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.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.