← Browse

@nexus-substrate/nexus-agents

A

MCP server package nexus-agents

mcp_servermcp

Install

agr install @nexus-substrate/nexus-agents --target claude

This artifact does not publish files for Claude.

Document

{ "name": "nexus-agents", "version": "2.173.6", "description": "Governance substrate for AI coding agents — adversarial PR review, drift-detected rules, tamper-evident audit, and closed-loop outcome routing for Claude, Codex, Gemini, and OpenCode", "mcpName": "io.github.nexus-substrate/nexus-agents", "license": "MIT", "type": "module", "main": "./dist/index.js", "types": "./dist/index.d.ts", "bin": { "nexus-agents": "./dist/cli.js" }, "exports": { ".": { "types": "./dist/index.d.ts", "import": "./dist/index.js" } }, "files": [ "dist", "scripts/postinstall.js", "src/workflows/templates", "src/security/ast-rules", "README.md" ], "repository": { "type": "git", "url": "git+https://github.com/nexus-substrate/nexus-agents.git" }, "homepage": "https://github.com/nexus-substrate/nexus-agents#readme", "bugs": { "url": "https://github.com/nexus-substrate/nexus-agents/issues" }, "publishConfig": { "access": "public", "provenance": true }, "keywords": [ "mcp", "model-context-protocol", "ai", "agents", "multi-agent", "governance", "code-review", "consensus", "audit", "orchestration", "claude", "codex", "openai", "gemini", "opencode", "ollama", "llm", "workflow" ], "author": "William Zujkowski", "engines": { "node": ">=22.0.0" }, "scripts": { "build": "tsup", "dev": "tsup --watch", "test": "vitest run", "test:e2e": "vitest run --config vitest.config.e2e.ts", "test:coverage": "vitest run --coverage", "lint": "eslint src/", "lint:fix": "eslint src/ --fix", "typecheck": "tsc --noEmit", "docs": "typedoc", "docs:watch": "typedoc --watch", "docs:api:md": "typedoc --options typedoc.markdown.json", "postinstall": "node scripts/postinstall.js || true", "prepublishOnly": "pnpm run build" }, "optionalDependencies": { "@atproto/api": "^0.20.36" }, "dependencies": { "@anthropic-ai/sdk": "^0.115.0", "@ast-grep/lang-go": "0.0.6", "@ast-grep/lang-python": "0.0.6", "@ast-grep/napi": "0.45.0", "@google/genai": "^2.15.0", "@modelcontextprotocol/sdk": "^1.30.0", "better-sqlite3": "^12.11.1", "jsonc-parser": "^3.3.1", "ollama": "^0.6.3", "openai": "^6.49.0", "semver": "^7.8.5", "tiktoken": "^1.0.22", "ts-morph": "^27.0.2", "typescript": "^6.0.3", "yaml": "^2.9.0", "zod": "^4.4.3" }, "devDependencies": { "@ai-sdk/anthropic": "^3.0.104", "@ai-sdk/google": "^3.0.103", "@ai-sdk/openai": "^3.0.90", "@types/better-sqlite3": "^7.6.13", "@types/semver": "^7.7.1", "@vitest/coverage-v8": "4.1.10", "ai": "^6.0.238", "fast-check": "^4.9.0", "nexus-memory": "workspace:*", "tsup": "^8.5.1", "typedoc": "0.28.20", "typedoc-plugin-frontmatter": "1.3.1", "typedoc-plugin-markdown": "4.12.0", "vitest": "4.1.10" }, "peerDependencies": { "@ai-sdk/anthropic": "^3.0.0", "@ai-sdk/google": "^3.0.0", "@ai-sdk/openai": "^3.0.0", "ai": "^6.0.0" }, "peerDependenciesMeta": { "ai": { "optional": true }, "@ai-sdk/anthropic": { "optional": true }, "@ai-sdk/openai": { "optional": true }, "@ai-sdk/google": { "optional": true } } }

Trustgrade A

  • passBody integrity

    Whether the stored document is plausibly the kind of file the artifact declares, rather than something fetched by mistake.

  • warnType matchbest-effort: server code not analyzed

    Whether the artifact is really the kind of thing its metadata claims it is.

  • passFreshness

    How long since the source repository was last pushed to.

  • passPrompt injection

    Scans the artifact's own text for instructions aimed at your agent rather than at you.

  • passLicense

    Whether the source repository declares an SPDX license permissive enough to redistribute.

How the grade is calculated

Each check contributes 0 points when it passes, 1 when it warns, and 2 when it fails. The total maps to a letter:

  • Aevery check passed
  • Bone warning
  • Ctwo warnings
  • Dprompt injection or body integrity failed, or three warnings
  • Fone of those failed, and something else is wrong

These are automated hygiene checks, not a security audit, and not a dependency or vulnerability scan. A grade of A means nothing was flagged — not that the artifact is safe.

Versions

  • git-3c960f9ff31d2026-08-06