codex-trajectory — 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 icesixgod · MCP Server · ★ 246

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

🔒 Is codex-trajectory safe to install? View the security audit →

About codex-trajectory

Codex Trajectory Read this in 简体中文. Codex Trajectory is a read-only Codex plugin that turns local task logs into a privacy-aware event ledger and interactive timeline. It shows turns, approximate model steps, reasoning summaries, assistant messages, tool timing, subagents, compaction, token usage, and failures without changing the original logs. Install Prerequisites: Codex and uv on macOS, Linux, or Windows. Open a new Codex task so the installed tools and skill are loaded. Then ask: Show the safe trajectory summary for this Codex task. Privacy model Safe summary mode is the default. It returns event names, timing, status, token usage, and bounded summaries while hiding tool inputs, tool outputs, raw record metadata, absolute log paths, Git remotes, base instructions, and encrypted reasoning. Full d

codexcodex-plugindeveloper-toolsmcppythontrajectoryuv

Quick Facts

Stars246
Forks16
LanguagePython
CategoryMCP Server
LicenseMIT
Quality Score73.2978136431184/100
Last Updated2026-09-13
Created2026-08-13
Platformscodex, mcp, python
Est. Tokens~15k

codex-trajectory alternative? Top 6 similar tools

Looking for a codex-trajectory alternative? If you're comparing codex-trajectory 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.

  • hal-9000 by vinta · ⭐ 137

    Opinionated AI coding agent and dev environment automation for macOS

  • mcp-nixos by utensils · ⭐ 823

    MCP-NixOS - Model Context Protocol Server for NixOS resources

  • DeepMCPAgent by cryxnet · ⭐ 806

    Model-agnostic plug-n-play LangChain/LangGraph agents powered entirely by MCP tools over HTTP/SSE.

  • python-utcp by universal-tool-calling-protocol · ⭐ 650

    Official python implementation of UTCP. UTCP is an open standard that lets AI agents call any API directly, wi

  • Overture by SixHq · ⭐ 630

    Overture is an open-source, locally running web interface delivered as an MCP (Model Context Protocol) server

  • roam-code by Cranot · ⭐ 518

    Local codebase intelligence CLI + MCP server for AI coding agents: SQLite code graph, 28 languages, 287 comman

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular Python Agent Tools

Frequently Asked Questions

What is codex-trajectory?

codex-trajectory is Privacy-aware trajectory viewer for local Codex task logs. It is categorized as a MCP Server with 246 GitHub stars.

What programming language is codex-trajectory written in?

codex-trajectory is primarily written in Python. It covers topics such as codex, codex-plugin, developer-tools.

How do I install or use codex-trajectory?

You can find installation instructions and usage details in the codex-trajectory GitHub repository at github.com/icesixgod/codex-trajectory. The project has 246 stars and 16 forks, indicating an active community.

What license does codex-trajectory use?

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

What are the best alternatives to codex-trajectory?

The top alternatives to codex-trajectory on Agent Skills Hub include hal-9000, mcp-nixos, DeepMCPAgent. 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