DeFi Garden
Server Details
Predictively underwritten DeFi yield discovery, goal planning, and risk verification with strict APY sanity rails.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-06-18
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 5 tools
Each tool has a clearly distinct role: rule explanation, multi-criteria pool search, single-pool raw lookup, DeFi Score lookup, and a forever-number calculator. get_pool and get_pool_score both retrieve pool-related data, but their outputs and purposes are explicitly separated.
Most names follow a predictable snake_case verb_noun pattern: explain_rails, find_pools, get_pool, get_pool_score. forever_number is descriptive but lacks a verb and breaks the pattern slightly.
Five tools is well-scoped for a read-only DeFi pool discovery, scoring, and calculation server. Each tool maps to a distinct step an agent would need without redundant surface area.
The surface covers the core workflow: understand filters, search pools, inspect a pool, retrieve its score, and calculate lump-sum requirements. Minor gaps exist, such as no explicit symbol-based raw pool lookup and no stated pagination or supported-chain listing, but agents can work around these via find_pools.
Available Tools
5 toolsexplain_railsAInspect
Returns DeFi Garden's active filtering rules (1000% APY sanity cap, $100K TVL floor, anomaly flagging) and the data source, for autonomous agent safety.
Inputs: no named parameters.
find_poolsAInspect
Search DeFi Garden's railed pool list by token symbol, chain, project, and minimum TVL floor. Excludes anomalous rates (>1000% APY) and pools below $100K TVL. Data is a daily snapshot of DefiLlama's pool feed.
Inputs: chain, limit, token, min_tvl, +1 more.
forever_numberAInspect
Computes the lump-sum capital whose yield alone covers a recurring monthly bill forever, using a TVL-weighted blended rate of railed pools (or a caller-supplied APY between 0 and 1000 percent).
Inputs: monthly (required), apy.
get_poolAInspect
Look up a single pool by its DefiLlama pool UUID, returning APY (base/reward breakdown), TVL, and anomaly / below-floor flags. Data is a daily snapshot of DefiLlama's pool feed.
Inputs: pool_id (required).
get_pool_scoreAInspect
Retrieve the DeFi Score (0-100) with its band name (AAA to HIGH RISK; DeFi Garden's own model output, not a credit rating), each pillar shown as a High / Medium / Low tier, never a number (yield stability, sustainability, capital stickiness, exit liquidity), the experimental 14-day forward yield forecast range (low / central / high), and retail access restrictions. Look up by pool_id, or by exact asset symbol (highest-TVL railed match, with candidates listed). The forecast is experimental.
Inputs: asset, chain, pool_id.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceRemote MCP server that lets AI assistants read tracked competitive intelligence — competitor news, reviews, website changes, social posts and ads — and act on it by managing projects, competitors, battle cards, reports and canvases. Every answer carries a source and a date, and write actions only publish when explicitly shared.MIT
- AlicenseCqualityCmaintenanceCompetitor Monitor AI - MCP server providing AI-powered tools and automation by MEOK AI Labs112 npm37 PyPIMIT
- AlicenseAqualityDmaintenanceEnables brand visibility monitoring across major AI platforms like ChatGPT, Claude, Gemini, and Perplexity. It allows users to track visibility scores, analyze competitor data, and receive actionable insights to improve AI-generated brand recommendations.1611 npm1MIT

industrylens-mcpofficial
AlicenseNot gradedqualityCmaintenanceBrowse IndustryLens's published competitive-intelligence reports and head-to-head competitor comparisons from any AI agent — real, source-backed data.MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.