by unmateria · MCP Server · ★ 55
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
None of the 42 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 42 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.
| Stars | 55 |
| Forks | 14 |
| Language | Python |
| Category | MCP Server |
| Quality Score | 73/100 |
| Last Updated | 2026-10-10 |
| Created | 2026-02-23 |
| Platforms | claude-code, mcp, python |
| Est. Tokens | ~25k |
mcp-access Give any AI assistant full control over Microsoft Access databases. Create forms, write VBA, design tables, manage controls, run queries, build relationships, and edit every corner of an — all through natural language. 66 tools that turn Access into something you can talk to. No Access expertise required. Just describe what you want.
These tools work well together with MCP-Access for enhanced workflows:
Looking for a MCP-Access alternative? If you're comparing MCP-Access with other mcp server tools, these 2 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
APEX turns Azure platform engineering requirements into verified, deploy-ready IaC — powered by GitHub Copilot
APEX turns Azure platform engineering requirements into verified, deploy-ready IaC — powered by GitHub Copilot
Explore other popular mcp server tools:
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 42 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: