bitcoinyield-mcp.yml
BitcoinYield serves a remote Model Context Protocol server for AI agents on its own host. No key, account or sign-up; an anonymous tools/list returns two tools.
One-click install for Cursor, VS Code, Claude, and 20+ other MCP clients, powered by API Commons MCP Install — visit install.apicommons.org for more information.
Endpoint
Hosted endpoint · transport streamable-http
Connect
This is a remote MCP server — point an MCP client at the endpoint URL. Clients with native remote support (Claude, Cursor, VS Code, …):
For stdio-only clients (older Claude Desktop, etc.), bridge with mcp-remote:
If the server requires authentication, add the provider's token/header (e.g. an X-API-Key) per its docs. A quick reachability check:
Tool quality observed · not scored
tools with readOnly / destructive hints
parameters described (8 total)
state-changing tools without destructiveHint
tool-list tokens (2 tools)
tools over ~1,200 tokens
Heaviest: list_yields 2417, list_offers 2312
From an anonymous initialize + tools/list capture measured 2026-10-20; tokens are chars/3.6 of each tool definition. Recorded for the Kin Score's agent readiness as an observed signal — it contributes no points yet.
Tools
list_yields— One entry per asset (Bitcoin, ETH, SOL, USDC, USDT and every other tracked stablecoin, tokenized Treasury and L1) with its best current yield across DeFi and CeFi under BitcoinYield's risk-weighted ranking, its A-D risk grade, and a link to the full comparison. by_grade gives the best proven rate at grade A, B and C (A = lower risk), the tradeoff a holder chooses between: a grade is null when nothing proven at it pays materially more (at least 0.05 points and 5%) than a safer grade. best_apy and each by_grade rate are in percent, as the asset page shows them (today's rate, or its 7-day average when that is lower), and rate_basis says whether the source quotes an APY or an APR. To answer 'what is the best yield on X', quote by_grade, the lowest-risk grade first: best_apy is the by_grade step the risk-weighted ranking puts first and can be a higher-risk one, or one closed to US residents. An asset with no proven offer has no pick: best_apy is null and no_pick_reason says why its top-ranked offer is not one. Set max_risk to limit every pick to offers graded at or below that letter. Rates are variable and not advice. No key required. With no asset or stablecoin filter this tool answers the headline assets (BTC, ETH, SOL, USDC, USDT, DAI, USDe, USD1, USDG, PYUSD, RLUSD); set all to true for every asset with a live yield.list_offers— The top live yield offers for one asset (5 by default, up to 20) in BitcoinYield's own order: rate and risk together, with offers that have a month of steady history and $10M+ of liquidity first. Each offer carries its platform, chain, product type, rate (APY or APR), organic versus incentive split, 30-day average, liquidity, A-D risk grade with its main reasons, US availability, investor access, the platform's own deposit link and the page to cite. Filter by chain or a risk ceiling. Use it to compare options; list_yields gives one pick per asset. Rates are variable and not advice. No key required. When nothing matches, the answer says why: the filters, a dollar that lost its peg, or no live quote on the asset.
About MCP
The Model Context Protocol (MCP) is an open protocol Anthropic introduced for connecting LLM-based agents to external tools and data sources. Providers publish MCP servers that expose their API surface as structured, discoverable tools — an MCP-compatible client (Claude Desktop, Cursor, Cline, Continue, etc.) can connect to the server and call its tools without any per-provider integration code.
Browse every MCP server on the APIs.io network or compare with the broader Agent Skill surfaces of the same providers.
Work with this as data
Every MCP server here is available over the APIs.io API and to AI agents over MCP.