coffee.402/mcp
NPM · 402COFFEE-MCP · SCANNED SEP 20
Trust layer for agent payments (x402, Base): verify agents, risk scores, signed escrow verdicts.
Available components
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security99
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- No install/post-install scripts declared.Pass
- 32 of 115 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency19
- Repository check failed: no source repository is declared. See how to fix → View diagnostics → Fail
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 71 days ago).Pass
- Security-disclosure policy not yet verified: we couldn't inspect the source repository.Unverified
Schema Quality & AI Usability80
- AI-judged instruction clarity (excellent).Pass
- Tool/resource definitions use about 826 tokens (~82/item across 10 items; 10 tools + 0 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management93
- Stability observed for 28 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage94
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 82% of tool parameters carry a description.Partial
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 10 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 10 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
How do I install the coffee.402/mcp server?
coffee.402/mcp runs locally as an npm package, launched with npx -y 402coffee-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · 402coffee-mcp
claude mcp add coffee-402-mcp -- npx -y 402coffee-mcp
{
"mcpServers": {
"coffee-402-mcp": {
"command": "npx",
"args": [
"-y",
"402coffee-mcp"
]
}
}
} {
"servers": {
"coffee-402-mcp": {
"command": "npx",
"args": [
"-y",
"402coffee-mcp"
]
}
}
} codex mcp add coffee-402-mcp -- npx -y 402coffee-mcp
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"coffee-402-mcp": {
"type": "local",
"command": [
"npx",
"-y",
"402coffee-mcp"
],
"enabled": true
}
}
} openclaw mcp add coffee-402-mcp --command npx --arg -y --arg 402coffee-mcp
mcp_servers:
coffee-402-mcp:
command: "npx"
args: ["-y", "402coffee-mcp"] {
"McpServers": {
"coffee-402-mcp": {
"Transport": "stdio",
"Command": "npx",
"Arguments": [
"-y",
"402coffee-mcp"
]
}
}
} assistant mcp add coffee-402-mcp -t stdio -c npx -a -y 402coffee-mcp
{
"mcpServers": {
"coffee-402-mcp": {
"command": "npx",
"args": [
"-y",
"402coffee-mcp"
]
}
}
} Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 18 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.
- 16 Sept 26 −2
- Stability: pass → 0.80 functional
- 15 Sept 26 0
- Stability: 0.97 → pass security
- 14 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.
- 12 Sept 26 +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.
- 10 Sept 26 +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.
- 9 Sept 26 −3
- Stability: pass → 0.80 functional
- 8 Sept 26 0
- Stability: 0.97 → pass security
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 20 Sept 2026 · Analysed npm/402coffee-mcp@0.1.1
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | npm |
Background: How many MCP packages publish verified provenance →
Dependencies 115 packages
| Packages resolved | 115 |
|---|---|
| Stale | 31 |
| No linked repository | 1 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
arbiter_policy ~45
FREE — the published 402.coffee arbiter policy: scope (machine-verifiable categories only), verdict semantics, evidence rules, neutrality, corrections, fees, signatures, liability.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
arbiter_verify ~195
PAID $0.25 ($0.60 scored) — get a SIGNED release/refund/escalate delivery verdict from the 402.coffee external arbiter for a machine-verifiable claim. Non-custodial: your escrow executes the verdict. Categories: http-delivery {url, expect_status?, expect_sha256?, min_bytes?, expect_contains?} · payload-hash {payload_text|payload_b64, expected_sha256} · ci-status {repo, commit_sha}. Scored variant embeds both parties' 402.coffee risk tiers.
| Name | Type | Req | Description |
|---|---|---|---|
| category | string | yes | – |
| conditions | object | yes | the pre-agreed verification conditions for the category |
| deal_ref | string | – | your opaque deal/escrow reference (echoed into the signed verdict) |
| parties | object | – | – |
| scored | boolean | – | true = $0.60 scored variant with parties' risk tiers |
No output schema declared.
No examples provided.
behavioural_test_info ~97
FREE — how to run the behavioural conformance tests (scam-resistance / recipient-awareness, $0.60 total each). These are ADVERSARIAL: a naive auto-paying client will sign the bait and FAIL — which is exactly what they measure — so they are not run by this MCP server's auto-payer. Returns the step-by-step flow and the one-command path.
| Name | Type | Req | Description |
|---|---|---|---|
| test | string | yes | which behavioural test |
No output schema declared.
No examples provided.
certify ~99
PAID $0.25 (basic) / $0.75 (suite) — certify THIS wallet's x402 client by completing a real payment against 402.coffee's conformance harness. Returns a public certificate URL + README badge. The behavioural tests (scam/recipient) are multi-step and adversarial — use behavioural_test_info for those.
| Name | Type | Req | Description |
|---|---|---|---|
| test | string | – | basic ($0.25) or full suite ($0.75) |
No output schema declared.
No examples provided.
check_credential ~69
FREE — fetch a wallet's portable W3C-VC-shaped credential AND verify its Ed25519 signature locally against 402.coffee's published JWKS (offline-verifiable proof it was issued by 402.coffee and not altered).
| Name | Type | Req | Description |
|---|---|---|---|
| wallet | string | yes | 0x wallet address |
No output schema declared.
No examples provided.
escrow_info ~66
FREE — the 402.coffee full-escrow product for merchants: route x402 sales through the on-chain x402r operator, funds held in AuthCaptureEscrow until the arbiter verifies delivery (release minus 1% or refund). Contracts, fee policy, integration snippet.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
list_tests ~50
FREE — the machine-readable 402.coffee menu: every conformance test, price, route, and payoff, plus the counterparty products (score, escrow, arbiter). No wallet, no spend.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
score_batch ~47
PAID $0.50 — risk scores for up to 25 wallets in one payment ($0.02/wallet effective).
| Name | Type | Req | Description |
|---|---|---|---|
| wallets | array | yes | up to 25 wallet addresses |
No output schema declared.
No examples provided.
score_wallet ~82
PAID $0.10 — deterministic 0–100 payment-risk score for any wallet: certified behaviour (scam-resistance, recipient-awareness) + real on-chain USDC payment history, with tier A–F, itemized evidence and flags. For deciding whether to transact with an agent.
| Name | Type | Req | Description |
|---|---|---|---|
| wallet | string | yes | 0x wallet address to score |
No output schema declared.
No examples provided.
verify_agent ~76
FREE — check whether a wallet has current 402.coffee conformance certs (pays correctly, refuses scams, checks recipients) plus a free on-chain USDC payment-activity summary. The one-call trust check before you transact with an agent.
| Name | Type | Req | Description |
|---|---|---|---|
| wallet | string | yes | 0x wallet address of the agent to check |
No output schema declared.
No examples provided.
What is the coffee.402/mcp server?
coffee.402/mcp is listed in the public MCP registry as coffee.402/mcp. Trust layer for agent payments (x402, Base): verify agents, risk scores, signed escrow verdicts. This page covers its npm package (402coffee-mcp).
Is the coffee.402/mcp server safe to use?
coffee.402/mcp scores 78 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 September 2026. It declares no install or post-install scripts. 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 coffee.402/mcp server expose?
coffee.402/mcp exposes 10 tools: verify_agent, check_credential, list_tests, score_wallet, score_batch, and 5 more. Their descriptions and schemas cost roughly 826 tokens of context every time the server is loaded.
Is the coffee.402/mcp server still maintained?
coffee.402/mcp 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.
What licence is the coffee.402/mcp server under?
coffee.402/mcp declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.