by faramesh · MCP Server · ★ 109
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.
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 | 109 |
| Forks | 19 |
| Language | Go |
| Category | MCP Server |
| License | Apache-2.0 |
| Quality Score | 66/100 |
| Open Issues | 10 |
| Last Updated | 2026-07-21 |
| Created | 2026-01-14 |
| Platforms | go, mcp |
| Est. Tokens | ~16k |
Every agent tool call is a policy decision. Declare permissions in . A local daemon permits, defers, or denies each tool call before it runs. Decisions are hash-chained in a WAL. No SDK lock-in. No cloud required. <img alt="Quickstart" src="https://img.s
These tools work well together with faramesh-core for enhanced workflows:
Looking for a faramesh-core alternative? If you're comparing faramesh-core with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Deterministic safety solutions for probabilistic AI agents
An introduction to the world of AI Agents
Remote approvals, policy checks, and execution evidence for unattended AI agents.
Regression testing for AI agents. Snapshot behavior,diff tool calls,catch regressions in CI. Works with LangGr
The deterministic merge gate for AI-generated agent capability changes — a local-first, static Tool-Use Readin
Runtime policy enforcement for AI agents. Cryptographic audit trail, human-in-the-loop approvals, kill switch.
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: