No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by enola-labs · MCP Server · ★ 256
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is enola safe to install? View the security audit →
enola Give your AI agent a map of the codebase before it starts exploring. enola is a local Model Context Protocol (MCP) server that generates compact architectural snapshots of repositories. Run it once, and your AI coding agent (Claude Code, Cursor, Copilot, or any MCP-compatible tool) gets a structured overview of modules, symbols, dependencies, routes, and architectural patterns - before it reads a single file. What This Is (and Isn't) A first step, not a replacement. enola is designed to run before your AI agent starts exploring code. It gives the agent a structural overview so it knows where to look and what connects to what. It does not replace grep, file search, code reading, or any traditional discovery tool - it makes them more effective by providing upfront context. Input for AI agents. The snapshot output (modules, symbols, dependencies, architectural patterns) is structured context designed for LLM consumption. It is not a dashboard, not a visualization tool, not a documentation generator. It answers the question: "What does this codebase look like?" so the agent can skip the guessing phase. Built for multi-repo work.
| Stars | 256 |
| Forks | 22 |
| Language | C |
| Category | MCP Server |
| License | Apache-2.0 |
| Quality Score | 68.9416276784676/100 |
| Open Issues | 5 |
| Last Updated | 2026-09-30 |
| Created | 2026-02-10 |
| Platforms | mcp |
| Est. Tokens | ~21k |
These tools work well together with enola for enhanced workflows:
Looking for a enola alternative? If you're comparing enola 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.
Local codebase intelligence CLI + MCP server for AI coding agents: SQLite code graph, 28 languages, 287 comman
Deterministic, local-first memory and guardrails for AI coding agents with no LLM in the hot path.
One command gives AI agents instant codebase context. ~250 tokens replaces 50,000+ tokens of exploration. Auto
Repo memory for coding agents. Local-first MCP for Claude Code, Cursor, Windsurf, and Codex CLI: symbol graph,
MCP server for AI coding agents. Instead of reading files one by one, your agent gets dependency graphs, git i
Framework-aware code intelligence MCP server — 88 framework integrations, 81 languages, 72.7% fewer input toke
Explore other popular mcp server tools:
enola is Architecture intelligence for AI coding agents - deterministic, cross-repository code analysis through MCP.. It is categorized as a MCP Server with 256 GitHub stars.
enola is primarily written in C. It covers topics such as ai-coding, architecture, architecture-analysis.
You can find installation instructions and usage details in the enola GitHub repository at github.com/enola-labs/enola. The project has 256 stars and 22 forks, indicating an active community.
enola is released under the Apache-2.0 license, making it free to use and modify according to the license terms.
The top alternatives to enola on Agent Skills Hub include roam-code, OpenLore, stacklit. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. 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: