MCP工具 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。
MCP工具 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。
MCP工具 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/sanna-ai/sanna
# 方式二:手动配置 claude_desktop_config.json
{
"mcpServers": {
"mcp--": {
"command": "npx",
"args": ["-y", "sanna"]
}
}
}
# 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 MCP工具 执行以下任务... Claude: [自动调用 MCP工具 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": {
"mcp__": {
"command": "npx",
"args": ["-y", "sanna"],
"env": {
// "API_KEY": "your-api-key-here"
}
}
}
}
// 保存后重启 Claude Desktop 生效
Sanna checks reasoning during execution, halts when constraints are violated, and generates portable cryptographic receipts proving governance was enforced. Constitution-as-code: your governance rules live in version-controlled YAML, not in a vendor dashboard.
enforcement_surface field — Receipts now record which SDK component generated them (middleware, gateway, cli_interceptor, http_interceptor).invariants_scope field — Receipts record which invariants were evaluated (full, authority_only, limited, none).CHECKS_VERSION bumped to "8", SPEC_VERSION to "1.3". Fields 15-16 are enforcement_surface_hash and invariants_scope_hash.allOf rules enforce halted → FAIL, warned → WARN, allowed → PASS.skip_default_checks parameter — Interceptor receipts derive status from enforcement.action without running C1-C5 checks (SAN-216).log enforcement (observe), move to warn (escalate), then halt (enforce).pip install sanna # Core library (Python 3.10+)
pip install sanna[mcp] # MCP server + gateway
pip install sanna[otel] # OpenTelemetry bridge
pip install sanna
Set up governance (one-time):
```bash sanna init # Choose template, set agent name, enforcement level sanna keygen # Generate Ed25519 keypair (~/.sanna/keys/)
No code changes to your agent. The gateway sits between your MCP client and downstream servers.
pip install sanna[mcp]
sanna init # Creates constitution.yaml + gateway.yaml
sanna keygen --label gateway
sanna sign constitution.yaml --private-key ~/.sanna/keys/<key-id>.key
sanna gateway --config gateway.yaml
Minimum gateway.yaml:
gateway:
constitution: ./constitution.yaml
signing_key: ~/.sanna/keys/<gateway-key-id>.key # Key generated by sanna keygen
constitution_public_key: ~/.sanna/keys/<author-key-id>.pub # Public key of constitution signer
receipt_store: .sanna/receipts/
downstream:
- name: notion
command: npx
args: ["-y", "@notionhq/notion-mcp-server"]
env:
OPENAPI_MCP_HEADERS: "${OPENAPI_MCP_HEADERS}"
default_policy: can_execute
Point your MCP client (Claude Desktop, Claude Code, Cursor) at the gateway instead of directly at your downstream servers. Every tool call is now governed. The gateway governs tool calls that pass through it — only actions that cross the governance boundary produce receipts. Reasoning is captured via the explicit _justification parameter in tool calls, not from internal model reasoning. The gateway cannot observe LLM chain-of-thought.
MCP Client (Claude Desktop / Claude Code / Cursor)
|
v (MCP stdio)
sanna-gateway
| 1. Receive tool call
| 2. Evaluate against constitution
| 3. Enforce policy (allow / escalate / deny)
| 4. Generate signed receipt
| 5. Forward to downstream (if allowed)
v (MCP stdio)
Downstream MCP Servers (Notion, GitHub, filesystem, etc.)
Run a self-contained governance demo — no external dependencies:
sanna demo
This generates keys, creates a constitution, simulates a governed tool call, generates a receipt, and verifies it.
cloud = CloudHTTPSink("https://governance.example.com/receipts", api_key="...")
All commands are available as sanna <command> or sanna-<command>:
| Command | Description |
|---|---|
sanna init | Interactive constitution generator with template selection |
sanna keygen | Generate Ed25519 keypair (--label for human-readable name) |
sanna sign | Sign a constitution with Ed25519 |
sanna verify | Verify receipt integrity, signature, and provenance chain |
sanna verify-constitution | Verify constitution signature |
sanna approve | Approve a signed constitution |
sanna demo | Run self-contained governance demo |
sanna inspect | Pretty-print receipt contents |
sanna check-config | Validate gateway config (dry-run) |
sanna gateway | Start MCP enforcement proxy |
sanna mcp | Start MCP server (7 tools, stdio transport) |
sanna diff | Diff two constitutions (text/JSON/markdown) |
sanna drift-report | Fleet governance drift report |
sanna bundle-create | Create evidence bundle zip |
sanna bundle-verify | Verify evidence bundle (7-step) |
sanna generate | Generate receipt from trace-data JSON |
The top-level sanna package exports 17 names:
from sanna import (
__version__, # Package version string
sanna_observe, # Decorator: governance wrapper for agent functions
SannaResult, # Return type from @sanna_observe-wrapped functions
SannaHaltError, # Raised when a halt-enforcement invariant fails
generate_receipt, # Generate a receipt from trace data
SannaReceipt, # Receipt dataclass
verify_receipt, # Offline receipt verification
VerificationResult, # Verification result dataclass
ReceiptStore, # SQLite-backed receipt persistence
DriftAnalyzer, # Per-agent failure-rate trending
# Receipt sinks (v1.0.0)
ReceiptSink, # Abstract base class for receipt persistence
NullSink, # No-op sink (default)
LocalSQLiteSink, # SQLite-backed local persistence
CloudHTTPSink, # HTTP endpoint with retry and buffer-on-failure
CompositeSink, # Fan-out to multiple sinks
SinkResult, # Result from a sink.send() call
FailurePolicy, # Enum: LOG, BUFFER, RAISE
)
Everything else imports from submodules: sanna.constitution, sanna.crypto, sanna.enforcement, sanna.evaluators, sanna.verify, sanna.bundle, sanna.hashing, sanna.drift, sanna.sinks.
高质量的开源MCP工具
该工具使用 AGPL-3.0 协议,商用场景请仔细阅读协议条款,必要时咨询法律意见。
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。
⚠️ AGPL 3.0 — 最严格的 Copyleft,网络服务端使用也需开源,SaaS 使用受限。
经综合评估,MCP工具 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 | sanna |
| 原始描述 | 开源MCP工具:Trust infrastructure for AI agents — constitution enforcement and cryptographic 。⭐8 · Python |
| Topics | ai-agentsai-governanceai-safety |
| GitHub | https://github.com/sanna-ai/sanna |
| License | AGPL-3.0 |
| 语言 | Python |
收录时间:2026-05-29 · 更新时间:2026-05-30 · License:AGPL-3.0 · 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