meridian — security grade SAFE, quality 73/100

Security audit verdict: SAFE · quality 73/100

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 rynfar · MCP Server · ★ 2.0k

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

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

About meridian

Meridian turns your Claude Max subscription into a local Anthropic API. Any tool that speaks the Anthropic protocol — OpenCode, Crush, Cline, Continue, Aider — connects to Meridian and gets Claude, powered by your existing subscription through the official Claude Code SDK. Harness Claude, your way. [!NOTE] Renamed from . If you're upgrading, see for the checklist. Your existing sessions, env vars, and agent configs all continue to work. Quick Start Meridian starts on . Point any Anthropic-compatible tool at it: bash ANTHROPICAPIKEY=x ANTHROPICBASEUR

ai-agentsai-codingaideranthropicantigravitybunclaudeclaude-agent-sdkclaude-maxcline

Quick Facts

Stars2,040
Forks225
LanguageTypeScript
CategoryMCP Server
Quality Score72.5272836388408/100
Open Issues17
Last Updated2026-09-23
Created2026-01-20
Platformsclaude-code, cli, gemini, mcp, node
Est. Tokens~18k

Compatible Skills

These tools work well together with meridian for enhanced workflows:

  • opencode-claude-auth — semantic(0.27)+complementary+shared_fw(anthropic)+rare_topics+same_lang+similar_pop+shared_platform (72%)
  • anthropic-max-router — semantic(0.33)+complementary+shared_fw(anthropic)+same_lang+similar_pop+shared_platform (64%)
  • Claude-Zeroclaw — semantic(0.15)+complementary+shared_fw(anthropic)+same_lang+similar_pop+shared_platform (63%)
  • opencode-with-claude — semantic(0.82)+rare_topics+same_lang+shared_platform (58%)
  • claude-agent-server — semantic(0.24)+complementary+rare_topics+same_lang+similar_pop+shared_platform (58%)

meridian alternative? Top 6 similar tools

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

  • opencode-with-claude by ianjwhite99 · ⭐ 580

    OpenCode plugin to use your Claude Max/Pro subscription with OpenCode via Meridian

  • Unity-MCP by IvanMurzak · ⭐ 4.3k

    AI Skills, MCP Tools, and CLI for Unity Engine. Full AI develop and test loop. Use cli for quick setup. Effici

  • claude-tap by liaohch3 · ⭐ 3.2k

    Intercept and inspect Coding Agent API traffic from Claude Code, Codex CLI, Gemini CLI, Cursor CLI, OpenCode,

  • agent-of-empires by njbrake · ⭐ 2.4k

    Manage multiple Claude Code, OpenCode agents from either TUI or Web for easy access on mobile. Also supports M

  • kiro-gateway by jwadow · ⭐ 2.3k

    👻 Proxy API gateway for Kiro IDE & CLI (Amazon Q Developer / AWS CodeWhisperer). Use free Claude models with

  • everything-claude-code-zh by xu-xiang · ⭐ 2.0k

    everything-claude-code 中文翻译项目:完整的 Claude Code 配置集合(agents, skills, hooks, commands, rules, MCPs)。源自 Anthropic

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular TypeScript Agent Tools

Frequently Asked Questions

What is meridian?

meridian is Use Claude and Antigravity with Pi, OpenCode and other coding clients. Local API bridge, usage dashboard and Mac app. Antigravity preview available in 1.74.0.. It is categorized as a MCP Server with 2.0k GitHub stars.

What programming language is meridian written in?

meridian is primarily written in TypeScript. It covers topics such as ai-agents, ai-coding, aider.

How do I install or use meridian?

You can find installation instructions and usage details in the meridian GitHub repository at github.com/rynfar/meridian. The project has 2.0k stars and 225 forks, indicating an active community.

What are the best alternatives to meridian?

The top alternatives to meridian on Agent Skills Hub include opencode-with-claude, Unity-MCP, claude-tap. 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