# What Agents Buy (remote · whatagentsbuy.com)

Independent measured reviews of x402 API sellers: pre-payment verdicts and accuracy grades.

- Trust score: 77/100 (medium)
- Change this week: 0
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-04

## Components

- remote · `whatagentsbuy.com`: 77/100 (this document), [markdown](https://verifymcp.io/servers/com-whatagentsbuy-whatagentsbuy/whatagentsbuy.md), [page](https://verifymcp.io/servers/com-whatagentsbuy-whatagentsbuy/whatagentsbuy)

## Channel facts

- Endpoint: `https://whatagentsbuy.com/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 2026-10-04.

- **Endpoint Security**: 63/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 7 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - 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**: 68/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 1440 tokens (~205/item across 7 items; 7 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 100/100
  - No destabilizing schema changes in the last 30 days.
- **Tool Coverage**: 95/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 85% 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 7 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 8 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 60/100
  - Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28.

## Install

### How do I install the What Agents Buy MCP server?

What Agents Buy is a hosted endpoint at https://whatagentsbuy.com/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 com-whatagentsbuy-whatagentsbuy 'https://whatagentsbuy.com/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "com-whatagentsbuy-whatagentsbuy": {
      "url": "https://whatagentsbuy.com/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "com-whatagentsbuy-whatagentsbuy": {
      "type": "http",
      "url": "https://whatagentsbuy.com/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.com-whatagentsbuy-whatagentsbuy]
url = "https://whatagentsbuy.com/mcp"
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add com-whatagentsbuy-whatagentsbuy --url 'https://whatagentsbuy.com/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-whatagentsbuy-whatagentsbuy:
    url: "https://whatagentsbuy.com/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "com-whatagentsbuy-whatagentsbuy": {
      "Transport": "http",
      "Url": "https://whatagentsbuy.com/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-whatagentsbuy-whatagentsbuy -t streamable-http -u 'https://whatagentsbuy.com/mcp'
```

### Other

```json
{
  "mcpServers": {
    "com-whatagentsbuy-whatagentsbuy": {
      "type": "http",
      "url": "https://whatagentsbuy.com/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.

### 2026-09-28 (score 77, 0)

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

### 2026-09-25 (score 77, +12)

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

### 2026-09-18 (score 65, 0)

- [security] The server rewrote its instructions, which are the text every model session reads

### 2026-09-16 (score 65, +1)

No change was recorded against any check on this day. Stability & Change Management went from 6 to 9.

### 2026-09-14 (score 64, +1)

No change was recorded against any check on this day. Stability & Change Management went from 0 to 3.

### 2026-09-10 (score 63, −2)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “check_before_paying” rewrote its description, which is the text the model reads
- [functional regression] MCP protocol: pass → fail
- [functional] MCP protocol version: 2025-11-25 → 2025-06-18
- [functional] Server version: 1.0.0 → 1.1.0
- [cosmetic] “find_api” added an optional parameter “allowed_verdicts”

### 2026-09-08 (score 65, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “check_before_paying” rewrote its description, which is the text the model reads

### 2026-08-31 (score 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “look_up_seller” rewrote its description, which is the text the model reads
- [security] Tool “rank_sellers” rewrote its description, which is the text the model reads

## MCP tools (7)

### `find_api` (~247 tokens)

Find a payable API for a task

USE WHEN you need an API that does something and want payable options. Searches the whole x402 market for what you describe and returns a ranked, pre-vetted shortlist, proven-accurate sellers first, then payment-safety, then price. Covers every reachable endpoint, not just ones we have bought from. Next step: check_before_paying on your pick, then read the payTo from the live 402 and sign against it.

Input parameters:

- `allowed_verdicts` (array): Optional policy filter: only return sellers whose current preflight verdict is in this list, e.g. ["CLEAR"]. Default: no filter, every result carries its verdict so you can decide.
- `limit` (integer): How many results (default 8, max 25)
- `max_price_usdc` (number): Optional ceiling on the per-call price in USDC
- `min_reliability` (integer): Optional floor on the reliability score 0-100 (default 0 = no floor; the whole reachable market)
- `task` (string, required): What you need, in words or keywords, e.g. 'validate an email address', 'BTC price', 'geocode an address'

### `check_before_paying` (~257 tokens)

The one check before your agent pays

USE WHEN your agent is about to pay an x402 API and you want to know if it is safe and worth it. Returns one verdict for a URL or host in the `verdict` field (gate on that; `light` is the same decision as a colour, for display): CLEAR (nothing alarming), HOLD (pay but resolve the reasons), ABORT (do not pay without checking the live 402), UNRATED (no data). Also returns a confidence tier (verified = a payment to this seller settled AND produced a gradeable result, checked = free probe measured) and its payment history. Folds live price and payTo honesty, phantom paywalls, delivery receipts, and the wash/real-demand read into that one light. Pass detail:true for the full read. Whatever it says, still read the payTo and amount out of the live 402 and sign against those. (Formerly named preflight.)

Input parameters:

- `detail` (boolean): Include the full payment-safety detail (live-402 honesty, demand shape, grades). Default false.
- `url` (string, required): Full URL or bare hostname, e.g. https://blockrun.ai/api/v1/exa/search or blockrun.ai

### `look_up_seller` (~128 tokens)

Everything known about one seller

USE WHEN you have a specific seller host and want its full track record. Returns every grade earned by actually paying it, what was quoted versus charged, whether goods arrived, its settlement volume, and its Organic Demand Score with the demand-shape read (is the volume real independent demand, or one wallet supplying almost all of it). The deep dossier on one seller; for a quick go/no-go before paying, use check_before_paying instead. (Formerly named get_service.)

Input parameters:

- `host` (string, required): Hostname, e.g. blockrun.ai or api.bitrefill.com

### `rank_sellers` (~113 tokens)

The leaderboard: biggest, or most real

USE WHEN you want a ranked list of sellers across the market. by='revenue' ranks by raw USDC received (who is busy); by='real_demand' ranks by Organic Demand Score (whose money comes from many independent wallets rather than one wallet supplying almost all of it). The two disagree often, and the disagreement is the point. For accuracy ranking within an objective category, use rank_by_accuracy. (Formerly named top_services.)

Input parameters:

- `by` (string)
- `limit` (integer)

### `rank_by_accuracy` (~155 tokens)

Who returns the most accurate value in a category

USE WHEN a category has an objective right answer (crypto-price, stock-price, fx-rate, gas-price, wallet-balance, weather) and you want the sellers we PAID ranked by how close their returned value was to a primary source that cannot be a reseller (exchange median, chain balanceOf, ECB rates, FMP quote). Top rows are the cheapest accurate sellers. Call with no category to list the available ones. (Formerly named most_accurate.)

Input parameters:

- `category` (string): One of: crypto-price, stock-price, fx-rate, gas-price, wallet-balance, weather. Omit to list categories.
- `limit` (integer): How many results (default 10, max 50)

### `market_size` (~105 tokens)

How big is the x402 market

USE WHEN asked how big x402 is, whether it is growing, or what settled recently. Returns both what actually settled on Base over the last day (from chain logs, per tracked seller) and the live market pulse (24h volume and payments with day-over-day change, a 7-day series, and stablecoin circulation). All measured from chain, not registry counters, which are not demand and can be bought. (Merges the former market_summary and market_pulse.)

### `known_payment_traps` (~82 tokens)

How agents lose money paying APIs

USE WHEN writing payment code, or before trusting an unfamiliar seller. The field notes: each is a specific way an agent paying an API loses money or is misled, what it cost to learn, and what to do instead. (Formerly named list_traps.)

Input parameters:

- `query` (string): Optional filter, e.g. 'price', 'delivery'

## Diagnostics

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

## Score history

- 2026-10-04: 77
- 2026-10-03: 77
- 2026-10-02: 77
- 2026-10-01: 77
- 2026-09-30: 77
- 2026-09-29: 77
- 2026-09-28: 77
- 2026-09-27: 77
- 2026-09-26: 77
- 2026-09-25: 77
- 2026-09-24: 65
- 2026-09-23: 65
- 2026-09-22: 65
- 2026-09-21: 65
- 2026-09-20: 65
- 2026-09-19: 65
- 2026-09-18: 65
- 2026-09-17: 65
- 2026-09-16: 65
- 2026-09-15: 64
- 2026-09-14: 64
- 2026-09-13: 63
- 2026-09-12: 63
- 2026-09-11: 63
- 2026-09-10: 63
- 2026-09-09: 65
- 2026-09-08: 65
- 2026-09-07: 65
- 2026-09-06: 65
- 2026-09-05: 65

## Common questions

### What is the What Agents Buy MCP server?

What Agents Buy is an MCP server listed in the public MCP registry as com.whatagentsbuy/whatagentsbuy. Independent measured reviews of x402 API sellers: pre-payment verdicts and accuracy grades. This page covers its hosted endpoint (https://whatagentsbuy.com/mcp).

### Is the What Agents Buy MCP server safe to use?

What Agents Buy scores 77 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 What Agents Buy MCP server expose?

What Agents Buy exposes 7 tools: find_api, check_before_paying, look_up_seller, rank_sellers, rank_by_accuracy, and 2 more. Their descriptions and schemas cost roughly 1,087 tokens of context every time the server is loaded.

### Does the What Agents Buy MCP server require authentication?

No. We connected to What Agents Buy without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the What Agents Buy MCP server still maintained?

What Agents Buy is still listed as active in the MCP registry. We last reached this channel on 4 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://whatagentsbuy.com/mcp
- Repository: https://github.com/neilkpatel/whatagentsbuy
- Website: https://whatagentsbuy.com/
- Changelog RSS feed: https://verifymcp.io/servers/com-whatagentsbuy-whatagentsbuy/whatagentsbuy.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-whatagentsbuy-whatagentsbuy/whatagentsbuy.json
- HTML version of this page: https://verifymcp.io/servers/com-whatagentsbuy-whatagentsbuy/whatagentsbuy