# io.github.89rat/code402 (remote · mcp.code402.dev)

Discover machine-payable APIs, probe x402 payment terms, and run seller operations. Non-custodial.

- Trust score: 87/100 (high trust)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-20

## Components

- remote · `mcp.code402.dev`: 87/100 (this document), [markdown](https://verifymcp.io/servers/89rat-code402/mcp.md), [page](https://verifymcp.io/servers/89rat-code402/mcp)

## Channel facts

- Endpoint: `https://mcp.code402.dev/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.0`

## 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 2026-09-20.

- **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**: 80/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 1276 tokens (~127/item across 10 items; 10 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**: 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**: 75/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "code402_probe_endpoint" implies "send" and declares readOnlyHint instead, contradicting what its own name says it does.
  - An AI judge read all 10 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the io.github.89rat/code402 MCP server?

io.github.89rat/code402 is a hosted endpoint at https://mcp.code402.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 89rat-code402 'https://mcp.code402.dev/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "89rat-code402": {
      "url": "https://mcp.code402.dev/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "89rat-code402": {
      "type": "http",
      "url": "https://mcp.code402.dev/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.89rat-code402]
url = "https://mcp.code402.dev/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "89rat-code402": {
      "type": "remote",
      "url": "https://mcp.code402.dev/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add 89rat-code402 --url 'https://mcp.code402.dev/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  89rat-code402:
    url: "https://mcp.code402.dev/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "89rat-code402": {
      "Transport": "http",
      "Url": "https://mcp.code402.dev/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add 89rat-code402 -t streamable-http -u 'https://mcp.code402.dev/mcp'
```

### Other

```json
{
  "mcpServers": {
    "89rat-code402": {
      "type": "http",
      "url": "https://mcp.code402.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.

### 2026-09-20 (score 87, +1)

- [security] Stability: 0.97 → pass

### 2026-09-17 (score 86, +1)

No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-15 (score 85, +1)

No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-13 (score 84, +1)

No change was recorded against any check on this day. Stability & Change Management went from 73 to 77. That category is still filling its 30-day observation window: 22 days of observed history at the previous scan, 23 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-11 (score 83, +1)

No change was recorded against any check on this day. Stability & Change Management went from 67 to 70. That category is still filling its 30-day observation window: 20 days of observed history at the previous scan, 21 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-09 (score 82, +1)

No change was recorded against any check on this day. Stability & Change Management went from 60 to 63. That category is still filling its 30-day observation window: 18 days of observed history at the previous scan, 19 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-07 (score 81, +1)

No change was recorded against any check on this day. Stability & Change Management went from 53 to 57. That category is still filling its 30-day observation window: 16 days of observed history at the previous scan, 17 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-05 (score 80, +1)

No change was recorded against any check on this day. Stability & Change Management went from 47 to 50. That category is still filling its 30-day observation window: 14 days of observed history at the previous scan, 15 at this one. The score rises as the window fills, whether or not the server changes.

## MCP tools (10)

### `code402_list_services` (~224 tokens)

List machine-payable services

List services on the code402 gateway storefront (GET /v1/services): first-party APIs and third-party seller listings, each with method, URL, USDC price, and network. No account or API key exists or is needed anywhere on the gateway — paid services are accountless, priced per call via x402. Paying for a service requires an x402-capable HTTP client with the buyer's own wallet — this tool only discovers. Returns { total, count, offset, has_more, next_offset?, services: [{ serviceId, name, description, method, url, price, price_usdc_units, network }] }.

Input parameters:

- `compact` (boolean): Token-saving mode: returns one terse line per service (serviceId | price | method | url) instead of full objects. Use for large catalogs.
- `limit` (integer): Maximum services to return (default 20)
- `offset` (integer): Services to skip (pagination, default 0)
- `query` (string): Case-insensitive substring filter on serviceId, name, and description

### `code402_get_service` (~79 tokens)

Get one service

Fetch a single service from the code402 storefront by its serviceId (as returned by code402_list_services). Returns the same service shape as code402_list_services, or an error naming close matches when the id is unknown.

Input parameters:

- `serviceId` (string, required): Exact serviceId, e.g. 'weather' or 'acme-lookup'

### `code402_probe_endpoint` (~98 tokens)

Probe a URL for x402 payment terms

Send an unpaid GET to any public https URL and report whether it answers with a valid x402 402 challenge, plus normalized terms { scheme, network, amount (USDC base units), price (dollars), payTo, asset }. Use before budgeting a payment or to liveness-check a listing. No payment is ever sent. Private/internal addresses are rejected.

Input parameters:

- `url` (string, required): Public https URL of the endpoint to probe

### `code402_gateway_health` (~47 tokens)

Gateway health & network

Check the code402 gateway's /healthz: returns { status, service, network } where network is the settlement chain currently configured (e.g. base-sepolia or base).

### `code402_register_seller` (~182 tokens)

Register a seller

Register a seller on the code402 gateway (or update its name — the payout wallet is immutable once set; re-binding requires EIP-191 proof): POST /v1/sellers with { id, wallet, name }. Payments for the seller's listings settle directly to this wallet (non-custodial). Registration is free; fees are 0.099% of settled volume, invoiced monthly against receipts (accrued until $9). Pro is $9/mo at 0% take. Returns { sellerId, wallet, storefront }. Prove wallet ownership later via the gateway's EIP-191 verify-challenge flow.

Input parameters:

- `id` (string, required): Seller slug, e.g. 'acme'
- `name` (string, required): Human-readable seller name
- `wallet` (string, required): EVM wallet that receives USDC payments

### `code402_create_listing` (~177 tokens)

List an API for sale

Create or update a paid listing for a registered seller: POST /v1/sellers/{sellerId}/services with { serviceId, upstream_url, price_usd, method?, description? }. The gateway then serves the listing at /s/{sellerId}/{serviceId} behind an x402 paywall paying the seller's wallet directly. Returns { listing, paid_endpoint }.

Input parameters:

- `description` (string): What buyers get for the price
- `method` (string): HTTP method of the upstream (default GET)
- `price_usd` (string, required): Price per call, e.g. '$0.05'
- `sellerId` (string, required): Registered seller slug
- `serviceId` (string, required): Listing slug, e.g. 'lookup'
- `upstream_url` (string, required): Public https URL of the API being sold

### `code402_get_seller_analytics` (~73 tokens)

Seller analytics

Fetch a seller's own settlement analytics (free): GET /v1/sellers/{sellerId}/analytics. Returns { total_settled_calls, gross_usd, unique_buyers, by_service: [{ service_id, calls }] }.

Input parameters:

- `sellerId` (string, required): Registered seller slug

### `code402_get_seller_invoice` (~115 tokens)

Seller take-rate invoice

Compute a seller's platform-fee invoice from settled receipts: GET /v1/sellers/{sellerId}/invoice?since={unix_ms}. Returns { tier, transactions, gross_usdc_units, platform_fee_usdc_units, seller_net_usdc_units, fee_bps }. Amounts are integer USDC base units (6 decimals).

Input parameters:

- `sellerId` (string, required): Registered seller slug
- `since` (integer): Unix ms timestamp; only receipts at/after this are invoiced (default 0)

### `code402_trust_check` (~157 tokens)

Trust-check an endpoint or domain

Query the code402 Atlas index for measured trust evidence on an endpoint or domain: probe-verified liveness (probedAlive), evidence tier (probe vs asserted), and ready-to-pay settlement terms (payTo, asset, CAIP-2 network, integer USDC amountUnits) when measured. Use before letting an agent pay any endpoint. Verified evidence is measured by probes, never self-reported. Returns { count, results: [{ title, url, probedAlive, evidence, settlement? }] }.

Input parameters:

- `limit` (integer): Max results (default 10)
- `q` (string, required): Search query — domain, URL, or service name, e.g. 'weather' or 'api.acme.com'

### `code402_get_agent_reputation` (~124 tokens)

Get an agent's signed reputation credential

Fetch an agent's tamper-evident reputation credential from the code402 Atlas rail: GET /v1/agent/{agent_id}/reputation. The credential is an HMAC-signed, expiring (10-minute TTL) bundle over a hash-chained outcome ledger — settled_ok, settled_fail, distinct_hosts, volume_units, reputation_score — verifiable without any shared secret via POST /v1/reputation/verify. Sellers use this to price counterparty risk before serving a new agent.

Input parameters:

- `agent_id` (string, required): Atlas agent id

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/89rat-code402/mcp#diagnostics

## Score history

- 2026-09-20: 87
- 2026-09-19: 86
- 2026-09-18: 86
- 2026-09-17: 86
- 2026-09-16: 85
- 2026-09-15: 85
- 2026-09-14: 84
- 2026-09-13: 84
- 2026-09-12: 83
- 2026-09-11: 83
- 2026-09-10: 82
- 2026-09-09: 82
- 2026-09-08: 81
- 2026-09-07: 81
- 2026-09-06: 80
- 2026-09-05: 80
- 2026-09-04: 79
- 2026-09-03: 79
- 2026-09-02: 79
- 2026-09-01: 78
- 2026-08-31: 78
- 2026-08-30: 77
- 2026-08-29: 77
- 2026-08-28: 76
- 2026-08-27: 58
- 2026-08-26: 58
- 2026-08-25: 57
- 2026-08-24: 75
- 2026-08-23: 74
- 2026-08-22: 73

## Common questions

### What is the io.github.89rat/code402 MCP server?

io.github.89rat/code402 is an MCP server listed in the public MCP registry as io.github.89rat/code402. Discover machine-payable APIs, probe x402 payment terms, and run seller operations. Non-custodial. This page covers its hosted endpoint (https://mcp.code402.dev/mcp).

### Is the io.github.89rat/code402 MCP server safe to use?

io.github.89rat/code402 scores 87 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 io.github.89rat/code402 MCP server expose?

io.github.89rat/code402 exposes 10 tools: code402_list_services, code402_get_service, code402_probe_endpoint, code402_gateway_health, code402_register_seller, and 5 more. Their descriptions and schemas cost roughly 1,276 tokens of context every time the server is loaded.

### Does the io.github.89rat/code402 MCP server require authentication?

No. We connected to io.github.89rat/code402 without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the io.github.89rat/code402 MCP server still maintained?

io.github.89rat/code402 is still listed as active in the MCP registry. We last reached this channel on 20 September 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://mcp.code402.dev/mcp
- Repository: https://github.com/89rat/m2m-exchange
- Website: https://code402.dev/
- Changelog RSS feed: https://verifymcp.io/servers/89rat-code402/mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/89rat-code402/mcp.json
- HTML version of this page: https://verifymcp.io/servers/89rat-code402/mcp