MCP Studio Tasks
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
MCP Studio Tasks — Advanced MCP Features & 2026 Stateless Workbench
A self-contained, runnable reference implementation for Model Context Protocol: Advanced Features, aligned with the stateless 2026-07-28 MCP specification (SEP-2577, Multi Round-Trip input-required Elicitation, durable Tasks v2, context-aware Completions, Multimodal outputs, and an end-to-end Chat Agent UI).
Capabilities Implemented
Feature Area | Implemented Behavior | Key Module |
Stateless Core vs. Legacy Sessions | Stateless | |
Server Handles & Opaque State | SQLite cart/workflow handles paired with owner authorization ( | |
Form & URL Elicitation ( | Multi-round-trip | |
Durable Tasks Extension & Notifications | SQLite-persisted Tasks ( | |
Completions & All 6 Content Types | Context-aware | |
End-to-End Chat Agent & Console UI | SDK-style async chat client handling tool selection, interactive elicitation prompts, background task polling, live SSE progress, and inline media/link rendering in a Light/Dark UI |
Related MCP server: production-grade-mcp-agentic-system
Quickstart
cd mcp-studio-tasks
uv sync --extra dev
uv run uvicorn mcp_studio_tasks.main:app --reload --port 8012Open http://127.0.0.1:8012 for the interactive Chat & Studio Workbench, or run the full automated test suite:
uv run pytest -vDocumentation
SPECIFICATION.md— Constitution invariants (INV-ADV-*) and traceable requirements (REQ-ADV-*)docs/ARCHITECTURE.md— Protocol sequence diagram and module responsibilitiesdocs/SPEC_MIGRATION_2026.md— WhyMcp-Session-Id,sampling, androots(SEP-2577) shifted to stateless_meta,input-required, and Tasks v2
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
MCP server for your apps' tools and custom tools, plus hosted AI agents and approval-gated workflows
Nifty's MCP server — exposes tasks, projects, messages, and files as tools for AI agents.
MCP server for progressive tool usage at any scale (see https://klavis.ai)
A full backend your AI coding agent can set up over MCP
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceA reference implementation demonstrating proper MCP server patterns with HTTP transport, featuring session management, progress notifications, and example tools for testing server functionality. Serves as a clean template for building MCP servers with streamable responses and comprehensive error handling.7MIT
- AlicenseNot gradedqualityDmaintenanceA production-grade MCP server designed for multi-tenant, authenticated, and observable AI agent systems, enabling secure tool execution across heterogeneous data sources.68MIT
- AlicenseNot gradedqualityDmaintenanceA minimal MCP server with sample tools, resources, and prompts, plus an aggregator to connect multiple external MCP servers and REST APIs, including experimental OAuth support.MIT
- FlicenseNot gradedqualityDmaintenanceLocal MCP server that exposes fixed tools for GPT, Claude, and Gemini while routing to any OpenAI-compatible chat completions backend with independent configuration per target.1-