AgentPay — trust routing + spend caps for x402 agents
NPM · @ROMUDILLE/AGENTPAY-MCP · 2 COMPONENTS
Buyer-side trust oracle + capped sessions for x402 agents: verified_route, receipts, 17 free tools.
Available components
Last scanned (18 hours ago)
Scores higher than 82% of npm servers
Category Crypto and Web3
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
- 30 of 94 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency45
- 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 1 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability74
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 776 tokens (~194/item across 4 items; 4 tools + 0 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 Management100
- No destabilizing schema changes in the last 30 days.Pass
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
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 4 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 4 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
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 Nov 26 +15
- Malware scan: unverified → pass ▲ security
- 2 Nov 26 −15
- Malware scan: pass → unverified ▼ security
- Schema quality: 217 → 194 ▲ functional
- Package version: 2.7.3 → 2.8.0 functional
- 30 Oct 26 +1
- Stability: 0.97 → pass security
- 28 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.
- 26 Oct 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.
- 24 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 77 to 80. That category is still filling its 30-day observation window: 23 days of observed history at the previous scan, 24 at this one. The score rises as the window fills, whether or not the server changes.
- 22 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 70 to 73. That category is still filling its 30-day observation window: 21 days of observed history at the previous scan, 22 at this one. The score rises as the window fills, whether or not the server changes.
- 20 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 63 to 67. That category is still filling its 30-day observation window: 19 days of observed history at the previous scan, 20 at this one. The score rises as the window fills, whether or not the server changes.
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 4 Nov 2026 · Analysed npm/@romudille/agentpay-mcp@2.8.0
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 94 packages
| Packages resolved | 94 |
|---|---|
| Stale | 30 |
| 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 →
estimate_plan ~155
Price a multi-tool plan BEFORE spending anything. Submits the tool calls an agent intends to make to the gateway's free /v1/plan/estimate and returns per-step cost, total, a fits-budget verdict, and a cheaper alternative per paid step. No payment, no wallet needed. Use when: planning a multi-step task with paid tools, "what would this cost", "does this plan fit my budget", or before committing a Session cap.
| Name | Type | Req | Description |
|---|---|---|---|
| budget | number | – | Optional USDC budget for the fits_budget verdict, e.g. 0.05 |
| steps | array | yes | Tool names to price, in order, e.g. ["token_price", "dune_query", "session_create"] |
No output schema declared.
No examples provided.
route ~202
Legacy alias of verified_route (kept for back-compat). Find and judge the best paid x402 tool for a need, within a budget. Discovers across Coinbase Bazaar, drops stubs (no schema / factory clones), ranks survivors by real usage (unique payers × 3 + calls + recency bonus), enforces the budget, price- tiebreaks quality-equal candidates. Returns ranked candidates + a recommendation + ready-to-pay details. Advise-only — no payment happens here. Prefer verified_route (same vetting, matches the paid tool + Bazaar listing). Use when: "which x402 tool for X", "find a paid API for X under $Y".
| Name | Type | Req | Description |
|---|---|---|---|
| budget | number | – | Maximum USDC per call (default 0.01). Tools priced above this are excluded. |
| need | string | yes | What capability you need, e.g. "funding rates", "token security", "DeFi TVL" |
No output schema declared.
No examples provided.
session_cap ~124
The hard spending cap of this AgentPay session and what has been spent so far, with the wallets that pay. Pass max_usd to LOWER the cap for this session (or restore it, up to the configured AGENTPAY_MAX_SPEND ceiling); raising the ceiling needs a restart. Call it before the first paid call so the user can confirm or change the cap, and whenever they ask what the agent may spend. Free, local.
| Name | Type | Req | Description |
|---|---|---|---|
| max_usd | number | – | New session cap in USD, at most the configured ceiling and not below what is already spent. |
No output schema declared.
No examples provided.
verified_route ~295
Buyer-side trust oracle for the x402 marketplace: "I need X, budget $Y — which tool is real?" Vets Coinbase Bazaar (discover → drop stubs/factory clones → rank by real unique-payer usage → budget-gate). This MCP runs the FREE single-query PREVIEW: it returns the vetted pick (name + usage stats + why) and survivor count to PROVE a real provider exists, but WITHHOLDS the provider URL + ready-to-pay x402 challenge. To get those — plus the full multi-query sweep + usage-based sybil-collapse + trust allowlist — fund this install's wallet with USDC on Base and set AGENTPAY_ENABLE_PAID=1 (the paid verified_route costs $0.01), or use the agentpay-x402 SDK. No payment happens while paid mode is off. Use when: "which x402 tool for X", "find a real/trustworthy paid API for X", "avoid a scam or dead stub", "vet this provider before I pay".
| Name | Type | Req | Description |
|---|---|---|---|
| budget_usd | number | – | Max USDC the agent will pay the downstream tool per call (default 0.01). |
| chain | string | – | Optional chain filter: "base", "arbitrum". Empty = all chains. |
| need | string | yes | What you need, e.g. "dex pair liquidity", "funding rates", "token security" |
No output schema declared.
No examples provided.
How do I install the AgentPay — trust routing + spend caps for x402 agents MCP server?
AgentPay — trust routing + spend caps for x402 agents runs locally as an npm package, launched with npx -y @romudille/agentpay-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 · @romudille/agentpay-mcp
claude mcp add romudille-bit-agentpay -- npx -y @romudille/agentpay-mcp
What is the AgentPay — trust routing + spend caps for x402 agents MCP server?
AgentPay — trust routing + spend caps for x402 agents is an MCP server listed in the public MCP registry as io.github.romudille-bit/agentpay. Buyer-side trust oracle + capped sessions for x402 agents: verified_route, receipts, 17 free tools. This page covers its npm package (@romudille/agentpay-mcp).
Is the AgentPay — trust routing + spend caps for x402 agents MCP server safe to use?
AgentPay — trust routing + spend caps for x402 agents scores 84 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 4 November 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 AgentPay — trust routing + spend caps for x402 agents MCP server expose?
AgentPay — trust routing + spend caps for x402 agents exposes 4 tools: verified_route, route, estimate_plan, session_cap. Their descriptions and schemas cost roughly 776 tokens of context every time the server is loaded.
Is the AgentPay — trust routing + spend caps for x402 agents MCP server still maintained?
AgentPay — trust routing + spend caps for x402 agents is still listed as active in the MCP registry. We last reached this channel on 4 November 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 AgentPay — trust routing + spend caps for x402 agents MCP server under?
AgentPay — trust routing + spend caps for x402 agents declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.