SDAR MCP Tasks Provider Runtime
A language-neutral runtime for the SEP-2663 task lifecycle and io.sdar/taskExecution Provider Profile, delegating resource facts and side effects to versioned gRPC/Protobuf adapters. Implemented in strict TypeScript, it provides durable scheduling, recovery, and a full test suite for conformance.
README
SDAR MCP Tasks Provider Runtime
An independently deployable, language-neutral Runtime for the SEP-2663 task lifecycle and the io.sdar/taskExecution Provider Profile. The Runtime is implemented in strict TypeScript and delegates resource facts and side effects to versioned gRPC/Protobuf Adapters.
The implementation follows SDAR_MCP_Tasks_Runtime_Codex_Goal_Task_Package_V1.0.md. Normative design inputs are under references/, the living execution plan is docs/implementation/runtime-exec-plan.md, and delivery evidence is under reports/runtime-v1/.
Runtime quick start
Prerequisites: Node.js 22, Corepack/pnpm 11, and Docker with Compose access.
corepack enable
pnpm install --frozen-lockfile
pnpm build
pnpm test:unit
pnpm test:contract
docker compose up --build --wait
curl --fail http://127.0.0.1:8080/health/ready
The default stack exposes Runtime HTTP on :8080, PostgreSQL on :5432, and an internal TypeScript Adapter on :7001. A Python Adapter image can be built with:
docker compose --profile python-adapter build adapter-python
Runtime startup applies migrations and runs durable scheduling/recovery before readiness. The reference Adapter state and PostgreSQL data use named volumes. For a release gate with PostgreSQL and Docker available, run:
TEST_DATABASE_URL=postgresql://sdar:sdar@127.0.0.1:5432/sdar_runtime_test pnpm verify
Configuration and security are documented in
configuration.md and
security-recovery.md; deployment and
incident procedures are in the runbook.
Adapter authors can run the dual-language P0-P4 workflow described in docs/conformance/adapter-testkit.md; its JSON reports use a published repository schema.
Adapter authors should begin with the
quick start and dual-language P0-P4 workflow in
adapter-testkit.md. API/RPC and state
semantics are summarized in api-reference.md
and state-reason-mapping.md.
Production Kubernetes JSON manifests are under deploy/kubernetes,
with migration/upgrade instructions in docs/database/upgrade.md.
Root commands in package.json expose every release gate; pnpm verify includes
formatting, lint, types, build/Proto drift, audit/SBOM, deployment/container,
unit/contract/integration/recovery/security/E2E/conformance and capacity checks.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。