Skip to main content
Glama
zhouwen-giser

SDAR MCP Tasks Provider Runtime

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 current development target is v2.0.0-rc.1, migrating the primary /mcp endpoint to the frozen SDAR MCP Tasks Unified Protocol Profile V1.0 while retaining the 1.1.0 Provider Ops Wire Schema. Its live plan is frozen-protocol-v1-exec-plan.md. Published v1.0.0-rc.2 and v1.0.0-rc.3 migrations, reports, tags, and release history remain immutable.

中文接口文档导航

面向外部系统的接口以中文说明为主,并保留协议中的英文标识符:

  • Runtime API 参考:说明 HTTP 健康/管理接口、MCP JSON-RPC 方法、tasks/observations(任务观测分页)和 Adapter gRPC 方法,包含输入输出样例。

  • Provider 遥测入口:说明 ProviderTelemetryIngress(Provider 遥测入口)及 EmitProviderEvents(批量提交事件)的字段、mTLS 身份规则、错误码和 TypeScript/Python 客户端样例。

  • Provider 运维遥测:说明 ProviderOpsEnvelope(Provider 运维事件信封)、外部 Collector 输出、指标、隐私和失败语义。

  • Runtime 配置参考:逐项解释环境变量、默认值和生产环境失败关闭要求。

  • Adapter 快速开始:说明 Provider/Adapter 对接方向和双语言示例客户端。

Related MCP server: WorkspaceGuard

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:v2

Configuration and security are documented in configuration.md and security-recovery.md; deployment and incident procedures are in the runbook. OTLP signal contracts, privacy rules and failure behavior are in provider-ops-telemetry.md. The signal architecture and Provider-facing gRPC contract are documented in observability.md and provider-telemetry-ingress.md.

Adapter authors should begin with the quick start and dual-language expanded Adapter protocol workflow in adapter-testkit.md. API/RPC and state semantics are summarized in api-reference.md and state-reason-mapping.md. The machine reports mark Runtime Profile coverage partial and real-resource safety not_claimed; a Mock Adapter result is not production qualification. Both mock Adapters include Provider telemetry clients and examples for resource state/metric/health, Task-bound execution progress, and replaying the same Provider event id after an uncertain call. This Provider-to-Runtime service requires no Provider-side OpenTelemetry SDK.

The standalone Home Assistant Climate Provider adds allowlisted climate.* state, power, HVAC-mode, and target-temperature operations through Home Assistant REST and WebSocket APIs.

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:v2 includes the frozen contract/hash checks, the numbered 74-case report, and the existing formatting, lint, types, build/Proto drift, audit/SBOM, deployment/container, unit/contract/integration/recovery/security/E2E/conformance, the six rc.1 red-regression guards, and the rc.3 capacity checks. CI additionally runs Buf lint/breaking against the immutable rc.1 tag and builds the Runtime plus both Adapter images with Compose.

A
license - permissive license
-
quality - not tested
B
maintenance

Maintenance

Maintainers
Response time
Release cycle
Releases (12mo)
Commit activity

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Servers

  • A
    license
    -
    quality
    A
    maintenance
    Deterministic execution engine for AI agents. 412 modules across 78 categories including browser automation, file I/O, Docker, data parsing, crypto, and scheduling. Supports STDIO and Streamable HTTP transport with execution trace, evidence snapshots, and replay from any step.
    Last updated
    478
    Apache 2.0
  • F
    license
    B
    quality
    B
    maintenance
    Structured workspace runtime for long-running coding agents, providing controlled workspace capabilities with task state, snapshots, checkpoints, drift detection, verification evidence, audit logs, and structured handoff.
    Last updated
    20
  • F
    license
    -
    quality
    B
    maintenance
    A native TypeScript AI orchestration engine and MCP server that coordinates autonomous sub-agents for complex coding tasks using DAG-based parallel execution and multi-agent consensus validation, with a real-time web dashboard.
    Last updated
    1
  • F
    license
    -
    quality
    C
    maintenance
    A production-oriented MCP runtime providing orchestration tools for IDE and agent integrations, including task management, diagnostics, and token usage reporting.
    Last updated

View all related MCP servers

Related MCP Connectors

  • Hosted NeuroDock — stateless communication and planning tools over OAuth-secured Streamable HTTP.

  • Workflow diagnostics, capability routing, and x402 settlement for MCP-compatible agents.

  • Private-by-default, local-first memory/context/task orchestrator for MCP apps and agents.

View all MCP Connectors

Latest Blog Posts

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/zhouwen-giser/sdar-mcp-tasks-provider-runtime'

If you have feedback or need assistance with the MCP directory API, please join our Discord server