PipRail
NPM · @PIPRAIL/MCP · SCANNED OCT 3
Budget-bound x402 payment wallet for AI agents — pays HTTP 402 URLs, capped locally. No backend.
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 Security98
- 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
- 31 of 110 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency48
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- 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 24 days ago).Pass
- Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability57
- 33% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Partial
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 1542 tokens (~154/item across 10 items; 8 tools + 2 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management83
- Stability observed for 25 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
- Structured output schemas are declared (38% of tools); any adoption earns full credit.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
- An AI judge read all 9 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 PipRail MCP server?
PipRail runs locally as an npm package, launched with npx -y @piprail/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 · @piprail/mcp
claude mcp add piprail-mcp -- npx -y @piprail/mcp
{
"mcpServers": {
"piprail-mcp": {
"command": "npx",
"args": [
"-y",
"@piprail/mcp"
]
}
}
} {
"servers": {
"piprail-mcp": {
"command": "npx",
"args": [
"-y",
"@piprail/mcp"
]
}
}
} codex mcp add piprail-mcp -- npx -y @piprail/mcp
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"piprail-mcp": {
"type": "local",
"command": [
"npx",
"-y",
"@piprail/mcp"
],
"enabled": true
}
}
} openclaw mcp add piprail-mcp --command npx --arg -y --arg @piprail/mcp
mcp_servers:
piprail-mcp:
command: "npx"
args: ["-y", "@piprail/mcp"] {
"McpServers": {
"piprail-mcp": {
"Transport": "stdio",
"Command": "npx",
"Arguments": [
"-y",
"@piprail/mcp"
]
}
}
} assistant mcp add piprail-mcp -t stdio -c npx -a -y @piprail/mcp
{
"mcpServers": {
"piprail-mcp": {
"command": "npx",
"args": [
"-y",
"@piprail/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.
- 3 Oct 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.
- 2 Oct 26 −3
- Stability: pass → 0.80 functional
- 1 Oct 26 0
- Stability: 0.97 → pass security
- 30 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.
- 28 Sept 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 27 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.
- 25 Sept 26 −3
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 24 Sept 26 +1
- 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 3 Oct 2026 · Analysed npm/@piprail/mcp@0.10.0
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 110 packages
| Packages resolved | 110 |
|---|---|
| Stale | 31 |
| 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 →
piprail_budget ~129
Read how much of your spend budget and time leash is left — per (network, asset) remaining, the cross-token GRAND TOTAL per denomination (e.g. how much USD you can still spend across every stablecoin and chain), the payment-count leash, the session time envelope, and your spend so far. Use it in Mode A (headless) to self-check BEFORE paying, so you never discover the leash by hitting a decline. Read-only; moves no funds. NOTE: the time envelope is in-memory for THIS process; the money/count totals persist only if a spend store is configured.
Input schema present but exposes no named parameters.
Structured output declared, but exposes no named fields.
No examples provided.
piprail_discover ~330
Find x402 payment-gated resources on the OPEN indexes (a phone book of payable APIs) WITHOUT paying. Use it to answer "what can I buy?" — search by topic, then quote/plan/pay a chosen one. By default returns only resources payable on your wallet's chain (network='self'); pass 'any' for every chain. Results are cross-scheme: ALWAYS call piprail_quote_payment on a chosen resource (it re-checks the live price) before piprail_pay_request.
| Name | Type | Req | Description |
|---|---|---|---|
| asset | string | – | Keep only resources paying in this token symbol, e.g. 'USDC'. |
| category | string | – | Keep ONLY this category, e.g. 'ai', 'finance', 'data' (strict). |
| limit | number | – | Max results to fetch per index (default 20). |
| maxPrice | number | – | Drop results advertised above this USD price. |
| minReliability | number | – | Drop results below this health score (0–100); unscored pass. |
| network | string | – | CAIP-2 id, 'self' (your chain — default), or 'any' (all chains). |
| query | string | – | Free-text topic to search for (optional). Multi-word queries are fanned out per word and results are ranked by relevance, so "crypto price feed" finds the best matches even when no single listing con… |
| sort | string | – | Ordering. Default 'relevance' with a query, else first-seen. |
| verified | boolean | – | Prefer verified listings (402 Index). |
No output schema declared.
No examples provided.
piprail_guide ~78
Read the PipRail agent contract — the quote → plan → pay loop, how to read a refusal (and which declines are TERMINAL), the never-re-pay rule for broadcast-but-unconfirmed payments, and Mode A (headless) vs Mode B (supervised). Read-only; call it once if unsure how to use these tools.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
piprail_pay_request ~168
Fetch an x402 payment-gated URL, automatically making the required payment if needed (subject to the spend policy + approval hook). Pays whichever rail the client is configured for — PipRail's backendless on-chain rail, or, when enabled, the standard `exact` rail (where the buyer signs and the server settles, so no buyer gas). Returns the HTTP status, the response body, and a payment receipt if one settled. If the payment is refused by policy or the approval hook, returns { declined: true, reason } — no funds moved.
| Name | Type | Req | Description |
|---|---|---|---|
| body | object|string | – | Optional request body for POST/PUT (a JSON object or a string). |
| method | string | – | HTTP method, default 'GET'. |
| url | string | yes | Full URL to fetch. |
No output schema declared.
No examples provided.
piprail_plan_payment ~124
Check whether you CAN pay an x402-gated URL before paying. Reads your wallet balance, native gas, and whether the recipient can receive — across every rail the URL offers on your chain — and returns { gated, payable, best, options, fundingHint }. payable:false means do NOT attempt the payment; fundingHint says exactly what to top up. Call this before piprail_pay_request so you never commit to a payment you cannot finish. Returns { gated: false } when no payment is needed.
| Name | Type | Req | Description |
|---|---|---|---|
| url | string | yes | Full URL of the gated resource. |
Structured output declared, but exposes no named fields.
No examples provided.
piprail_quote_payment ~81
Get the price of an x402 payment-gated URL WITHOUT paying. Returns the amount, token, chain, recipient, and whether it is within the spend policy. Returns { gated: false } when the URL needs no payment. Call this first to decide whether a resource is worth buying.
| Name | Type | Req | Description |
|---|---|---|---|
| url | string | yes | Full URL of the gated resource. |
Structured output declared, but exposes no named fields.
No examples provided.
piprail_register ~394
List an x402 payment-gated resource YOU run on the open indexes so other agents can discover it. Default target is 402 Index — no auth, no signature, no payment; a self-registered listing is pending review (verify your domain on 402index.io for instant approval). Returns one outcome per index ({ source, ok, detail, visibility, note }); a step the chain can't satisfy comes back ok:false with the reason. Moves no funds; nothing is PipRail-hosted. NOTE: index/agent payers are overwhelmingly standard `exact` clients — a default onchain-proof-only gate gets listed but they cannot pay it, so add an `exact` rail (and set the gate's `discovery` option, required for x402scan) to be usefully discoverable AND payable.
| Name | Type | Req | Description |
|---|---|---|---|
| asset | string | – | Payment asset symbol, e.g. 'USDC' (metadata). |
| category | string | – | A category, e.g. 'ai', 'finance', 'data' — the top findability field (most listings have none). |
| contactEmail | string | – | Contact email for the listing. |
| description | string | – | What the resource offers. Pack the words agents will search for INTO this text — index search is literal, so a keyword that isn't in the name/description won't be found. |
| name | string | – | Display name (defaults to the host). |
| network | string | – | Network slug to advertise, e.g. 'base' (defaults to the paying chain). Set it when registering from a multi-chain wallet so the listing names the right chain. |
| priceUsd | number | – | Advertised price in USD (metadata). |
| provider | string | – | Who runs the resource (provider/org name). |
| tags | array | – | Keywords; folded into the description so they're searchable. |
| url | string | yes | Full URL of the resource to list. |
No output schema declared.
No examples provided.
piprail_verify_receipt ~224
Re-verify a PipRail VERIFIABLE RECEIPT against the chain — confirm a payment REALLY settled (the funds provably moved to payTo for AT LEAST the stated amount) WITHOUT trusting whoever handed you the receipt. Read-only and WALLET-FREE: pass the PipRailReceipt JSON (from a prior piprail_pay_request `verifiableReceipt`, or any third party). Returns { ok, onChain:{payTo,asset,amount,payer}, matchesClaims, ageSeconds, error? }: `ok` = the chain confirms the settlement; `onChain.payer` is RE-DERIVED from the tx and `matchesClaims:false` means the receipt forged the payer; `amount` is a verified lower bound. Pass `rpcUrl` for a chain outside the common presets.
| Name | Type | Req | Description |
|---|---|---|---|
| receipt | object | yes | The PipRailReceipt JSON ({ piprail, receipt, resource, decimals? }) to re-verify. |
| rpcUrl | string | – | Optional RPC URL for the receipt's chain (required for chains outside the common presets). |
No output schema declared.
No examples provided.
What is the PipRail MCP server?
PipRail is an MCP server listed in the public MCP registry as io.github.piprail/mcp. Budget-bound x402 payment wallet for AI agents, pays HTTP 402 URLs, capped locally. No backend. This page covers its npm package (@piprail/mcp).
Is the PipRail MCP server safe to use?
PipRail scores 79 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 3 October 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 PipRail MCP server expose?
PipRail exposes 8 tools: piprail_discover, piprail_quote_payment, piprail_plan_payment, piprail_pay_request, piprail_register, and 3 more. Their descriptions and schemas cost roughly 1,528 tokens of context every time the server is loaded.
Is the PipRail MCP server still maintained?
PipRail is still listed as active in the MCP registry. We last reached this channel on 3 October 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 PipRail MCP server under?
PipRail declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.