Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

io.github.m9labs-railscope/verantis-mcp

PYPI · VERANTIS-MCP · 2 COMPONENTS · SCANNED AUG 20

Verified directory for machine payments (x402 & MPP): check services and wallets before agents pay.

67 Trust /100
Trust breakdown (6 categories)

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 →

Supply Chain Security100
  • No malware found by supply-chain analysis.Pass
  • No known CVEs affecting this package version or its production dependencies.Pass
  • Runs hatchling.build at install time, a recognised native-build step with no shell scripting around it. View diagnostics → Pass
  • No production dependencies, so there is no dependency health to assess. View diagnostics → Pass
Provenance & Transparency32
Schema Quality & AI Usability72
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 678 tokens (~169/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 Management10
  • Stability observed for 3 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
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Install

Add this component to your MCP client. Where a client-specific snippet is available, pick your client below and copy it straight into your config; otherwise use the connection detail shown.

pypi · verantis-mcp

# add to Claude Code
claude mcp add m9labs-railscope-verantis-mcp -- uvx verantis-mcp
# add to Codex CLI
codex mcp add m9labs-railscope-verantis-mcp -- uvx verantis-mcp
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "m9labs-railscope-verantis-mcp": {
      "type": "local",
      "command": [
        "uvx",
        "verantis-mcp"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add m9labs-railscope-verantis-mcp --command uvx --arg verantis-mcp
# ~/.hermes/config.yaml
mcp_servers:
  m9labs-railscope-verantis-mcp:
    command: "uvx"
    args: ["verantis-mcp"]
// mcp.json
{
  "mcpServers": {
    "m9labs-railscope-verantis-mcp": {
      "command": "uvx",
      "args": [
        "verantis-mcp"
      ]
    }
  }
}
Changelog

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.

  • 19 Aug 26 +15
    • Malware scan: unverified → pass security
  • 18 Aug 26 −14
    • Malware scan: pass → unverified security
    • Schema quality: 129 → 169 functional
    • Schema quality: 129 → 160 functional
    • Tool coverage: 77% → 100% functional
    • Stability: unverified → 0.07 functional
    • Schema quality: good → excellent functional
    • Package version: 0.1.3 → 0.2.1 functional
    • Package version: 0.1.3 → 0.2.0 functional
  • 16 Aug 26 66

    First indexed and scored.

Diagnostics

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 19 Aug 2026 · Analysed pypi/verantis-mcp@0.2.1

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem pypi
Install scripts 1 script
Hook Tier Command
build_backend allowlisted hatchling.build
Dependencies 0 packages
Packages resolved 0
Tree resolution Complete
MCP tools · 4 exposed · ~678 tokens

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.

Tool Tokens
check_wallet ~179

Check a recipient wallet BEFORE your agent pays it — a pre-payment guard. Pass the pay-to address a service asked you to pay; returns whether Verantis knows the wallet, its EARNED reputation tier, and human-readable reasons. A wallet IS a settlement rail, so the reply names the rail it settles on ('rail': chain + protocols), its host, on-chain buyer retention (distinct buyers, repeat rate, distribution), and the host's OTHER rails ('also_settles_on'). If 'shared_wallet' is true the address fronts many services (a relay/treasury) so the reputation reflects the pool, not one service — treat with care. An unknown or low-reputation recipient is a reason to pause.

NameTypeReqDescription
pay_tostringyesrecipient wallet address (0x… for Base/EVM, base58 for Solana)

No output schema declared.

No examples provided.

directory_stats ~20

Index-level statistics: services, verification breakdown, data freshness.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

find_paid_service ~407

Search Verantis's verified directory of machine-payable services (x402, MPP). Results are UNIFIED per service (host): each carries its settlement rails ('rails': base / solana / tempo), and every rail has its OWN reputation, price, and buyer retention — never blended. Pass 'chain' and 'matched_rail' marks that chain's rail so you see the reputation for the rail you'll actually pay on. 'coming_soon' lists advertised chains not yet measured. Prefer verified=true before paying anyone.

NameTypeReqDescription
chainstringsettlement network, e.g. base, solana, polygon, tempo
exclude_concentratedbooleanexclude services from operators with many listings under one registrable owner (a neutral concentration signal, not a fraud claim)
limitintegermaximum number of results to return (default 10)
max_latency_msintegerreject services slower than this (ms)
max_price_usdnumbermax price per call in USD
min_scoreintegerminimum trust score 0-100 — set high (e.g. 85) for money-moving tasks
protocolstringrestrict to one payment protocol: x402 or mpp
proven_onlybooleanonly services that have EARNED reputation over time (excludes 'new' services and 'watch' services whose on-chain payments are concentrated / not yet broadly distributed). Reputation is earned via con…
querystringyeswhat you need, e.g. 'twitter data', 'web search', 'rpc ethereum'
require_freshbooleanlive re-probe stale results before returning — use before paying real money; adds ~1s per stale service
verified_onlybooleanonly services that passed the latest live probe

No output schema declared.

No examples provided.

get_service ~72

Full unified record for one service host: every settlement rail it accepts on, each with its own reputation, price, buyers, volume and history, plus coming-soon chains. Pass the host (domain).

NameTypeReqDescription
domainstringyesthe service host / domain to look up, e.g. api.nansen.ai

No output schema declared.

No examples provided.