io.github.mythos-agent/mythos-agent

MCPcommunity
v4.0.1io.github.mythos-agentUnknownUpdated 5mo agonpmGitHub

Open-source AI security agent: SAST, DAST, and policy-as-code over MCP.

开源。读你的代码、标记可能的安全问题、解释推理过程、给出修复建议。 mythos-agent 用一位专职安全审阅者的方式来审阅你的代码 —— 系统性地走过常见的问题模式、查找已知 CVE 的结构变体、按置信度排序发现、并给出可以直接采纳或拒绝的修复建议。灵感与 Anthropic 内部的 Mythos 安全代理同源，但本项目是独立实现、并非克隆、也无任何隶属关系。完整定位见 VISION.md。 给新贡献者：为期 6 个月的当前工作计划见置顶 Issue 。带 🙋 标记的条目是欢迎协作的部分。刚加入？参考 CONTRIBUTING.md 里的 指引。 给安全团队与 EU CRA 合规的下游制造商：漏洞披露 SLA 见 SECURITY.md，EU CRA 角色声明见 docs/security/cra-stance.md，公开威胁模型见…

Works in
ClaudeCursorCopilotGemini

Inferred from the transports this listing declares (stdio). A client not listed here hasn’t been ruled out — it just isn’t something Forge can confirm.

Automatically indexed from public sources. Not yet verified by the developer on Forge.Claim this listing →
43GitHub stars
10Forks
5mo agoLast update
Package
Authorio.github.mythos-agent
LicenseUnknown
Version4.0.1
Sourcemcp-registry
npmmythos-agent
GitHubmythos-agent/mythos-agent
SBOMCycloneDX 1.6 ↓
Trust Status
B
60/100Good
✓Listed in Forge index+10/10
—Publisher identity verified+0/20
→ Publisher: run `forge publish` from the package repo to claim ownership
—Ed25519 publish signature+0/5
→ Included automatically when the publisher runs `forge publish`
—Domain verification+0/5
→ Publisher: host /.well-known/forge.json on the package homepage with { "publisher": "<github-login>" }
—npm Trusted Publishing (Sigstore)+0/5
→ Publish from GitHub Actions with --provenance so the attestation binds this package to this repo
—npm maintainer match+0/5
→ Earned once your identity is verified above and that login is an npm maintainer of this package
✓CVE scan · clean+30/30
✓Static analysis · clean+20/20
Paste into Claude Code, Cursor, or any AI assistant to fix all gaps
StatusCommunity-indexed
PublisherUnverified
SignatureUnsigned
Domain—
Provenance—
Dependencies✓ 53 resolved+ · none vulnerable
Tool surface11 tools · none privileged
Security scan✓ Cleanv4.3.0 · 3mo agoHow well does this scan work?
EvalsNone
IndexedJun 13, 2026

Verification confirms publisher identity (repo ownership), not code safety. The security scan covers known CVEs and suspicious install scripts.

Tools

11 tools · none privileged
Statically extracted from the published packagev4.3.0 · 3mo ago

Read out of the source npm actually ships, at scan time. The package was never executed. Tools registered dynamically at runtime, or hidden inside bundled or minified code, can be missed — so this is a floor on the tool surface, not a complete census of it.

list_functionsNo description published

This tool published no description. Forge does not invent one.

list_endpointsNo description published

This tool published no description. Forge does not invent one.

find_callersNo description published

This tool published no description. Forge does not invent one.

find_calleesNo description published

This tool published no description. Forge does not invent one.

trace_call_pathNo description published

This tool published no description. Forge does not invent one.

find_unprotected_endpointsNo description published

This tool published no description. Forge does not invent one.

get_security_overviewNo description published

This tool published no description. Forge does not invent one.

read_fileNo description published

This tool published no description. Forge does not invent one.

search_codeNo description published

This tool published no description. Forge does not invent one.

list_filesNo description published

This tool published no description. Forge does not invent one.

find_ast_patternNo description published

This tool published no description. Forge does not invent one.

0 of 11 tools published a description.

Tool names and descriptions are written by the publisher and shown verbatim as inert text. They are the strings an MCP client passes to a model, so Forge scans them for prompt-injection patterns — any finding appears with the security scan above. “Privileged” is a keyword match on the tool name, not an audit of what the tool does: a benign-sounding name can still do anything.

About

开源。读你的代码、标记可能的安全问题、解释推理过程、给出修复建议。 mythos-agent 用一位专职安全审阅者的方式来审阅你的代码 —— 系统性地走过常见的问题模式、查找已知 CVE 的结构变体、按置信度排序发现、并给出可以直接采纳或拒绝的修复建议。灵感与 Anthropic 内部的 Mythos 安全代理同源，但本项目是独立实现、并非克隆、也无任何隶属关系。完整定位见 VISION.md。 给新贡献者：为期 6 个月的当前工作计划见置顶 Issue **。带 🙋 标记的条目是欢迎协作的部分。刚加入？参考 CONTRIBUTING.md 里的 指引。 给安全团队与 EU CRA 合规的下游制造商：漏洞披露 SLA 见 SECURITY.md，EU CRA 角色声明见 docs/security/cra-stance.md，公开威胁模型见 docs/security/threat-model.md，版本策略与 LTS/EOL 政策见 RELEASES.md。OpenSSF Best Practices Badge（Passing 层）申请目标为 2026 年 6 月；发布产物通过…

Keywords
mcp
Alternatives
Comparing tool surfaces…

Tools exposed

11 tools · none privileged · observed by static extraction. A tool surface is what one scan read on one day, not a live capability list.

Linked names open Forge’s index of every entry observed exposing that tool. Browse all indexed tools.

No dependency coverage

This package was last scanned before Forge began storing the resolved tree. The next scan will record it.