blocklens-mcp-server
MCP server for Blocklens Bitcoin on-chain analytics, providing AI agents access to 127 on-chain metrics and chart rendering.
README
blocklens-mcp-server
MCP (Model Context Protocol) server for Blocklens Bitcoin on-chain analytics. Connect your AI agent to 127 on-chain metrics computed from raw blockchain data — no API wrappers, no delays.
Quick Start
Remote Access (No Install)
Connect directly to the hosted endpoint — no packages, no local setup:
Claude.ai (Browser): Settings → Connectors → Add → URL: https://mcp.blocklens.co
Claude Desktop / Cursor / Windsurf (via mcp-remote):
{
"mcpServers": {
"blocklens": {
"command": "npx",
"args": ["mcp-remote", "https://mcp.blocklens.co"]
}
}
}
Any MCP HTTP client: POST to https://mcp.blocklens.co (Streamable HTTP transport)
Local Install
Claude Desktop
Add to your claude_desktop_config.json:
{
"mcpServers": {
"blocklens": {
"command": "npx",
"args": ["-y", "blocklens-mcp-server"],
"env": {
"BLOCKLENS_API_KEY": "blk_your_key_here"
}
}
}
}
Config file location:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json
Cursor / Windsurf
Add to your MCP config (.cursor/mcp.json):
{
"blocklens": {
"command": "npx",
"args": ["-y", "blocklens-mcp-server"],
"env": {
"BLOCKLENS_API_KEY": "blk_your_key_here"
}
}
}
Demo Mode (No API Key)
Works without an API key — you get 60 days of history for basic-tier metrics. Get an API key at blocklens.co/api-keys for full access.
Available Tools (15)
| Tool | Description |
|---|---|
list_metrics |
List all 127 available metrics with categories and tiers |
search_metrics |
Search metrics by keyword |
get_metric |
Get full definition of a single metric |
get_categories |
List metric categories with counts |
get_prices |
BTC daily OHLC, market cap, volume, drawdown, realized volatility (1W–1Y) |
get_holder_supply |
LTH/STH supply breakdown, circulating supply |
get_holder_valuation |
Realized cap/price, MVRV, thermo cap, delta cap, balanced price, investor cap |
get_holder_profit |
NUPL, realized/unrealized P/L, SOPR — LTH/STH breakdowns (Pro tier) |
get_cohort_metrics |
Age cohort supply, realized cap, realized price (12 age brackets) |
get_utxo_history |
UTXO set breakdown by age cohort |
get_coindays |
Coin Days Destroyed, liveliness, vaultedness, dormancy, dormancy flow |
get_blockchain |
Block height, blocks mined |
get_cycle_performance |
Cycle performance indexed from lows, ATHs, halvings |
get_latest_metrics |
Latest snapshot across all categories |
render_chart |
Render any metric as PNG with annotations and templates |
Metrics Coverage (127 total)
Market Data (27 metrics)
Price, OHLC, volume, market cap, drawdown from ATH, 6 realized volatility windows (1W, 2W, 1M, 3M, 6M, 1Y), cycle performance, and individual cycle tracks from lows, ATHs, and halvings.
Supply (16 metrics)
Circulating supply, LTH/STH supply, cost basis distribution heatmap, and 12 age cohort supplies (<24h through 10y+) for HODL Waves analysis.
Valuation (41 metrics)
Realized cap, realized price, MVRV (aggregate + LTH/STH), thermo cap, delta cap, average cap, balanced price, investor cap, market cap/thermo cap ratio, and 24 age cohort realized prices and caps.
Profitability (12 metrics)
NUPL, unrealized/realized P/L, SOPR — each with aggregate, LTH, and STH breakdowns.
Coin Days (11 metrics)
Coin Days Destroyed (CDD), binary CDD, supply-adjusted CDD, liveliness, vaultedness, dormancy, dormancy flow, net coin days, coin days accumulated, transferred price, transfer volume.
ETF Analytics (11 metrics)
Total BTC holdings, AUM, net/cumulative flows, cumulative money flow, ETF realized price, US Spot ETF realized price, US Spot cumulative money flow, BTC dominance, US BTC holdings, ETF premium average.
Blockchain (2 metrics)
Block height, blocks mined.
Chart Rendering
The render_chart tool generates PNG charts inline in the conversation.
Quick examples:
render_chart({ metric: "price", days: 365 })
render_chart({ template: "mvrv_ratio" })
render_chart({ metrics: ["lth_supply", "sth_supply"], style: "area" })
render_chart({ metric: "dormancy_flow", overlay: "price" })
render_chart({ template: "realized_volatility", days: 730 })
Annotations — reference lines and areas:
render_chart({
metric: "lth_mvrv",
reference_lines: [
{ "y": 3.5, "label": "Overheated", "stroke": "#ef4444", "dash": "3 3" }
],
reference_areas: [
{ "y1": 0, "y2": 0.85, "label": "Undervalued", "fill": "#22c55e", "fill_opacity": 0.15 }
]
})
Example Prompts
- "What's Bitcoin's current MVRV ratio and what does it say about valuation?"
- "Show me realized volatility — is short-term vol higher than long-term?"
- "Chart dormancy flow with price overlay for the last 2 years"
- "Compare LTH and STH supply trends over 90 days"
- "Are long-dormant coins waking up? Check liveliness and CDD"
- "Show cycle performance from each halving — are we tracking historical patterns?"
- "What's the current NUPL level? Is the market in euphoria or fear?"
Access Tiers
| Tier | History | Metrics | Daily Requests |
|---|---|---|---|
| Demo (no key) | 60 days | Basic (grade 0) | Unlimited |
| Pro ($50/mo) | Unlimited | All grade 0–1 | 10,000 |
| Enterprise ($900/mo) | Unlimited | All grade 0–2 | 100,000 |
Links
- Remote MCP Endpoint
- Blocklens
- Full Documentation
- Metrics Reference
- API Reference
- Get API Key
- MCP Protocol
License
MIT
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
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
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.