mcp-midasflow
MidasFlow Flow API - Cross-exchange order flow, whale detection, liquidations, funding rates, squeeze alerts for AI agents. Native MCP server.
README
MidasFlow Flow API — MCP Quickstart
Agent-native crypto market-data feed for AI agents and LLMs. Connect Claude, ChatGPT, Cursor, or any MCP-compatible agent to cross-exchange order flow, whale prints, liquidations, derivatives context, anomaly/squeeze detection, and calibrated P(TP1) scores — over a native Model Context Protocol (MCP) server or plain REST, with one Bearer key.
⚠️ Market DATA, not financial advice. And not the Flow (FLOW) blockchain — this is MidasFlow Flow API.
- MCP server:
https://mcp.midasflow.ai/mcp - REST base:
https://mcp.midasflow.ai/v1 - Keyless schema (self-describing, no auth):
https://mcp.midasflow.ai/v1/schema - Docs: https://midasflow.ai/docs/api
- Get a key: https://midasflow.ai/app/ (free tier — 200 units/day)
What it gives an agent
A single Bearer-key feed of cross-exchange crypto market DATA, shaped for an LLM to reason over:
- Order flow — CVD, cross-exchange flow origin (where the aggression actually comes from)
- Whale prints + multi-exchange liquidations + liquidation heatmap
- Derivatives context — funding, open interest, basis
- Anomalies, squeeze proximity, regime/phase context, support/resistance, sweeps
- Calibrated P(TP1) scores + structured trade plans (size by expectancy, not vibes)
- Realized track-record / accuracy feeds (honest win-rate with confidence bounds)
The agent discovers the full, current tool + field set itself from the keyless schema — no hardcoded parser to break:
curl -s https://mcp.midasflow.ai/v1/schema | jq '.tiers, .endpoints[].path'
Connect
Claude Code / CLI (remote MCP)
claude mcp add --transport http midasflow https://mcp.midasflow.ai/mcp \
--header "Authorization: Bearer mf_live_YOUR_KEY"
Claude Desktop (config)
See examples/claude_desktop_config.json. Add the midasflow block to your mcpServers and replace the key.
Any MCP client
Point it at the remote Streamable-HTTP endpoint https://mcp.midasflow.ai/mcp with header Authorization: Bearer mf_live_YOUR_KEY.
REST (no MCP client needed)
See examples/rest_quickstart.sh:
# whole-market context (cheap), then a per-symbol calibrated score
curl -s -H "Authorization: Bearer mf_live_YOUR_KEY" https://mcp.midasflow.ai/v1/market
curl -s -H "Authorization: Bearer mf_live_YOUR_KEY" https://mcp.midasflow.ai/v1/score/BTCUSDT
Tiers (agent / API — daily weighted units)
| Tier | Price | Units/day | Notes |
|---|---|---|---|
| Free | $0 | 200 | feed ~15 min lagged; great for poking the schema |
| PRO | $49/mo | 750 | real-time |
| VIP | $99/mo | 1,500 | real-time + raw PUMP + per-signal edge band |
| Prime | $199/mo | 8,500 | model scores + MFBreakout |
| Apex | $399/mo | 16,600 | everything + priority rate-limit / queue |
Each tier also includes the human-facing Telegram bot. A "unit" is a weighted cost (context calls ~1, heavy crown calls up to ~12); see GET /v1/usage for live weights.
License
The sample code in this repo is MIT (see LICENSE). The MidasFlow Flow API service itself is proprietary / commercial.
MidasFlow Flow API — market DATA for AI agents. Founded 2022. Not financial advice; not the Flow (FLOW) blockchain.
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.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
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.