What makes Stripe notable?

1.2K downloads. Trust evidence available

How should Stripe be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

Stripe

Safely inspect Stripe payments, customers, invoices, and subscriptions Skill: Stripe Owner: maverick Summary: Safely inspect Stripe payments, customers, invoices, and subscriptions Tags: latest:1.0.4 Version history: v1.0.4 | 2026-08-05T08:38:30.633Z | user Migrate Stripe to official remote MCP OAuth v1.0.3 | 2026-05-21T10:05:28.152Z | user Convert skill metadata frontmatter to YAML v1.0.2 | 2026-05-17T17:00:12.927Z | user Update mcporter setup and invocation contracts v1.0.1 | 2026-05-

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.2k

Updated

Oct 10, 2026

Version

1.0.4

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1.2K downloads reported by the source. Last updated 10/10/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 10, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 10, 2026
Adoption signal: 1.2K downloadsadoption · observed Oct 10, 2026
Latest release: 1.0.4release · observed Aug 5, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s17b4scyfsybdcep8c0034pgs186087n:maverick-stripe-mcp

Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-maverick-maverick-stripe-mcp/snapshot"

Documentation

CLAWHUB

29,661 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: maverick-stripe-mcp
description: Search and read ordinary single-account Stripe data through Stripe's official remote MCP with MCP-native OAuth. The config-level allowlist hides all write, mixed, feedback, and preview-only top-level tools. Use for sandbox-first inspection of Stripe payments, customers, invoices, subscriptions, account context, and documentation.
homepage: https://docs.stripe.com/mcp
metadata:
openclaw:
emoji: '💳'
requires:
bins:
- mcporter
env:
- MAVERICK_STRIPE_MCP_REFRESH_TOKEN
- MAVERICK_STRIPE_MCP_CLIENT_ID
- MAVERICK_STRIPE_MCP_ACCESS_TOKEN
primaryEnv: MAVERICK_STRIPE_MCP_REFRESH_TOKEN
setup:
script: scripts/setup.sh
install:
- id: node
kind: node
package: [email protected]
bins:
- mcporter
label: Install mcporter (node)
---

# Stripe

## How to use this skill

This skill uses Stripe's official remote MCP server at `https://mcp.stripe.com`. Maverick's config-level allowlist is the source of truth for which of Stripe's advertised tools are visible to the assistant.

**Step 1 — Discover the live tool catalog and any server-published usage instructions.** Always run this first; do not rely on tool names from memory:

```sh
mcporter --config {baseDir}/mcporter.json list maverick-stripe-mcp --schema
```

The output includes the server's `Instructions:` field, if published, and a JSON Schema for every tool's parameters. Treat this as the authoritative reference for the rest of the session.

**Step 2 — Call an allowlisted read tool** using the form `maverick-stripe-mcp.<tool>`:

```sh
mcporter --config {baseDir}/mcporter.json call maverick-stripe-mcp.<tool> <arg>=<value> ...
```

Add `--output json` for structured output and transport-error envelopes:

```sh
mcporter --config {baseDir}/mcporter.json call --output json maverick-stripe-mcp.<tool> ...
```

## Safety

The exposed tool set is intentionally read-only. `stripe_api_write`, `create_refund`, the mixed read/write `stripe_report`, `send_stripe_mcp_feedback`, and the Treasury-preview `get_balance_summary` are invisible at the mcporter protocol layer. Refunds, subscriptions, invoices, payment links, customer/payment mutations, and every other write remain unavailable until Maverick has a real execution-time approval gate.

`stripe_api_read` is documented as GET-only, but it accepts broad Stripe API paths and may reach preview GET endpoints. mcporter filters exact tool names, not tool arguments, so do not describe this allowlist as a resource-path restriction.

Use Stripe sandbox for validation and confirm the selected Stripe environment before account-data reads. The broker does not persist sandbox/live mode, so local authorization or sync state proves neither environment. Sandbox and live MCP authorizations are separate; never infer one from the other or switch environments without the user's explicit intent.

## Authentication

Ordinary single-accoun

_meta.json

{
  "ownerId": "kn734qkn0pkds34pv28ksc0p7h81ha6e",
  "slug": "maverick-stripe-mcp",
  "version": "1.0.4",
  "publishedAt": 1785919110633
}

skill-card.md

## Description:

Search and read ordinary single-account Stripe data through Stripe's official remote MCP with MCP-native OAuth, with a config-level allowlist hiding write, mixed, feedback, and preview-only top-level tools.

This skill is ready for commercial/non-commercial use.

## Publisher:

[maverick](https://clawhub.ai/user/maverick)

### License/Terms of Use:

MIT-0

## Use Case:

Developers and operators use this skill to inspect Stripe payments, customers, invoices, subscriptions, account context, and documentation through allowlisted read-oriented MCP tools. Users should validate in sandbox first and confirm the selected Stripe environment before account-data reads.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: The skill can read Stripe account data through authorized MCP tools.

Mitigation: Install only when assistant access to Stripe data is intended, use sandbox first, and confirm live versus sandbox before reads.

Risk: Credential setup can overwrite newer local OAuth vault state if stale token values are supplied.

Mitigation: Rerun setup only after fresh authorization or credential rotation.

Risk: The read allowlist is tool-level and does not restrict every possible Stripe API resource path accepted by broad read tools.

Mitigation: Review requested paths before broad Stripe reads and do not treat local authorization or sync state as proof of the active Stripe environment.

## Reference(s):

- [ClawHub Stripe skill page](https://clawhub.ai/maverick/skills/maverick-stripe-mcp)
- [Stripe MCP overview and OAuth notes](https://docs.stripe.com/mcp)
- [Model Context Protocol authorization](https://modelcontextprotocol.io/specification/2025-11-25/basic/authorization)
- [Stripe restricted API keys](https://docs.stripe.com/keys/restricted-api-keys)
- [mcporter config reference](https://github.com/openclaw/mcporter/blob/main/docs/config.md)

## Skill Output:

**Output Type(s):** [text, markdown, shell commands, configuration, guidance]

**Output Format:** [Markdown guidance with inline shell commands and JSON/YAML configuration references]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [The skill guides allowlisted read-oriented MCP calls; returned data may include Stripe account information when valid credentials are present.]

## Skill Version(s):

1.0.4 (source: server release metadata)

## Ethical Considerations:

Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.

mcporter.json

{
  "imports": [],
  "mcpServers": {
    "maverick-stripe-mcp": {
      "baseUrl": "https://mcp.stripe.com",
      "transport": "http",
      "auth": "oauth",
      "allowedTools": [
        "stripe_api_search",
        "stripe_api_details",
        "stripe_api_read",
        "get_stripe_account_info",
        "search_stripe_documentation",
        "stripe_implementation_planner"
      ]
    }
  }
}

agents/openai.yaml

interface:
  display_name: 'Stripe'
  short_description: 'Safely inspect Stripe payments, customers, invoices, and subscriptions'
  default_prompt: 'Confirm the selected Stripe environment, use sandbox for validation, then use the allowlisted Stripe MCP read tools to inspect payment, customer, invoice, and subscription data. Never claim write access, a verified sandbox/live mode from local sync state, or Stripe Connect access.'

Github ReposUpdated 1d agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.