swival — security grade SAFE, quality 63/100

Security audit verdict: SAFE · quality 63/100

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 Swival · MCP Server · ★ 341

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is swival safe to install? View the security audit →

About swival

Swival A coding agent for any model. Documentation Swival is a CLI coding agent built to be practical, reliable, and easy to use. It works with frontier models, but its main goal is to be as reliable as possible with smaller models, including local ones. It is designed from the ground up to handle tight context windows and limited resources without falling apart. It connects to LM Studio, llama.cpp, HuggingFace Inference API, OpenRouter, Google Gemini, Gemini Enterprise Agent Platform (formerly Vertex AI), ChatGPT Plus/Pro, AWS Bedrock, any OpenAI-compatible server (ollama, mlxlm.server, vLLM, etc.), or any external command (, custom wrappers, etc.), sends your task, and runs an autonomous tool loop until it produces an answer. With LM Studio and llama.cpp it auto-discovers your loaded model, so there's nothing to configure. Pure Python, no framework. Quickstart Pick the provider that matches how you want to run models: First command

a2aagentagent-to-agentaiclicodecodingevalhuggingfacelmstudio

Quick Facts

Stars341
Forks21
LanguagePython
CategoryMCP Server
LicenseMIT
Quality Score63.2964421232415/100
Last Updated2026-09-22
Created2026-02-24
Platformscli, mcp, python
Est. Tokens~17k

Compatible Skills

These tools work well together with swival for enhanced workflows:

  • clauder — semantic(0.15)+complementary+rare_topics+same_lang+similar_pop+shared_platform (55%)
  • fast-resume — semantic(0.27)+complementary+same_lang+similar_pop+shared_platform (55%)
  • tunacode — semantic(0.26)+complementary+same_lang+similar_pop+shared_platform (54%)

swival alternative? Top 6 similar tools

Looking for a swival alternative? If you're comparing swival 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.

  • blade-code by echoVic · ⭐ 179

    AI-powered CLI coding agent with 20+ built-in tools, MCP support, and multi-model providers

  • adal-cli by SylphAI-Inc · ⭐ 106

    The automation-first agent harness. Every coding agent can build — AdaL does GTM directly from your codebase.

  • agnix by agent-sh · ⭐ 422

    The missing linter and lsp for AI coding assistants. Validate CLAUDE.md, AGENTS.md, SKILL.md, hooks, MCP. Plug

  • ClaudeR by IMNMV · ⭐ 337

    Connect RStudio to Claude Code, Codex, Gemini, and other LLM agents via MCP. Multi-agent orchestration, automa

  • cc-skills by samber · ⭐ 204

    🧑‍🎨 A collection of agentic skills that works

  • awesome-a2a by pab1it0 · ⭐ 187

    Agent2Agent (A2A) – awesome A2A agents, tools, servers & clients, all in one place.

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular Python Agent Tools

Frequently Asked Questions

What is swival?

swival is A small, powerful, open-source CLI coding agent that works with open models.. It is categorized as a MCP Server with 341 GitHub stars.

What programming language is swival written in?

swival is primarily written in Python. It covers topics such as a2a, agent, agent-to-agent.

How do I install or use swival?

You can find installation instructions and usage details in the swival GitHub repository at github.com/Swival/swival. The project has 341 stars and 21 forks, indicating an active community.

What license does swival use?

swival is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to swival?

The top alternatives to swival on Agent Skills Hub include blade-code, adal-cli, agnix. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

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:

View on GitHub → Browse MCP Server tools