HuangtingFlux — Huangting Protocol MCP Server
This server enforces a mandatory three-stage workflow that compresses user prompts before sending them to your LLM, tracks token usage per reasoning step, and appends performance metrics to final outputs. You call start_task to get a condensed instruction and context_id, report_step_result after each operation to log costs, then finalize_and_report to append a markdown table showing savings. It broadcasts stats to a live dashboard at huangtingflux.com and claims 40% token reduction on complex tasks. Built on FastAPI with Redis backing, it exposes these three tools plus get_network_stats over MCP's streamable HTTP transport. Reach for it if you want enforced token accounting baked into your agent loop rather than bolted on afterward.
- tools
- 4
- transport
- HTTP
- last updated
- Mar 18, 2026
Tools
4 toolsPublic tool metadata for what this MCP can expose to an agent.
start_taskCompresses the user's verbose prompt into a core instruction, saving 30-60% of input tokens. Creates a unique context_id for the task.
Compresses the user's verbose prompt into a core instruction, saving 30-60% of input tokens. Creates a unique context_id for the task.
No parameter schema in public metadata yet.
report_step_resultAgent reports the token cost of each reasoning step. This data is broadcast to the live dashboard and stored for the final report.
Agent reports the token cost of each reasoning step. This data is broadcast to the live dashboard and stored for the final report.
No parameter schema in public metadata yet.
finalize_and_reportRefines the agent's final draft and automatically appends a Markdown performance table, making the token savings transparent and verifiable.
Refines the agent's final draft and automatically appends a Markdown performance table, making the token savings transparent and verifiable.
No parameter schema in public metadata yet.
get_network_stats
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageReadme
Huangting-Flux Hub
An Eastern Wisdom Protocol That Reduces Your AI Agent Token Usage by 40%
This repository contains the source code for the HuangtingFlux Hub, the official MCP (Model Context Protocol) server for the Huangting Protocol. It provides a mandatory three-stage Standard Operating Procedure (SOP) for AI Agents to minimize token consumption.
Live Dashboard: huangtingflux.com
MCP Integration Guide
HuangtingFlux is exposed via the standard Model Context Protocol (MCP), allowing for seamless integration with any compliant AI Agent.
Method 1: Manus Agent (Recommended)
In your Manus Agent's MCP settings, add the following server URL:
Details
- Repository
- github.com/xiandao-labs/huangting-flux-hub
- Categories
- AI & LLM Tools, Automation & Workflows
- Transport
- HTTP
- Registry
- MCP registry, active
Related AI & LLM Tools MCP servers
View all
LaunchSpylaunchspyio/launchspy-agentAds, funnels and pricing of coaches and course creators: Meta ads, hooks, funnel X-Ray, tools.0stars
Maindex Expert Memory Servicemaindexapp/maindexTeam-shared memory MCP: 15 tools, search, links, collections, bulk ops, Teams workspaces.0stars
Mcp Audit Serverjoepangallo/mcp-audit-serverThin MCP and CLI proxy for AI agent and MCP security auditing via a hosted backend0stars
Archangel Agency MCPjthora/archangel-agency-mcpUniversal Language briefings, FusionGirl context JSONs, service catalog, agent info. x402-enabled.0stars
Enterprise Internal Knowledge Base: Production-Ready RAG + MCPkimsb2429/internal-knowledge-baseProduction-ready RAG + MCP demo: eval-in-CI merge gate, Langfuse traces, structure-aware chunking.0stars