← Browse

@moonshotai/agent-core

A

MCP server package @moonshot-ai/agent-core

mcp_servermcp

Install

agr install @moonshotai/agent-core --target claude

This artifact does not publish files for Claude.

Document

{ "name": "@moonshot-ai/agent-core", "version": "0.15.7", "private": true, "description": "The unified agent engine for Kimi", "license": "MIT", "author": "Moonshot AI", "homepage": "https://github.com/MoonshotAI/kimi-code/tree/main/packages/agent-core#readme", "repository": { "type": "git", "url": "git+https://github.com/MoonshotAI/kimi-code.git", "directory": "packages/agent-core" }, "bugs": { "url": "https://github.com/MoonshotAI/kimi-code/issues" }, "keywords": [ "kimi", "agent", "ai", "llm", "session", "tools" ], "files": [ "dist" ], "type": "module", "imports": { "#/agent": "./src/agent/index.ts", "#/agent/background": "./src/agent/background/index.ts", "#/agent/compaction": "./src/agent/compaction/index.ts", "#/agent/config": "./src/agent/config/index.ts", "#/agent/context": "./src/agent/context/index.ts", "#/agent/cron": "./src/agent/cron/index.ts", "#/agent/goal": "./src/agent/goal/index.ts", "#/agent/permission": "./src/agent/permission/index.ts", "#/agent/plan": "./src/agent/plan/index.ts", "#/agent/swarm": "./src/agent/swarm/index.ts", "#/agent/tool": "./src/agent/tool/index.ts", "#/config": "./src/config/index.ts", "#/flags": "./src/flags/index.ts", "#/loop": "./src/loop/index.ts", "#/rpc": "./src/rpc/index.ts", "#/session": "./src/session/index.ts", "#/": "./src/.ts" }, "exports": { ".": { "types": "./src/index.ts", "default": "./src/index.ts" }, "./package.json": { "types": "./package.json", "default": "./package.json" }, "./session/store": { "types": "./src/session/store/index.ts", "default": "./src/session/store/index.ts" }, "./": { "types": "./src/.ts", "default": "./src/*.ts" } }, "scripts": { "build": "tsdown", "test": "vitest run", "test:baseline": "vitest run", "typecheck": "tsc -p tsconfig.json --noEmit", "clean": "rm -rf dist" }, "dependencies": { "@antfu/utils": "^9.3.0", "@jsquash/webp": "^1.5.0", "@modelcontextprotocol/sdk": "^1.29.0", "@moonshot-ai/kaos": "workspace:^", "@moonshot-ai/kimi-code-oauth": "workspace:^", "@moonshot-ai/kosong": "workspace:^", "@moonshot-ai/protocol": "workspace:^", "@mozilla/readability": "^0.6.0", "ajv": "^8.18.0", "ajv-formats": "^3.0.1", "chokidar": "^4.0.3", "ignore": "^5.3.2", "jimp": "^1.6.1", "js-yaml": "^4.1.1", "linkedom": "^0.18.12", "node-pty": "^1.1.0", "nunjucks": "^3.2.4", "open": "^10.2.0", "pathe": "^2.0.3", "picomatch": "^4.0.4", "proper-lockfile": "^4.1.2", "regexp.escape": "^2.0.1", "retry": "0.13.1", "smol-toml": "^1.6.1", "socks": "^2.8.9", "tar": "^7.5.13", "ulid": "^3.0.1", "undici": "^7.27.1", "yauzl": "^3.3.0", "zod": "^4.3.6" }, "devDependencies": { "@types/js-yaml": "^4.0.9", "@types/nunjucks": "^3.2.6", "@types/picomatch": "^4.0.3", "@types/proper-lockfile": "^4.1.4", "@types/regexp.escape": "^2.0.0", "@types/retry": "0.12.0", "@types/sinon": "^21.0.1", "@types/tar": "^7.0.87", "@types/yauzl": "^2.10.3", "@types/yazl": "^2.4.6", "sinon": "^22.0.0", "yazl": "^3.3.1" } }

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-08fceeab71262026-08-06