Install
$ agentstack add skill-sumup-sumup-skills-sumup-mcp ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
SumUp MCP Server Guide
Use this skill when setup or usage of the SumUp MCP server is requested.
Canonical endpoint:
https://mcp.sumup.com/mcp
What this skill covers
- MCP server wiring in MCP-capable clients
- Auth handshake troubleshooting
- Prompt patterns for tool-driven SumUp API tasks
- Safe usage guardrails for production and sandbox contexts
Minimal Setup Checklist
- Add an MCP server entry named
sumup. - Set URL to
https://mcp.sumup.com/mcp. - Use streamable HTTP transport if the client requires explicit transport.
- Complete authentication flow when prompted by the client.
- Confirm tools are discoverable before first task prompt.
Example MCP Server Declaration
{
"servers": {
"sumup": {
"url": "https://mcp.sumup.com/mcp",
"transport": "streamable_http"
}
}
}
Adapt field names to the target client's MCP config schema.
Prompt Patterns
- "List my SumUp merchant checkouts from the last 24 hours."
- "Create a sandbox checkout for 12.34 EUR and return the checkout id."
- "Inspect this checkout id and summarize status transitions."
- "Show what data is needed to reconcile failed payments for this reference."
Common Failure Modes
Server not reachable
- Confirm exact URL and transport.
- Check client allows outbound HTTPS.
- Retry from a clean session.
Auth loop or unauthorized
- Re-run auth handshake and ensure correct account/environment.
- Confirm the token/session has required scopes.
Tools not appearing
- Refresh/reload MCP server in client.
- Confirm server alias matches the expected name in prompts/config.
Safety and Reliability Rules
- Never expose secrets or raw tokens in prompts or logs.
- Prefer sandbox for new workflows and regression tests.
- For payment-critical actions, verify final checkout status through deterministic reads.
- Record checkout ids/references for auditability and reconciliation.
Required Response Contract
When answering MCP setup/use requests, include:
- Exact server configuration snippet.
- Authentication steps and where failures usually happen.
- One verification command/prompt to confirm setup.
- A safe first task in sandbox before production usage.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: sumup
- Source: sumup/sumup-skills
- License: Apache-2.0
- Homepage: https://developer.sumup.com/
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.