abs-mcp-comparison — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited abs-mcp-comparison (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Keep the README comparison against other Audiobookshelf MCP servers current, evidence-backed, and clearly marked as AI-generated.
asks for parallel research or when there are multiple independent targets.
package metadata. Treat aggregator pages as secondary evidence.
docs/tools.md,docs/API_TOOL_ANALYSIS.md, and .agents/skills/.
<!-- AI-GENERATED-COMPARISON:START --><!-- AI-GENERATED-COMPARISON:END -->## AI Generated Comparison - Last updated YYYY-MM-DDusing the current local date.
servers or make a recommendation in the README.
the Codex user. Suggestions should be evidence-based and should not imply they are already planned.
coverage. Distinguish read-only inspection/search resources from tools that can change Audiobookshelf state, and call out any safety gates such as read-only mode, explicit enable flags, or destructive confirmations.
Candidate gaps from this comparison subsection inside theREADME generated block. Include only evidence-backed gaps, mark them as candidates, and link existing GitHub issues when they exist.
one-sentence scopes. Ask the user whether they want issues created for all candidates, a selected subset, or none. Do not create issues unless the user explicitly confirms.
For each credible public server, capture:
registry, or MCP registry entry.
Start with current known public targets, then search for new ones:
michaeldvinci/audiobookshelf-mcpsandymac/audiobookshelf-mcpsierikov/audiobookshelf-mcpForceConstant/audiobookshelf_mcpschmidt-software/mcp-audiobookshelfAudiobookshelf MCP server, `site:github.comaudiobookshelf mcp, site:npmjs.com audiobookshelf mcp, and site:pypi.org audiobookshelf mcp`.
Check the current files instead of relying on memory:
README.md: public positioning, MCP surface, install paths, and comparison.docs/tools.md: tool inputs, output shapes, read-only behavior, and stubs.docs/API_TOOL_ANALYSIS.md: source-backed API inventory and candidateendpoint rationale.
.agents/skills/abs-api-source-sync/SKILL.md: API sync workflow.Common differentiators to verify before stating:
ABS_READ_ONLY=true by default.abs_find_misorganized_items audits file layout without moving files.When using this skill, report:
notable peers.
for all of them, only the ones you choose, or none.`
Stop and ask before proceeding when:
issues and the user has not explicitly confirmed that action.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.