concierge-hq/concierge
🚀 Universal SDK for building next-gen MCP servers
Implements progressive tool disclosure by organizing capabilities into workflow stages with enforced transitions, reducing context window bloat and ensuring agents follow defined business logic paths. Provides optional semantic search for large APIs (100+ tools), session-scoped state sharing between steps, and multiple transports (stdio, HTTP, SSE) while remaining protocol-compatible with existing MCP servers through zero-change wrapping.
481 stars.
Stars
481
Forks
101
Language
Python
License
—
Category
Last pushed
Mar 11, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/mcp/concierge-hq/concierge"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
Related servers
activepieces/activepieces
AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation /...
evalstate/fast-agent
Code, Build and Evaluate agents - excellent Model and Skills/MCP/ACP Support
flytohub/flyto-core
The open-source execution engine for AI agents. 412 modules, MCP-native, triggers, queue,...
Klavis-AI/klavis
Klavis AI (YC X25): MCP integration platforms that let AI agents use tools reliably at any scale
Azure-Samples/AI-Gateway
Labs to explore AI Models, MCP servers, and Agents with the AI Gateway powered by Azure API...