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 styler-ai · MCP Server · ★ 436
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is ProjectAtlas safe to install? View the security audit →
ProjectAtlas Rust-native, high-performance local repository intelligence for coding agents and large codebases. A persistent SQLite map guides Codex, Claude Code, OpenCode, and other MCP-capable agents to the right code before they spend context reading the wrong files. About Every file not opened. Every folder not explored. ProjectAtlas guides coding agents with purpose metadata and an intelligent code graph, reducing token costs by over 90%. The "over 90%" figure is a workload-specific local estimate from the published audit, not a universal savings guarantee or provider-billing result; see [One Large-Application Audit](#one-large-application-
| Stars | 436 |
| Forks | 13 |
| Language | Rust |
| Category | MCP Server |
| License | MIT |
| Quality Score | 67.6790910455532/100 |
| Open Issues | 20 |
| Last Updated | 2026-10-04 |
| Created | 2026-01-01 |
| Platforms | claude-code, codex, mcp, rust |
| Est. Tokens | ~25k |
These tools work well together with ProjectAtlas for enhanced workflows:
Looking for a ProjectAtlas alternative? If you're comparing ProjectAtlas 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.
Professional context and harness engineering for Claude Code and OpenAI Codex. Build production-grade software
The control plane for AI coding agents.
A personal context store for AI agents and assistants—reuse your existing coding agent CLI (Codex/Claude/OpenC
Open-source cross-agent memory layer for coding agents via MCP. Compatible with Claude Code, Codex, Cursor, Wi
Structural code intelligence for AI agents — semantic search, knowledge graphs, and a built-in MCP server in o
Local-first AI knowledge layer. Extract architecture, query from any AI tool via MCP. Private by architecture.
Explore other popular mcp server tools:
ProjectAtlas is Every file not opened. Every folder not explored. Tokens saved. ProjectAtlas guides coding agents with purpose metadata and an intelligent code graph, reducing token costs by over 90%.. It is categorized as a MCP Server with 436 GitHub stars.
ProjectAtlas is primarily written in Rust. It covers topics such as claude-code, code-intelligence, codex.
You can find installation instructions and usage details in the ProjectAtlas GitHub repository at github.com/styler-ai/ProjectAtlas. The project has 436 stars and 13 forks, indicating an active community.
ProjectAtlas is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to ProjectAtlas on Agent Skills Hub include pilot-shell, ai-devkit, OpenContext. 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: