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 aplavin · MCP Server · ★ 83
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is julia-mcp safe to install? View the security audit →
julia-mcp MCP server that gives AI assistants access to efficient Julia code execution. Avoids Julia's startup and compilation costs by keeping sessions alive across calls, and persists state (variables, functions, loaded packages) between them — so each iteration is fast. Sessions start on demand, persist state between calls, and recover from crashes — no manual management Each project directory gets its own isolated Julia process Pure stdio transport — no open ports or sockets Tools juliaeval(code, envpath?, timeout?) — execute Julia code in a persistent session. sets the Julia project directory (omit for a temporary session). defaults to 60s and is auto-disabled for operations. juliarestart(envpath?) — restart a session, clearing all state. If is omitted, restarts the temporary session.
| Stars | 83 |
| Forks | 17 |
| Language | Python |
| Category | MCP Server |
| License | MIT |
| Quality Score | 74.0792867332492/100 |
| Open Issues | 4 |
| Last Updated | 2026-08-22 |
| Created | 2026-02-01 |
| Platforms | mcp, python |
| Est. Tokens | ~6k |
These tools work well together with julia-mcp for enhanced workflows:
Looking for a julia-mcp alternative? If you're comparing julia-mcp with other mcp server tools, these 3 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Skill + MCP server to turn your agent into an RLM. Load context, iterate with search/code/think tools, converg
self-extending sandboxed agentic harness. a loop, two tools and an llm
Sage Mode for F# development — REPL with solution or project loading, Live Testing for FREE, Hot Reload, and s
Explore other popular mcp server tools:
julia-mcp is MCP server for persistent Julia sessions — fast iteration without startup/compilation overhead. It is categorized as a MCP Server with 83 GitHub stars.
julia-mcp is primarily written in Python. It covers topics such as ai, julia, llm.
You can find installation instructions and usage details in the julia-mcp GitHub repository at github.com/aplavin/julia-mcp. The project has 83 stars and 17 forks, indicating an active community.
julia-mcp is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to julia-mcp on Agent Skills Hub include aleph, mi, SageFs. 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: