occasio 是 AI Skill Hub 本期精选MCP工具之一。综合评分 8.0 分,整体质量较高。我们强烈推荐将其纳入你的 AI 工具库,帮助提升工作效率。
occasio 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
occasio 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
# 方式一:通过 Claude Code CLI 一键安装
claude skill install https://github.com/occasiolabs/occasio
# 方式二:手动配置 claude_desktop_config.json
{
"mcpServers": {
"occasio": {
"command": "npx",
"args": ["-y", "occasio"]
}
}
}
# 配置文件位置
# macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
# Windows: %APPDATA%/Claude/claude_desktop_config.json
# 安装后在 Claude 对话中直接使用 # 示例: 用户: 请帮我用 occasio 执行以下任务... Claude: [自动调用 occasio MCP 工具处理请求] # 查看可用工具列表 # 在 Claude 中输入:"列出所有可用的 MCP 工具"
// claude_desktop_config.json 配置示例
{
"mcpServers": {
"occasio": {
"command": "npx",
"args": ["-y", "occasio"],
"env": {
// "API_KEY": "your-api-key-here"
}
}
}
}
// 保存后重启 Claude Desktop 生效
Local-first audit chain and identity gate for AI coding agents. Your prompts, your tool calls, your audit log; all on your machine, cryptographically verifiable later — and an agent may request an identity (ssh / cloud / root), not silently assume one.
Occasio is a local proxy that sits between your AI coding agent (Claude Code, Cline, or anything that talks to the Anthropic API) and whichever LLM endpoint you configured. Every tool call passes through one human-readable policy file you control. You can see what is leaving your machine in real time, block what should not happen, and end up with a tamper-evident hash-chained log that a third party can verify offline months later if you ever need to prove what your agent did.
Nothing about Occasio sends data to a third party. There is no Occasio cloud, no Occasio account, no telemetry. Read docs/WHY-LOCAL.md for the architecture, docs/COMPARE.md for how this differs from cloud-hosted AI observability tools, and docs/SUSTAINABILITY.md for how a local-first product is funded under Apache 2.0.

Screenshot: occasio eyes --demo against synthetic data — no real paths, no real traffic. The "(demo)" badge top-left is always shown in demo mode.
npm install -g @occasiolabs/occasio
occasio demo audit # Auditor scenario: signed attestation + cross-verifier proof (10s, no API key)
occasio demo attest # End-to-end attestation pipeline against a synthetic chain
occasio demo anomalies # Live EDR detection on a synthetic adversarial chain
occasio harness # Real Claude Code attacking a denied path — defense holds
The first three demos run against synthetic data so you can see the full pipeline in seconds with no external dependencies. The fourth spawns a real Claude Code subordinate under your Anthropic login (bundled auth — no API key required) and proves the defense end-to-end. Start with demo audit — it answers the only question that actually matters: "prove what your AI agent did in CI."
---
npm install -g @anthropic-ai/claude-code) — or any agent that respects ANTHROPIC_BASE_URLsigstore-python (optional) — adds the cryptographic Sigstore step to the Python verifier---
occasio approvals approve apr_… --once # you, single-use, short TTL
New here? The 5-minute Getting Started guide walks the identity-gate flow end to end — install → init --template strict → run your agent → approve a borrow → verify the log. Every command in it is tested against the published release.
Requires Node.js ≥ 18. Works on Windows, macOS, Linux.
npm install -g @occasiolabs/occasio # Install
occasio doctor # Verify setup (Node, claude CLI, port, profile)
occasio init # Write ~/.occasio/policy.yml (dev-default)
occasio init --template strict # …or the identity gate: deny secrets, gate ssh/cloud/root behind approval
occasio register # Add 'claude' shell alias (one-time)
claude "read package.json and tell me the version"
After the alias is registered, every claude invocation routes through Occasio transparently. Audit-chain rows accumulate at ~/.occasio/pipeline-events.jsonl.
Inspect the run:
occasio status # Session totals
occasio replay --detail # Run-level audit
occasio audit verify # Re-walk the hash chain end-to-end
occasio anomalies # Run EDR detectors over the last 15 minutes
occasio attest --run-id <uuid> # Build a behavioral attestation for one session
occasio explain <event-id> # Why was this blocked? — the matched policy rule + how to unblock
---
deny_paths rule producing identical BLOCK rows under Claude Code's HTTP proxy and the MCP server.---
spec/agent-attestation/v1/README.md — predicate type specificationschemas/agent-attestation-v1.json — authoritative JSON Schemadocs/AUDIT.md — audit-chain row schema and canonical-serialisation rulesdocs/compliance-mapping.md — SOC 2 Common-Criteria mappingdocs/python-verifier.md — independent Python verifierdocs/edr-demo.md — defense-in-depth walkthroughdocs/reference-pipeline.md — end-to-end CI pipelineintegrations/attest-action/ — GitHub Action that signs + posts a Check Runintegrations/attest-view/ — static browser viewer for attestation files---
Produce one file an auditor or CI receives and checks in a single command:
occasio attest --run-id <uuid> --sign # behavioral attestation (Sigstore optional)
occasio bundle --run <uuid> --out run.occasio.json # pack attestation + chain slice + policy + manifest
occasio verify run.occasio.json # 6 offline checks; exit ≠ 0 on tamper
verify checks the schema, the manifest hashes, the chain slice integrity, the policy binding, the git-state vs chain cross-check, and the Sigstore signature when present — all against data embedded in the file (never the producer's machine). The run is bound to the concrete code it touched via git_state rows (HEAD + diff hash + changed files). Signing is optional; an unsigned bundle still verifies everything else. Bundles embed absolute producer paths — an internal-audit artifact; review before sharing publicly. → docs/VERIFY.md
~/.occasio/policy.yml governs the Occasio-controlled path: secret handling, deny_paths/allow_paths, custom deny_patterns, per-round limits, and tool routing. Approve it and pin against drift:
occasio policy init # starter policy.yml
occasio policy validate # lint before you rely on it
occasio policy lock --sign --out policy.lock.json # record the approved policy
occasio policy diff --since policy.lock.json # CI gate: exit 1 if the policy drifted
Both run as local browser UIs but answer different questions:
occasio dashboard (3001) | occasio eyes (3002) | |
|---|---|---|
| Focus | Session-level metrics: cost, savings, tokens | Per-exchange traffic: what went out, what came back |
| Granularity | Aggregate counters + per-request summary table | Full HTTP bodies, decoded SSE, local tool outputs |
| Capture needed | No — reads session.json + daily logs | Yes — pass --eyes to the proxy (opt-in) |
| Data scope | Metadata only | Full payload bytes (kept locally under ~/.occasio/eyes/) |
| Best for | "How much have I spent today?" | "What did the agent actually send to Anthropic?" |
Both live on 127.0.0.1 only. No CORS, no auth, no external network.
---
Occasio 是专为 AI coding agent 设计的“本地优先”审计链与身份网关。它作为一个本地代理,运行在 AI agent(如 Claude Code、Cline 或任何调用 Anthropic API 的工具)与底层系统之间。Occasio 的核心价值在于确保你的 Prompt、工具调用(tool calls)以及审计日志全部保留在本地,并具备后续加密验证的能力。此外,它引入了身份请求机制,使 agent 在获取 ssh、cloud 或 root 等权限时必须经过显式请求,而非静默占用。
运行 Occasio 需要满足以下环境要求:首先需安装 Node.js ≥ 18 版本;其次需要安装 Claude Code(通过 `npm install -g @anthropic-ai/claude-code`)或任何支持 `ANTHROPIC_BASE_URL` 配置的 agent;此外,若需使用独立验证器(independent verifier)和 LAO 上下文裁剪功能,则需要 Python 3 环境以及 `sigstore-python` 库。
安装过程非常简单。你可以通过 npm 全局安装 Occasio:执行 `npm install -g @occasiolabs/occasio`。安装完成后,建议运行 `occasio doctor` 来检查当前环境是否配置正确。在实际使用场景中,如果 agent 尝试执行受限操作(如 `ssh deploy@host`),Occasio 会自动拦截并生成一个审批请求(如 `apr_...`),等待用户手动确认。
对于初学者,建议参考 [5-minute Getting Started guide](docs/GETTING-STARTED.md) 进行端到端的流程演练,涵盖从安装、使用 `init --template strict` 初始化、运行 agent 到最后审批借用权限及验证日志的全过程。所有命令均已在正式版本中通过测试,支持 Windows、macOS 和 Linux 系统。你可以通过 `occasio approve apr_... --once` 来实现单次、短时效(TTL)的权限审批。
Occasio 提供了完善的规范与 Schema 定义。开发者可以参考 `spec/agent-attestation/v1/README.md` 获取谓词类型规范,并通过 `schemas/agent-attestation-v1.json` 获取权威的 JSON Schema。关于审计链行 Schema(audit-chain row schema)以及规范化序列化(canonical-serialisation)的详细说明,请查阅 `docs/AUDIT.md`。
Occasio 提供两套核心工作流:1. 证据工作流(Evidence workflow):通过 `occasio attest` 生成行为证明,结合 `occasio bundle` 将证明、审计链切片、策略及清单打包成 `.occasio.json` 文件,最终使用 `occasio verify` 进行一键式验证。2. 策略工作流(Policy workflow):通过 `~/.occasio/policy.yml` 管理权限,涵盖密钥处理、路径黑白名单(`deny_paths`/`allow_paths`)、自定义模式匹配、每轮限制及工具路由。使用 `occasio policy init` 初始化,并用 `validate` 进行校验以防止配置漂移。
高质量的MCP工具,值得关注
AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。
✅ Apache 2.0 — 宽松开源协议,可商用,需保留版权声明和 NOTICE 文件,含专利授权条款。
经综合评估,occasio 在MCP工具赛道中表现稳健,质量优秀。如果你已有明确的使用需求,可以直接上手体验;如果还在评估阶段,建议对比同类工具后再做决策。
| 原始名称 | occasio |
| 原始描述 | 开源MCP工具:See what your AI coding agent actually does, locally, and prove it later if you 。⭐8 · JavaScript |
| Topics | mcpjavascript |
| GitHub | https://github.com/occasiolabs/occasio |
| License | Apache-2.0 |
| 语言 | JavaScript |
收录时间:2026-06-01 · 更新时间:2026-06-01 · License:Apache-2.0 · AI Skill Hub 不对第三方内容的准确性作法律背书。
选择 Agent 类型,复制安装指令后粘贴到对应客户端