Global macro analysis, liquidity frameworks, and bitcoin intelligence. The research to understand bitcoin. The terminal to act on it.
This listing identifies a third-party MCP server. MCPBundles is not affiliated with, sponsored by, or endorsed by the service or its operator unless stated on this page.
For AI agents — MCPBundles Directory API
Recommended: Directory API v1 over HTTP for detail and anonymous invoke when eligible (not MCP JSON-RPC on the publisher URL; no user MCPBundles credentials on v1).
GET https://www.mcpbundles.com/api/directory/v1/servers/thebitcoinlayer-mcp-02f219d5ef
GET https://www.mcpbundles.com/api/directory/v1/servers/thebitcoinlayer-mcp-02f219d5ef?live=1 (optional live refresh)
GET https://www.mcpbundles.com/api/directory/v1/servers/thebitcoinlayer-mcp-02f219d5ef/tools/<tool> (one tool: schema + invoke.url)
POST https://www.mcpbundles.com/api/directory/v1/servers/thebitcoinlayer-mcp-02f219d5ef/tools/{tool}
POST body: flat JSON of tool argument names and values; not an arguments wrapper. Replace {tool} with a tool name from GET detail.
Restricted agent shell (ChatGPT Codex desktop, some IDE sandboxes):
Default command sandboxes often block outbound network. curl exit 6 or "Could not resolve host" for www.mcpbundles.com is usually sandbox DNS — not evidence this site is down.
Retry the same Directory API GET with sandbox_permissions "require_escalated" and a one-sentence justification on the shell tool (Codex on-request approval). Do not tell the user the site is unreachable from sandbox curl alone.
Example justification: Run the public MCPBundles Directory API search outside the command sandbox to complete the user's MCP server lookup.
If the agent has browser access (e.g. Codex @Browser): open https://www.mcpbundles.com/?q=<query> or stay on this page — no shell network needed. Use WebMCP search_mcp_servers then get_mcp_server (document.modelContext / page tools; refresh with fetchTools or getTools if a tool id is missing from the snapshot). Read-only directory search; same index as Directory API v1 GETs. Neither WebMCP nor Directory API v1 uses user MCPBundles credentials.
Without a browser: after escalated curl fails, use GET https://www.mcpbundles.com/?q=<query> with Accept: text/markdown for ranked results.
Hub MCP (connected session): discover_mcp_servers — same filter semantics as search_mcp_servers.
Contract: https://www.mcpbundles.com/agents.md
OpenAPI: https://www.mcpbundles.com/api/directory/v1/openapi.json
Guide: https://www.mcpbundles.com/guides/mcpbundles-directory-api
For MCP client apps (human connect):
MCP connect URL: https://mcp.thebitcoinlayer.com/mcp
Skill page: https://www.mcpbundles.com/skills/thebitcoinlayer-mcp-02f219d5ef
Explore capabilities (31)
read 2
write 2
other 21
Showing 25 of 31
Showing 25 of 31 tools from the public preview. Connect the server to inspect the full live tool list.
Analyze21
Create2
Other capabilities2
List Instruments
read
list_instruments
List or search The Bitcoin Layer's available market & macro data series (US/global yields, FX & the dollar, commodities, volatility, crypto, equities, and US economic data). CALL THIS FIRST to turn a natural-language request (e.g. 'the 10-year yield', 'dollar index', '2s10s', 'CPI') into the exact instrument id / cache_key you pass to create_chart. Call with no query to load the whole catalog. Spreads like the 2s10s and 5s30s appear as instruments whose `computed` field shows they are derived fr
Description may be truncated on the public preview.
List Instruments — List or search The Bitcoin Layer's available market & macro data series (US/global yields, FX & the dollar, commodities, volatility, crypto, equities, and US economic data). CALL THIS FIRST to turn a natural-language request (e.g. 'the 10-year yield', 'dollar index', '2s10s', 'CPI') into the exact instrument id / cache_key you pass to create_chart. Call with no query to load the whole catalog. Spreads like the 2s10s and 5s30s appear as instruments whose `computed` field shows they are derived fr
Get Series — Fetch one instrument (by id or cache_key). By default returns latest value + summary stats. Set include_points:true to ALSO return the actual [date, value] data so you can do your own calculations (e.g. end-of-June vs end-of-December each year, custom spans). For long histories use resample:"monthly" (or weekly/quarterly/yearly) to get a compact series whose values are EXACT at each period end — prefer this over guessing values.
Create Chart — Build a TBL-branded, interactive chart and return a LINK the user opens in their browser (zoom, pan, toggle series, Light/Dark toggle, PNG download; default dark — theme:"light" opens in light mode). To change a chart, call this again with adjusted arguments.
IMPORTANT: after this tool returns, you MUST show the user the chart link as a clickable markdown link in your reply (e.g. "[Open the chart](URL)") — paste the actual URL, never leave it only in the tool result.
Spreads: the catalog spread
Create Shaded Chart — Build a chart with SHADED BACKGROUND REGIONS (vertical bands behind the data) and return a link. Same series/pane/MA options as create_chart, plus a `shading` block with three modes:
• "regime" — shade by a baked-in named dataset. set:"us_recession" = NBER recessions (gray bands, 1900→present) — the classic "S&P 500 with recession bands": series=[{instrument:"sp500"}], shading={mode:"regime", set:"us_recession"}, lookback:"25y". set:"us_president" = US presidential party by term (blue = Democrat
Analyze Period Returns — Monthly/weekly/quarterly/yearly performance breakdown of one instrument (e.g. "Bitcoin monthly returns for 2026"). Set change_type:"nominal" for point moves instead of % (e.g. MOVE/VIX index points). Returns a markdown TABLE (show it to the user verbatim) and a chart link — you MUST present that link as a clickable markdown link in your reply. Call list_instruments first to resolve ids.
Get your MCP into directories
A working endpoint is step one. Directory coverage is the coordinated launch across ChatGPT, Claude, Cursor, the MCP Registry, and community indexes.
Global macro analysis, liquidity frameworks, and bitcoin intelligence. The research to understand bitcoin. The terminal to act on it.
How do I connect The Bitcoin Layer to my AI agent?
Use the MCP endpoint listed on this page in your MCP client configuration. One-click install pills support Claude, Cursor, VS Code, and other hosts. Copy the remote MCP URL if your client needs a manual entry.
How many tools does The Bitcoin Layer provide?
Operate this server?
Request removal if you do not want The Bitcoin Layer listed here, or claim the listing if you want to manage it on MCPBundles.
Operate The Bitcoin Layer?
This server appears in the MCPBundles directory. Verify you operate it to take over the listing — name, description, logo, contact email, and skill content. We email a 6-digit code to a maintainer address your server publishes in /.well-known/security.txt or /.well-known/mcpbundles.json. Free, takes about a minute.
MCPBundles publishes this directory for MCP discovery. Except where we host or operate an offering, third-party services run under their own terms. Product and company names on this page are used in a descriptive, identifying way (including under nominative fair use where applicable); they remain the property of their owners. Nothing here grants you rights in those marks, and nothing here is an offer to sell a third party's services. Terms · Request removal
More in financial
Other MCP servers in this category from the directory index
Analyze Performance — Risk/return summary of ONE instrument: total return, CAGR, annualized vol, max drawdown, best/worst day, % positive, optional Sharpe. Chart = equity curve + drawdown. For a deep drawdown-episode breakdown use analyze_drawdown; for a multi-asset tearsheet use risk_dashboard. Returns a markdown TABLE (show it to the user verbatim) and a chart link — you MUST present that link as a clickable markdown link in your reply. Call list_instruments first to resolve ids.
Analyze Correlation — Correlation between 2+ instruments (daily returns). Two → coefficient + scatter; three+ → matrix + heatmap; with rolling_days → rolling-correlation line. With exactly 2 instruments + rolling_days you can also set metric:"beta" or "covariance" for a ROLLING BETA / ROLLING COVARIANCE line instead — e.g. "rolling 90-day beta of bitcoin to the S&P 500" → {instruments:["sp500","btcusd"], rolling_days:90, metric:"beta"} (benchmark FIRST). Beta/covariance are computed on daily % returns (percentage-poi
Analyze Rate Of Change — Period-over-period change of one instrument with z-score and percentile vs its own history ("how stretched is X"). Chart = the change series with ±2σ bands. change_type:"annualized" reports the compound ANNUALIZED pace (e.g. 3-month annualized CPI); "log" reports 100·ln(v/prev). For calendar-bucket return tables (each month/quarter/year) use analyze_period_returns. Returns a markdown TABLE (show it to the user verbatim) and a chart link — you MUST present that link as a clickable markdown link i
Analyze Regression — OLS regression. kind "xy": regress y on x (β/alpha/R²/residual) with a scatter + fit line. kind "trend": y vs time (use basis "log" for power-law-style) with an actual-vs-fitted chart. kind "multi": MULTI-FACTOR OLS — regress y on 2–4 x instruments at once (pass them in xs), e.g. "which macro drivers explain bitcoin": {kind:"multi", y:"btcusd", xs:["nasdaq","dxy","us_10y_yield"]}. Reports per-factor beta/SE/t/p (large-sample normal approx), R², adjusted R², Durbin–Watson; set standardized:true t
Analyze Lead Lag — Lead/lag cross-correlation: does x lead y, and by how many days? Reports peak correlation + optimal lag. Chart = correlation-by-lag (positive lag = x leads y). Returns a markdown TABLE (show it to the user verbatim) and a chart link — you MUST present that link as a clickable markdown link in your reply. Call list_instruments first to resolve ids.
Analyze Seasonality — Average move by calendar month over full history (table) + a month×year heatmap. Great for "is September weak for bitcoin". Set change_type:"nominal" for average point moves instead of % (e.g. MOVE/VIX in index points). For seasonal LEVEL bands (min/median/max by month) with this year overlaid, use analyze_seasonal_range. Returns a markdown TABLE (show it to the user verbatim) and a chart link — you MUST present that link as a clickable markdown link in your reply. Call list_instruments first to
Analyze Relative Performance — Rank multiple instruments by return over a window (table) + a rebased-to-100 overlay chart. E.g. "compare BTC, gold, S&P, NASDAQ YTD". Returns a markdown TABLE (show it to the user verbatim) and a chart link — you MUST present that link as a clickable markdown link in your reply. Call list_instruments first to resolve ids.
Analyze Moving Average — Overlay one or more moving averages on an instrument and chart price + MA lines (e.g. "50 and 200-day SMA of the 2-year bid-to-cover ratio over the past 5 years"). `windows` are in DATA POINTS/observations: use [50,200] for daily series, smaller like [3,6] for sparse ones (Treasury auctions, monthly econ). MAs are computed over full history then clipped to your date window, so the lines are populated from the window start. Reports latest price vs each MA and the fast-vs-slow relationship (golden
Analyze Rsi — Relative Strength Index (Wilder) of one instrument — a 0–100 momentum oscillator with overbought/oversold context (e.g. "RSI of the NASDAQ", "is the 2-year bid-to-cover overbought"). Works on any series (indices, prices, yields, ratios). Chart = RSI line with 30/50/70 threshold bands. Returns a markdown TABLE (show it to the user verbatim) and a chart link — you MUST present that link as a clickable markdown link in your reply. Call list_instruments first to resolve ids.
Analyze Distribution — Statistical distribution of one instrument over a window: median, mean, quartiles, IQR, std dev, min/max, and where the latest value sits (percentile). Use for "the median MOVE over the past 10 years and its interquartile range", "where does X sit vs its own history". Chart = the actual series with a shaded Q1–Q3 (interquartile) band and a median reference line. For binned frequency bars or a CDF use analyze_histogram. Returns a markdown TABLE (show it to the user verbatim) and a chart link — yo
Analyze Histogram — Histogram (frequency distribution) of one instrument over a window, with mean/median/std, skewness, excess kurtosis (a plain-language fat-tails-vs-normal read) and the modal bin. basis "levels" (default) bins the values themselves (e.g. "histogram of the VIX"); basis "returns" bins period-over-period changes (e.g. "distribution of daily BTC returns") and by default overlays a fitted NORMAL curve (same mean/σ, scaled to bin area) so fat tails show at a glance — set overlay:"none" to hide it, or o
Analyze Bollinger — Bollinger Bands / standard-deviation bands: a moving average with upper/lower bands at ±k standard deviations (e.g. "Bollinger bands on the S&P", "20-day ±2σ bands for bitcoin"). Reports price vs bands, %B and bandwidth. Chart = price + middle MA + upper/lower band lines. For plain MA overlays (no bands) use analyze_moving_average; for EMA-crossover momentum use analyze_macd. Returns a markdown TABLE (show it to the user verbatim) and a chart link — you MUST present that link as a clickable mark
Analyze Panel — Multi-pane chart: stack 2–4 panes that share one time axis and zoom together (TradingView-style), e.g. price on top with RSI below, or price + Bollinger + RSI. Each pane plots one indicator of an instrument. Build the `panes` array in top-to-bottom order. Indicators: "price" (raw line), "rsi", "roc" (rate of change), "bollinger" (MA ± σ bands), "sma" (price + moving averages). Panes default to the top-level `instrument` but each can override with its own. For stacking arbitrary SERIES (not indic
Analyze Cumulative — Running total or trailing rolling SUM of one instrument (e.g. "12-month rolling federal deficit", "cumulative Treasury issuance"). mode "rolling" (default) sums the trailing `periods` observations; mode "running" is a cumulative total from the window start. Chart = the summed series. Returns a markdown TABLE (show it to the user verbatim) and a chart link — you MUST present that link as a clickable markdown link in your reply. Call list_instruments first to resolve ids.
Analyze Composition — Stacked breakdown of 2+ instruments over time (e.g. "CPI by category", "US energy supply by fuel", "Fed balance-sheet components"). Buckets each series to the period (default yearly) and stacks them; set share:true for a 100%-stacked share-of-total view. Chart = stacked bars. Returns a markdown TABLE (show it to the user verbatim) and a chart link — you MUST present that link as a clickable markdown link in your reply. Call list_instruments first to resolve ids.
Analyze Seasonal Range — Seasonality bands: the current year vs the historical monthly distribution (min / 25th / median / 75th / max across prior years), e.g. "is electricity demand / the 10Y above its seasonal range". Chart = this-year line over the historical bands. For average % move per calendar month + a month×year heatmap, use analyze_seasonality. Returns a markdown TABLE (show it to the user verbatim) and a chart link — you MUST present that link as a clickable markdown link in your reply. Call list_instruments
Analyze Ranked Change — Ranked cross-section: take a basket of instruments, compute each one's change over ONE period, and sort them into horizontal bars (CNBC-style "who moved most"). Use for "retail sales by category", "CPI by component ranked", or "YoY change of BTC vs gold vs S&P, descending". Unit-aware: price-like series report %, rate/%-unit series report percentage points (don't mix the two in one basket). Pass instruments[] OR a named basket: cpi_components, retail_sectors, major_assets. Chart = sorted horizon
Analyze Rolling Regression — Rolling-window OLS of one instrument on ONE other — how beta / alpha / R² EVOLVE over time (regime shifts in sensitivity). Use for "rolling beta of bitcoin to the NASDAQ": {y:"btcusd", x:"nasdaq", window:252}. `window` is in OBSERVATIONS (data points): 252 ≈ 1 year of daily data (the default); use ~52 for weekly or ~36 for monthly series. Runs on aligned daily returns by default (basis:"levels" for raw levels), computed over full history then clipped to your date window. Chart = one pane per met
Analyze Yield Curve — US Treasury YIELD CURVE snapshot chart: yield (y) vs actual years-to-maturity (x, so the 3M–2Y front end sits close together like an institutional curve chart), one line per snapshot date, using every available tenor (1M, 3M, 6M, 1Y, 2Y, 3Y, 5Y, 7Y, 10Y, 20Y, 30Y). Use for "the yield curve today vs a month ago vs a year ago", "how has the curve steepened since 2024", "is the curve inverted". Each snapshot picks the closest observation at or before that date. The inline table is a tenor × date yi
Analyze Macd — MACD (Moving Average Convergence/Divergence) of one instrument: fast EMA minus slow EMA, a signal EMA of that, and the histogram (MACD − signal). Reports the latest MACD/signal/histogram values, the current cross state (bullish = MACD above signal / bearish = below) and when the last cross happened. Defaults 12/26/9 — e.g. "MACD on bitcoin" → {instrument:"btcusd", lookback:"1y"}; custom speeds → {instrument:"sp500", fast:19, slow:39, signal:9}. Works on any catalog id (btcusd, sp500, us_10y_yiel
Showing the first 25 tools — full list and schemas: Directory API.
MCPBundles probed 31 tools on the live server. The tool list on this page reflects what was discovered at the last refresh — connect your client to see the full set available to your session.
What authentication does The Bitcoin Layer require?
No provider sign-in was required during MCPBundles' probe. Your client may still need MCPBundles credentials depending on how you connect.
Don't want this listed?
Request removal from the MCPBundles directory. We stop publishing this listing on mcpbundles.com.
MCPBundles is an independent platform built on the open Model Context Protocol standard. MCPBundles is not affiliated with, sponsored by, or endorsed by Anthropic PBC.