Civitas
Civitas
Civitas 是一个自主的多智能体食品采购系统,结合了协商、证据谱系分析、自适应重新规划、确定性优化和受保护的 MCP 执行。其目标产品接口是一个与 Codex 兼容的 MCP 服务器:操作员以对话方式陈述采购目标,Codex 调用 Civitas 的意图级工具,而 Civitas 主导完整的规划与安全流程。
专门的 Parliament 智能体调查相互竞争的目标,并比较求解器生成的采购备选方案。随后,一个具备证据意识的 Jury 会评估来源出处、真实的来源独立性、矛盾以及对抗性异议,然后操作才能通过执行安全边界。
React 应用程序是一个可选的、只读的证据与执行审计查看器,而非产品的主要入口点。该仓库包含严格的入站 MCP 契约、传输无关的采购外观、确定性集成套件,以及基于查看器的错误共识演示。将这些部分连接到 PostgreSQL、持久化工作器和真实采购提供方的部署组合仍然因环境而异。参见 MCP_INTERFACE.md、MCP_AGENT_WORKPLAN.md、PLAN.md、AGENTS.md、TECH_STACK.md 和 SECURITY.md。
产品接口
预期的部署在应用程序两侧都使用 MCP:
Operator → Codex → Civitas MCP server → planning / Jury / execution services
→ procurement-provider MCP serversCodex 负责对话、意图捕获、进度叙述和呈现审批请求。Civitas 对类型化输入、证据检索、优化、Parliament、Jury 与 Dissent、重新规划、新鲜度重新验证、审批绑定、幂等性和执行审计保持权威。模型或聊天消息无法绕过这些控制。
主要交互应尽可能精简:
User: Protect seven days of demand across our warehouses while minimizing waste.
Codex: Civitas found false consensus on a stale lead-time source and replanned.
The revised plan has Integrity 92/100 and all hard gates pass.
Approve the exact plan for execution?Related MCP server: mendicant-mcp-server
开发
前提条件:Python 3.12、uv、Node.js 24、pnpm 10.31.0 和 Docker Compose。
uv sync --frozen --all-groups
pnpm install --frozen-lockfile
docker compose up -d postgres
uv run alembic upgrade headPostgreSQL 默认监听端口 55432,以避免与本地安装冲突。设置 CIVITAS_POSTGRES_PORT 可覆盖该端口。
使用以下命令运行必要的检查:
uv run ruff format --check .
uv run ruff check .
uv run mypy
uv run pytest
pnpm format
pnpm lint
pnpm typecheck
pnpm build使用以下命令在本地运行当前的演示 API 和可选的审计查看器:
uv run uvicorn civitas.api.app:create_app --factory --host 127.0.0.1 --port 8001
pnpm --filter @civitas/web devVite 开发服务器将 /api 请求代理到 http://127.0.0.1:8001。
civitas.api.app:create_app 是本地模拟的演示 API。它不使用任何真实提供方,也不会产生真实的采购副作用。请保持其绑定在回环地址上。civitas.api.guarded_api 中由持久化支持的 API 工厂在被部署组合时,需要至少 32 个字符的 bearer token 和一个组织绑定。
演示
当前的端到端集成演示是一个错误共识案例文件。它从供应商 A 基于共享的过期证据获胜开始,经过洁净室 Dissent 检查,重新打开规划,在新鲜公开证据出现后批准供应商 B,然后执行新鲜度重新验证和防重复的 MCP 执行。
使用以下命令运行黄金套件:
uv run pytest tests/golden/test_scenarios.py -q使用以下命令运行集成相关的检查:
uv run pytest tests/integration/test_demo_api.py tests/unit/execution/test_service.py tests/contract/test_mcp_integration.py -q对于离线查看器演示,请打开 http://127.0.0.1:5173,选择 False consensus with clean-room dissent,然后开始运行。SSE 流在场景执行期间生成。事件记录应显示以下顺序:
evidence retrieval
→ Parliament proposal / challenge / concession
→ Jury investigate
→ clean-room Dissent evidence
→ replanning
→ Jury approve
→ freshness revalidation
→ execution succeeded
→ duplicate execution downgraded to duplicateThis server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
Control plane for autonomous software labor. Agents claim objectives over MCP with audit trail.
Coordinate multiple AI agents over MCP: atomic claims, leases, shared ledger, handoffs, tasks.
Multi-agent governance: task orchestration, compliance, decision validation, and ML predictions.
AI work orchestration for plans, tasks, teams, and coding-agent dispatch.
Related MCP Servers
- FlicenseAqualityBmaintenanceModel-agnostic multi-agent system that discovers government benefits and insurance plans, validates eligibility, and produces prioritized enrollment action plans. Integrated with Google Antigravity via MCP for a conversational interface.41
- AlicenseNot gradedqualityDmaintenanceEnables advanced probabilistic orchestration for AI agents with adaptive planning, coordination, and learning capabilities.28MIT
- AlicenseNot gradedqualityBmaintenanceEnables multi-model leader-worker agent orchestration, workflow execution, and deterministic validation via structured MCP tools.16Apache 2.0
- AlicenseNot gradedqualityCmaintenanceEnables multiple AI models to collaborate under a shared goal, architecture, plan, loops, sandbox, and acceptance criteria via a local-first MCP server.Apache 2.0
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/minnhaaaaa/civitas'
If you have feedback or need assistance with the MCP directory API, please join our Discord server