Install
$ agentstack add skill-batteryshark-skill-tap-mcp-testing ✓ 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 Used
- ✓ 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
Test a FastMCP Server
- Run
bin/mcp-testing PATHto inventory tests and MCP surfaces, then read [references/test-matrix.md](references/test-matrix.md). - Test pure domain functions directly without an MCP runtime.
- Use an in-memory
Client(server)for component discovery, schema, tool/resource/prompt behavior, errors, structured results, elicitation, authorization, visibility, and task semantics. - Mock at the domain adapter boundary, not FastMCP internals. Assert requested side effects and the absence of forbidden side effects.
- Add subprocess tests only for stdio lifecycle/configuration and HTTP tests only for routing, authentication, proxy, streaming, or deployment integration.
- Test every destructive or external operation across preview, approve, decline, authorization failure, timeout, retry, and duplicate request cases.
- Compare the exposed component catalog or fingerprints when compatibility matters.
Use [agents/test-reviewer.md](agents/test-reviewer.md) to identify missing behavioral and security cases.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: batteryshark
- Source: batteryshark/skill-tap
- License: MIT
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.