.003, auto $0.01, embeddings $0.002), no API key: a funded wallet is the account. Beyond this catalog, Agent402 can ROUTE-AND-EXECUTE against the OPEN x402 ecosystem: POST https://agent402.tools/api/route/execute with { task, include:"external" } resolves a PROVEN external seller (real settled volume), pays it on your behalf, and relays the result (marked untrustedContent) - one call to reach thousands of outside tools, from a $0.01 flat fee. That path is wallet-only, so run it with your own wallet via the HTTP API or the stdio agent402-mcp package's route_and_execute tool (this hosted connector holds no wallet). Returns { results, workflows } - each result has slug, price, access, description, inputSchema; run one with call_tool.

Input parameters:

- `limit` (number): Max results (default 10)
- `query` (string, required): What you need, e.g. "decode JWT", "miles to km", "cron next run"

### `find_tool` (~129 tokens)

Resolve a task to the one best Agent402 tool

DECIDE, don't browse: resolve a plain-language task to the single best-matching Agent402 tool, returned call-ready - slug, price, input schema, and a worked example (its counterpart search_tools returns a list of candidates to compare - search explores, find decides). Returns { task, matches } with the top pick first; then run call_tool with the chosen slug + params.

Input parameters:

- `limit` (number): Max results (default 5)
- `task` (string, required): What you want to do, e.g. "extract the article from this url" or "convert miles to km"

### `call_tool` (~157 tokens)

Run an Agent402 tool

Run an Agent402 tool by slug (discover slugs with search_tools or find_tool; params must match that tool's inputSchema). The 222 pure-CPU tools execute free on this hosted connector (rate-limited, no wallet - proof-of-work covers them) and return the tool's JSON result. Wallet-only tools (live market data like stock-quote at $0.003, live search, browser rendering, PDFs, durable memory) return a paid-access setup guide instead - this connector holds no wallet. An unknown slug returns an error pointing back to search_tools.

Input parameters:

- `params` (object): Tool input, matching the tool's inputSchema
- `slug` (string, required): Tool slug, e.g. "unit-convert"

### `get_payment_info` (~196 tokens)

Payment and wallet setup

How paying for Agent402 tools works and how to manage a wallet. This hosted connector holds NO wallet: 222 pure-CPU tools run free here (or solve a proof-of-work puzzle), the rest - including the /v1 OpenAI-compatible LLM gateway (chat nano $0.003, embeddings $0.002; no API key, wallet = account) - settle in USDC via x402. Covers: the free vs paid split, how to configure a funded wallet + per-call and budget spend caps, the rails (USDC on Base, Solana, Polygon, Arbitrum, Monad, Celo, Avalanche, Sei, Optimism, Stellar, or Algorand - or USDG on Robinhood Chain), and checking a wallet's balance/transaction history via the wallet-balances / wallet-transactions tools. Returns { connector, freeTier, pay, spendControls, balanceAndHistory }.

### `generate_hash` (~89 tokens)

Hash

[free, no wallet] Cryptographic hash of a text string. Algorithms: sha256 (default), sha512, sha1, md5. Returns hex and base64 digests. Returns { algo, hex, base64 }.

Input parameters:

- `algo` (string): sha256 | sha512 | sha1 | md5
- `text` (string, required): Text to hash (max 100KB)

### `convert_units` (~184 tokens)

Unit convert

[free, no wallet] Convert a value between units of length, mass, temperature, volume, area, speed, time, data, pressure, energy, power, angle, frequency - every unit the retired convert-* endpoints handled (e.g. miles, kilograms, us-gallons, fahrenheit, psi, kilowatt-hours). Returns { result, from, to }.

Input parameters:

- `from` (string, required): Source unit id - any unit of length, mass, temperature, volume, area, speed, time, data, pressure, energy, power, angle, or frequency (e.g. "miles", "fahrenheit", "us-gallons"). Short aliases like "k…
- `to` (string, required): Target unit id - must be in the same category as `from`.
- `value` (number, required)

### `generate_qr` (~82 tokens)

QR code

[free, no wallet] Generate a QR code PNG from any text or URL. ?text=…&size=256 (128-1024). Returns { contentType, body }.

Input parameters:

- `size` (string): Image width px (128-1024, default 256)
- `text` (string, required): Content to encode (max 2KB)

### `format_json` (~77 tokens)

JSON validate & format

[free, no wallet] Validate, pretty-print, or minify JSON. Returns parse errors with position when invalid. Returns { valid, formatted }.

Input parameters:

- `indent` (number): Spaces of indentation; 0 = minify (default 2)
- `json` (string, required): JSON text to validate/format (max 100KB)

### `decode_jwt` (~61 tokens)

JWT decode

[free, no wallet] Decode a JWT without verification: header, payload, expiry status, and time remaining. (Decoding only - signatures are NOT verified.) Returns { header, payload, expired }.

Input parameters:

- `token` (string, required): The JWT string

### `convert_base64` (~70 tokens)

Base64

[free, no wallet] Base64 encode or decode text. mode: encode (default) or decode. Handles URL-safe base64 on decode. Returns { mode, result }.

Input parameters:

- `mode` (string): encode | decode
- `text` (string, required): Input text (max 100KB)

### `generate_uuid` (~86 tokens)

UUID generator

[free, no wallet] Generate UUIDs. ?version=4 (default, random) or 7 (time-ordered), ?count=1..100. Returns { version, uuids }.

Input parameters:

- `count` (string): How many (1-100, default 1)
- `version` (string): 4 (random) or 7 (time-ordered)

### `parse_csv` (~83 tokens)

CSV to JSON

[free, no wallet] Parse CSV (quoted fields supported) into a JSON array of objects, using the first row as headers (header=false for arrays). Returns { rows, count }.

Input parameters:

- `csv` (string, required): CSV text (max 100KB)
- `delimiter` (string): Default ,
- `header` (boolean): First row is headers (default true)

### `convert_timezone` (~159 tokens)

Timezone convert

[free, no wallet] Convert a datetime from one IANA timezone to another. Accepts ISO 8601, Unix timestamps (seconds or milliseconds), or natural date strings. Returns the converted time in both timezones with UTC offset. ?datetime=2026-06-23T14:00:00&from=America/New_York&to=Asia/Tokyo. Returns { input, from, to, utc }.

Input parameters:

- `datetime` (string, required): Datetime to convert (ISO 8601, Unix timestamp, or natural date string)
- `from` (string, required): Source IANA timezone (e.g. America/New_York)
- `to` (string, required): Target IANA timezone (e.g. Asia/Tokyo)

### `get_wallet_balances` (~194 tokens)

Wallet token balances (indexed)

[wallet-required, $0.002/call] All token balances for any address in one call, from Coinbase's indexed data API - ERC-20 + native on EVM, SPL on Solana; no per-token contract calls, no RPC wrangling. Networks: base, ethereum, base-sepolia, solana, solana-devnet. Symbols/decimals populated for whitelisted tokens (USDC always included). Returns { address, network, balances, count }. This hosted connector holds no wallet, so calling it here returns paid-access setup; run it with a funded wallet via npx agent402-mcp or any x402 client.

Input parameters:

- `address` (string, required): Wallet address - EVM 0x… or Solana base58, matching the network
- `network` (string): base (default) | ethereum | base-sepolia | solana | solana-devnet

### `get_wallet_transactions` (~221 tokens)

Wallet transaction history

[wallet-required, $0.002/call] Return the most recent asset transfers (incoming + outgoing) for a wallet address - native coin, ERC-20, ERC-721, ERC-1155 - already merged and sorted newest first. Each row carries the block, tx hash, counterparty, asset, and decimal value. Cap is 100 per direction; widen the window via `fromBlock` if you need deeper history. Returns { address, network, limit, transfers }. This hosted connector holds no wallet, so calling it here returns paid-access setup; run it with a funded wallet via npx agent402-mcp or any x402 client.

Input parameters:

- `address` (string, required): 0x-prefixed 40-char hex wallet address.
- `fromBlock` (string): Optional starting block in hex (default 0x0 = earliest).
- `limit` (number): Max transfers per direction (1-100, default 25).
- `network` (string): ethereum / base / polygon / arbitrum / optimism (default base).

### `about_agent402` (~63 tokens)

About this Agent402 connector

[free] What this connector is and how to pay for the tools it fronts: catalog size, the free compute tier and its limits, the payment rails accepted, and the machine-readable discovery URLs. Call this first if you need to know whether a wallet is required.

### `top_x402_sellers` (~122 tokens)

Top x402 sellers

[free] Ranked x402 sellers from the on-chain settlement leaderboard: settled call counts, USDC totals and distinct buyers per seller. Use it to find other services in the open x402 ecosystem. This host's own wallet is excluded unless include is set to all.

Input parameters:

- `include` (string): external (default) hides this host's own wallet; all includes it.
- `limit` (integer): How many sellers to return (default 10).
- `sort` (string): Rank by settled USDC (default) or by settled call count.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/mikeypetrillo-agent402/agent402#diagnostics

## Score history

- 2026-08-03: 77
- 2026-08-02: 76
- 2026-08-01: 76
- 2026-07-31: 75
- 2026-07-30: 72
- 2026-07-29: 71
- 2026-07-28: 70
- 2026-07-27: 69
- 2026-07-26: 69

## Links

- Remote endpoint: https://agent402.tools/mcp
- Repository: https://github.com/MikeyPetrillo/Agent402
- Website: https://agent402.tools/
- Changelog RSS feed: https://verifymcp.io/servers/mikeypetrillo-agent402/agent402/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/mikeypetrillo-agent402/agent402/changelog.json
- HTML version of this page: https://verifymcp.io/servers/mikeypetrillo-agent402/agent402