yieldhunter is an MCP server published by io.github.agentsherpa, hosted at yieldhunter-agent-production.up.railway.app. When last checked on 2026-11-21 it was working: it answers and lists its tools. It declares 6 tools, including health, list_yields, score_opportunity, compare_opportunities, explain_score.
Risk-adjusted stablecoin yield ranks for other agents. Research only. Never holds keys or executes.
4 connections through 5 shared values. Tap any node.
Inferred from the host name and headers: what a server runs on, not who runs it.
Liveness and capability check for yieldhunter (yieldhunter.eth). Returns service status, schemaVersion, scoringVersion, feature flags, and the list of available tools. Use this first to verify connectivity. If yields+pegs vintage is missing or at/over YH_STALE_DEGRADE_SECONDS (default 2h), health may refresh DefiLlama market caches once (same adapters as list_yields; not a list_yields tool call). Kill switch on: health still answers, refresh skipped. Research estimates only — non-custodial; never holds keys or executes transactions. Copy-paste path starts here, then list_yields. Example input: {}
No parameters.
{
"name": "health",
"title": "Health",
"description": "Liveness and capability check for yieldhunter (yieldhunter.eth).\n\nReturns service status, schemaVersion, scoringVersion, feature flags, and the list of available tools.\n\nUse this first to verify connectivity. If yields+pegs vintage is missing or at/over YH_STALE_DEGRADE_SECONDS (default 2h), health may refresh DefiLlama market caches once (same adapters as list_yields; not a list_yields tool call). Kill switch on: health still answers, refresh skipped. Research estimates only — non-custodial; never holds keys or executes transactions.\n\nCopy-paste path starts here, then list_yields.\nExample input: {}",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}None yet. Changes appear after a server's second daily check.
Squares are this server's values; dots are other servers sharing them. A shared address or publisher is a lead, not proof of a common operator.
Rank stablecoin yield opportunities on Ethereum, Base, and Arbitrum using multi-factor **risk-adjusted** scoring (not raw APY). chains/chainIds: those three only (aliases eth/ETH/Ethereum, arb/ARB, BASE) — any unsupported or blank value (solana, optimism, "") is VALIDATION_ERROR, not a silent default-universe fallback. sourceChainKey: same keys/aliases; blank or unknown keys are VALIDATION_ERROR (bridge cost is not estimated). Default ranking is risk-adjusted score, not highest APY. For headline yield order, use sortBy=net_apy. Default is risk-adjusted ranking with balanced weights. Optional params are policy controls for visiting agents. Default when omitted: sortBy=risk_adjusted, sortOrder=desc, riskAppetite=balanced (v1.1 weights), no minScore, no category filter, diversity=soft (max 2 markets per protocol in presented top-k). Primary composite key: compositeRiskAdjusted (protocol risk, depeg/counterparty, liquidity, yield quality base vs incentive, net yield after gas/bridge). Opportunities may include stability signals: apyChange24h is pool-level DefiLlama apyPct1D when present as a number (including 0 = observed flat change); null/missing means unknown/not provided for that pool (e.g. some Pendle markets) — not the same as 0, never invent 0; tvlChange24hPct is protocol-level DefiLlama change_1d (shared across markets of the same protocol — not this pool's TVL flow; missing stays null); large APY jumps warn only. Also exitRisk/exitRiskReason (size-vs-pool liquidity heuristic only: pool TVL vs notionalUsd + liquidity confidence — not on-chain withdraw, not queue/cap/pause/lockup, not transfer whitelist/eligibility/redemption, not an execution gate; unknown ≠ safe; medium often means liquidity confidence medium, not “small pool”; low is strict; when knownIssues mention transfer/eligibility do not treat low as free exit; soft warnings on high/unknown, plus low/medium if those issues are present; does not change default risk-adjusted ranking). Optional policy knobs: sortBy (risk_adjusted|net_apy|gross_apy|tvl), sortOrder, riskAppetite (conservative|balanced|aggressive), minScore (0–100 after appetite; practical bands ~≥85 treasury default, ≥80 selective; 90 is rare/very strict — a few top L2 blue-chips may clear it), categories / excludeCategories (lending|rwa|other), diversity (soft|off — default top prefers protocol diversity; set off for every market from one protocol), includeFactors (boolean, default false — when true each opportunity has scores.factors compact map without a second tool call), maxRewardShare (0–1 optional incentive-share gate only — max reward/total; e.g. 0.3 treasury, 0.25 stricter; unknown share excluded when set; does not remove high base-only APY farms — pair with minScore/riskAppetite/excludeCategories for capital preservation). Prefer this when capital preservation and sustainable yield matter more than headline APY. Research only — never executes transactions or holds keys. Copy-paste path (after health {}): { "assets": ["USDC"], "sortBy": "risk_adjusted" } Then contrast #1 vs #2 (risk-adjusted winner vs next row — often higher rate / thinner liquidity / other chain). Do not contrast against the max-APY row in the ten. Examples: (a) Treasury/conservative: { "riskAppetite": "conservative", "minScore": 85, "excludeCategories": ["rwa"], "maxRewardShare": 0.3, "minTvlUsd": 10000000, "limit": 10 } (b) Default research (v1.1): { "assets": ["USDC"], "sortBy": "risk_adjusted" } (c) Yield-seeking: { "sortBy": "net_apy", "riskAppetite": "aggressive", "chains": ["base"], "assets": ["USDC"], "limit": 15 } (d) With factor breakdown: { "assets": ["USDC"], "limit": 5, "includeFactors": true }
| Parameter | Type | Description |
|---|---|---|
| limit | integer | Max results to return (default 10, max 25). Example: 10 |
| assets | array | Stablecoin symbols to match in pool symbol, e.g. ["USDC","USDT"] |
| chains | array | Filter chains: ethereum | base | arbitrum (aliases eth/ETH/Ethereum, arb/ARB, BASE; or Llama names). Default when field omitted: all three. Blank, whitespace, or unsupported values (solana, optimism, "") are VALIDATION_ERROR — not a silent fallback. Example: ["base","ethereum"] |
| sortBy | string | Sort key: "risk_adjusted" (default) | "net_apy" | "gross_apy" | "tvl" |
| chainIds | array | Optional numeric chain ids: 1, 8453, 42161 only. Any other id is VALIDATION_ERROR (not a silent default-universe fallback). |
| minScore | any | Minimum compositeRiskAdjusted after appetite weights (0–100). Omitted = no filter |
| diversity | string | Presented top-k protocol diversity: "soft" (default, max 2 per protocol) | "off" (plain score order, every market) |
| minTvlUsd | number | Minimum TVL in USD (default 1000000). Example: 5000000 |
| protocols | array | Optional protocol slugs, e.g. ["aave-v3","morpho-blue"]. Blank entries are VALIDATION_ERROR (not treated as all protocols). |
| sortOrder | string | Sort direction: "desc" (default) | "asc" |
| categories | array |
{
"name": "list_yields",
"title": "List risk-adjusted yields",
"description": "Rank stablecoin yield opportunities on Ethereum, Base, and Arbitrum using multi-factor **risk-adjusted** scoring (not raw APY). chains/chainIds: those three only (aliases eth/ETH/Ethereum, arb/ARB, BASE) — any unsupported or blank value (solana, optimism, \"\") is VALIDATION_ERROR, not a silent default-universe fallback. sourceChainKey: same keys/aliases; blank or unknown keys are VALIDATION_ERROR (bridge cost is not estimated).\n\nDefault ranking is risk-adjusted score, not highest APY. For headline yield order, use sortBy=net_apy.\n\nDefault is risk-adjusted ranking with balanced weights. Optional params are policy controls for visiting agents.\n\nDefault when omitted: sortBy=risk_adjusted, sortOrder=desc, riskAppetite=balanced (v1.1 weights), no minScore, no category filter, diversity=soft (max 2 markets per protocol in presented top-k). Primary composite key: compositeRiskAdjusted (protocol risk, depeg/counterparty, liquidity, yield quality base vs incentive, net yield after gas/bridge). Opportunities may include stability signals: apyChange24h is pool-level DefiLlama apyPct1D when present as a number (including 0 = observed flat change); null/missing means unknown/not provided for that pool (e.g. some Pendle markets) — not the same as 0, never invent 0; tvlChange24hPct is protocol-level DefiLlama change_1d (shared across markets of the same protocol — not this pool's TVL flow; missing stays null); large APY jumps warn only. Also exitRisk/exitRiskReason (size-vs-pool liquidity heuristic only: pool TVL vs notionalUsd + liquidity confidence — not on-chain withdraw, not queue/cap/pause/lockup, not transfer whitelist/eligibility/redemption, not an execution gate; unknown ≠ safe; medium often means liquidity confidence medium, not “small pool”; low is strict; when knownIssues mention transfer/eligibility do not treat low as free exit; soft warnings on high/unknown, plus low/medium if those issues are present; does not change default risk-adjusted ranking).\n\nOptional policy knobs: sortBy (risk_adjusted|net_apy|gross_apy|tvl), sortOrder, riskAppetite (conservative|balanced|aggressive), minScore (0–100 after appetite; practical bands ~≥85 treasury default, ≥80 selective; 90 is rare/very strict — a few top L2 blue-chips may clear it), categories / excludeCategories (lending|rwa|other), diversity (soft|off — default top prefers protocol diversity; set off for every market from one protocol), includeFactors (boolean, default false — when true each opportunity has scores.factors compact map without a second tool call), maxRewardShare (0–1 optional incentive-share gate only — max reward/total; e.g. 0.3 treasury, 0.25 stricter; unknown share excluded when set; does not remove high base-only APY farms — pair with minScore/riskAppetite/excludeCategories for capital preservation).\n\nPrefer this when capital preservation and sustainable yield matter more than headline APY.\n\nResearch only — never executes transactions or holds keys.\n\nCopy-paste path (after health {}): { \"assets\": [\"USDC\"], \"sortBy\": \"risk_adjusted\" }\nThen contrast #1 vs #2 (risk-adjusted winner vs next row — often higher rate / thinner liquidity / other chain). Do not contrast against the max-APY row in the ten.\n\nExamples:\n(a) Treasury/conservative: { \"riskAppetite\": \"conservative\", \"minScore\": 85, \"excludeCategories\": [\"rwa\"], \"maxRewardShare\": 0.3, \"minTvlUsd\": 10000000, \"limit\": 10 }\n(b) Default research (v1.1): { \"assets\": [\"USDC\"], \"sortBy\": \"risk_adjusted\" }\n(c) Yield-seeking: { \"sortBy\": \"net_apy\", \"riskAppetite\": \"aggressive\", \"chains\": [\"base\"], \"assets\": [\"USDC\"], \"limit\": 15 }\n(d) With factor breakdown: { \"assets\": [\"USDC\"], \"limit\": 5, \"includeFactors\": true }",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"limit": {
"type": "integer",
"maximum": 25,
"description": "Max results to return (default 10, max 25). Example: 10",
"exclusiveMinimum": 0
},
"assets": {
"type": "array",
"items": {
"type": "string"
},
"description": "Stablecoin symbols to match in pool symbol, e.g. [\"USDC\",\"USDT\"]"
},
"chains": {
"type": "array",
"items": {
"type": "string"
},
"description": "Filter chains: ethereum | base | arbitrum (aliases eth/ETH/Ethereum, arb/ARB, BASE; or Llama names). Default when field omitted: all three. Blank, whitespace, or unsupported values (solana, optimism, \"\") are VALIDATION_ERROR — not a silent fallback. Example: [\"base\",\"ethereum\"]"
},
"sortBy": {
"enum": [
"risk_adjusted",
"net_apy",
"gross_apy",
"tvl"
],
"type": "string",
"description": "Sort key: \"risk_adjusted\" (default) | \"net_apy\" | \"gross_apy\" | \"tvl\""
},
"chainIds": {
"type": "array",
"items": {
"type": "integer"
},
"description": "Optional numeric chain ids: 1, 8453, 42161 only. Any other id is VALIDATION_ERROR (not a silent default-universe fallback)."
},
"minScore": {
"anyOf": [
{
"type": "number",
"maximum": 100,
"minimum": 0
},
{
"type": "null"
}
],
"description": "Minimum compositeRiskAdjusted after appetite weights (0–100). Omitted = no filter"
},
"diversity": {
"enum": [
"soft",
"off"
],
"type": "string",
"description": "Presented top-k protocol diversity: \"soft\" (default, max 2 per protocol) | \"off\" (plain score order, every market)"
},
"minTvlUsd": {
"type": "number",
"minimum": 0,
"description": "Minimum TVL in USD (default 1000000). Example: 5000000"
},
"protocols": {
"type": "array",
"items": {
"type": "string"
},
"description": "Optional protocol slugs, e.g. [\"aave-v3\",\"morpho-blue\"]. Blank entries are VALIDATION_ERROR (not treated as all protocols)."
},
"sortOrder": {
"enum": [
"asc",
"desc"
],
"type": "string",
"description": "Sort direction: \"desc\" (default) | \"asc\""
},
"categories": {
"type": "array",
"items": {
"enum": [
"lending",
"rwa",
"other"
],
"type": "string"
},
"description": "Include only these categories: \"lending\" | \"rwa\" | \"other\""
},
"horizonDays": {
"type": "number",
"maximum": 365,
"description": "Holding horizon in days for gas/bridge amortization (default 30). Example: 30",
"exclusiveMinimum": 0
},
"notionalUsd": {
"type": "number",
"description": "Notional USD size for net-yield cost amortization and exitRisk TVL multiples (default 10000). Example: 10000",
"exclusiveMinimum": 0
},
"riskAppetite": {
"enum": [
"conservative",
"balanced",
"aggressive"
],
"type": "string",
"description": "Scoring weight profile: \"balanced\" (default/v1.1) | \"conservative\" | \"aggressive\""
},
"includeFactors": {
"type": "boolean",
"description": "If true, each opportunity includes scores.factors compact map (protocolRisk, depegCounterparty, liquidity, yieldQuality, costAdjusted). Default false — omits heavy factors[] rationales."
},
"maxRewardShare": {
"anyOf": [
{
"type": "number",
"maximum": 1,
"minimum": 0
},
{
"type": "null"
}
],
"description": "Incentive-share gate only: max reward/total of gross APY, 0–1 (e.g. 0.3 treasury, 0.25 stricter). Does not remove high base-only APY farms. Capital preservation still needs minScore/riskAppetite/excludeCategories. Omitted = no filter. Unknown share excluded when set."
},
"sourceChainKey": {
"type": "string",
"description": "Agent's current chain for bridge cost estimate: ethereum | base | arbitrum (aliases: eth, ETH, Ethereum, arb, ARB, BASE). Blank/whitespace is VALIDATION_ERROR (omit the field to default). Unknown keys (solana, foo) return VALIDATION_ERROR — no invented bridge fee."
},
"excludeCategories": {
"type": "array",
"items": {
"$ref": "#/properties/categories/items"
},
"description": "Exclude these categories, e.g. [\"rwa\"]"
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": true,
"destructiveHint": false
}
}Compute the full multi-factor risk-adjusted score for a single opportunity from list_yields. Chain: pass list_yields opportunities[].id as poolId, opportunityId, or id (same DefiLlama pool UUID; id is the canonical list field). Returns APY breakdown (base/reward/total), factor scores with rationales, net yield after gas/bridge, exitRisk heuristic (TVL vs notional + liq conf only; medium ≠ small pool; not queues/caps/transfer whitelist/eligibility/on-chain withdraw; do not treat low as free exit when knownIssues mention transfer/eligibility), warnings, and sources. sourceChainKey is ethereum|base|arbitrum only — unknown keys (foo, solana) are VALIDATION_ERROR; no invented bridge fee. Research estimates only — non-custodial. Example (any one id field): { "id": "43641cf5-a92e-416b-bce9-27113d3c0db6", "horizonDays": 30, "notionalUsd": 10000 } Also accepts poolId or opportunityId with the same value.
| Parameter | Type | Description |
|---|---|---|
| id | string | Same as list_yields opportunities[].id (canonical response field name). |
| poolId | string | Alias for list_yields opportunities[].id (historical tool field). Same DefiLlama pool UUID. Example: "43641cf5-a92e-416b-bce9-27113d3c0db6" |
| horizonDays | number | Holding horizon in days for gas/bridge amortization (default 30). Example: 30 |
| notionalUsd | number | Notional USD size for net-yield cost amortization and exitRisk TVL multiples (default 10000). Example: 10000 |
| opportunityId | string | Alias for list_yields opportunities[].id (same pool key as poolId / id). |
| sourceChainKey | string | Agent's current chain for bridge cost estimate: ethereum | base | arbitrum (aliases: eth, ETH, Ethereum, arb, ARB, BASE). Blank/whitespace is VALIDATION_ERROR (omit the field to default). Unknown keys (solana, foo) return VALIDATION_ERROR — no invented bridge fee. |
{
"name": "score_opportunity",
"title": "Score opportunity",
"description": "Compute the full multi-factor risk-adjusted score for a single opportunity from list_yields.\n\nChain: pass list_yields opportunities[].id as poolId, opportunityId, or id (same DefiLlama pool UUID; id is the canonical list field).\n\nReturns APY breakdown (base/reward/total), factor scores with rationales, net yield after gas/bridge, exitRisk heuristic (TVL vs notional + liq conf only; medium ≠ small pool; not queues/caps/transfer whitelist/eligibility/on-chain withdraw; do not treat low as free exit when knownIssues mention transfer/eligibility), warnings, and sources. sourceChainKey is ethereum|base|arbitrum only — unknown keys (foo, solana) are VALIDATION_ERROR; no invented bridge fee.\n\nResearch estimates only — non-custodial.\n\nExample (any one id field):\n{ \"id\": \"43641cf5-a92e-416b-bce9-27113d3c0db6\", \"horizonDays\": 30, \"notionalUsd\": 10000 }\nAlso accepts poolId or opportunityId with the same value.",
"inputSchema": {
"type": "object",
"anyOf": [
{
"required": [
"id"
]
},
{
"required": [
"opportunityId"
]
},
{
"required": [
"poolId"
]
}
],
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"id": {
"type": "string",
"minLength": 1,
"description": "Same as list_yields opportunities[].id (canonical response field name)."
},
"poolId": {
"type": "string",
"minLength": 1,
"description": "Alias for list_yields opportunities[].id (historical tool field). Same DefiLlama pool UUID. Example: \"43641cf5-a92e-416b-bce9-27113d3c0db6\""
},
"horizonDays": {
"type": "number",
"maximum": 365,
"description": "Holding horizon in days for gas/bridge amortization (default 30). Example: 30",
"exclusiveMinimum": 0
},
"notionalUsd": {
"type": "number",
"description": "Notional USD size for net-yield cost amortization and exitRisk TVL multiples (default 10000). Example: 10000",
"exclusiveMinimum": 0
},
"opportunityId": {
"type": "string",
"minLength": 1,
"description": "Alias for list_yields opportunities[].id (same pool key as poolId / id)."
},
"sourceChainKey": {
"type": "string",
"description": "Agent's current chain for bridge cost estimate: ethereum | base | arbitrum (aliases: eth, ETH, Ethereum, arb, ARB, BASE). Blank/whitespace is VALIDATION_ERROR (omit the field to default). Unknown keys (solana, foo) return VALIDATION_ERROR — no invented bridge fee."
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": true,
"destructiveHint": false
}
}Side-by-side comparison of 2–5 opportunities by risk-adjusted score. Pass list_yields opportunities[].id values as poolIds or opportunityIds. Returns ranked list, compact comparison table fields (including protocolSlug for get_protocol_risk), winnerId, and rationale bullets (including when raw APY leader differs from risk-adjusted winner). sourceChainKey is ethereum|base|arbitrum only (unknown → VALIDATION_ERROR; no invented bridge fee). Research only — non-custodial. Example: { "poolIds": ["pool-id-a", "pool-id-b", "pool-id-c"], "horizonDays": 30 }
| Parameter | Type | Description |
|---|---|---|
| poolIds | array | 2–5 list_yields opportunities[].id values. Example: ["id-a","id-b"]. Alias: opportunityIds. |
| horizonDays | number | Holding horizon in days for gas/bridge amortization (default 30). Example: 30 |
| notionalUsd | number | Notional USD size for net-yield cost amortization and exitRisk TVL multiples (default 10000). Example: 10000 |
| opportunityIds | array | Alias for poolIds — same list_yields opportunities[].id values. |
| sourceChainKey | string | Agent's current chain for bridge cost estimate: ethereum | base | arbitrum (aliases: eth, ETH, Ethereum, arb, ARB, BASE). Blank/whitespace is VALIDATION_ERROR (omit the field to default). Unknown keys (solana, foo) return VALIDATION_ERROR — no invented bridge fee. |
{
"name": "compare_opportunities",
"title": "Compare opportunities",
"description": "Side-by-side comparison of 2–5 opportunities by risk-adjusted score.\n\nPass list_yields opportunities[].id values as poolIds or opportunityIds.\n\nReturns ranked list, compact comparison table fields (including protocolSlug for get_protocol_risk), winnerId, and rationale bullets (including when raw APY leader differs from risk-adjusted winner). sourceChainKey is ethereum|base|arbitrum only (unknown → VALIDATION_ERROR; no invented bridge fee).\n\nResearch only — non-custodial.\n\nExample:\n{\n \"poolIds\": [\"pool-id-a\", \"pool-id-b\", \"pool-id-c\"],\n \"horizonDays\": 30\n}",
"inputSchema": {
"type": "object",
"anyOf": [
{
"required": [
"poolIds"
]
},
{
"required": [
"opportunityIds"
]
}
],
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"poolIds": {
"type": "array",
"items": {
"type": "string",
"minLength": 1
},
"maxItems": 5,
"minItems": 2,
"description": "2–5 list_yields opportunities[].id values. Example: [\"id-a\",\"id-b\"]. Alias: opportunityIds."
},
"horizonDays": {
"type": "number",
"maximum": 365,
"description": "Holding horizon in days for gas/bridge amortization (default 30). Example: 30",
"exclusiveMinimum": 0
},
"notionalUsd": {
"type": "number",
"description": "Notional USD size for net-yield cost amortization and exitRisk TVL multiples (default 10000). Example: 10000",
"exclusiveMinimum": 0
},
"opportunityIds": {
"type": "array",
"items": {
"type": "string",
"minLength": 1
},
"maxItems": 5,
"minItems": 2,
"description": "Alias for poolIds — same list_yields opportunities[].id values."
},
"sourceChainKey": {
"type": "string",
"description": "Agent's current chain for bridge cost estimate: ethereum | base | arbitrum (aliases: eth, ETH, Ethereum, arb, ARB, BASE). Blank/whitespace is VALIDATION_ERROR (omit the field to default). Unknown keys (solana, foo) return VALIDATION_ERROR — no invented bridge fee."
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": true,
"destructiveHint": false
}
}Agent-readable explanation of why an opportunity received its risk-adjusted score. Chain: pass list_yields opportunities[].id as poolId, opportunityId, or id (aliases for the same key). Returns a summary paragraph, factor bullets with weighted contributions, net-yield notes, an exitRisk heuristic line (liquidity-only — not on-chain withdraw or transfer/eligibility; medium often confidence-driven, not pool size; extra bullet when knownIssues note transfer restrictions), plus id and protocolSlug (same as list_yields; pass protocolSlug to get_protocol_risk). sourceChainKey is ethereum|base|arbitrum only (unknown → VALIDATION_ERROR; no invented bridge fee). Prefer this when you need to justify a ranking to a human or another agent. Research only — non-custodial. Example: { "opportunityId": "43641cf5-a92e-416b-bce9-27113d3c0db6", "horizonDays": 30 } Also accepts poolId or id with the same value.
| Parameter | Type | Description |
|---|---|---|
| id | string | Same as list_yields opportunities[].id (canonical response field name). |
| poolId | string | Alias for list_yields opportunities[].id (historical tool field). Same DefiLlama pool UUID. Example: "43641cf5-a92e-416b-bce9-27113d3c0db6" |
| horizonDays | number | Holding horizon in days for gas/bridge amortization (default 30). Example: 30 |
| notionalUsd | number | Notional USD size for net-yield cost amortization and exitRisk TVL multiples (default 10000). Example: 10000 |
| opportunityId | string | Alias for list_yields opportunities[].id (same pool key as poolId / id). |
| sourceChainKey | string | Agent's current chain for bridge cost estimate: ethereum | base | arbitrum (aliases: eth, ETH, Ethereum, arb, ARB, BASE). Blank/whitespace is VALIDATION_ERROR (omit the field to default). Unknown keys (solana, foo) return VALIDATION_ERROR — no invented bridge fee. |
{
"name": "explain_score",
"title": "Explain score",
"description": "Agent-readable explanation of why an opportunity received its risk-adjusted score.\n\nChain: pass list_yields opportunities[].id as poolId, opportunityId, or id (aliases for the same key).\n\nReturns a summary paragraph, factor bullets with weighted contributions, net-yield notes, an exitRisk heuristic line (liquidity-only — not on-chain withdraw or transfer/eligibility; medium often confidence-driven, not pool size; extra bullet when knownIssues note transfer restrictions), plus id and protocolSlug (same as list_yields; pass protocolSlug to get_protocol_risk). sourceChainKey is ethereum|base|arbitrum only (unknown → VALIDATION_ERROR; no invented bridge fee). Prefer this when you need to justify a ranking to a human or another agent.\n\nResearch only — non-custodial.\n\nExample:\n{ \"opportunityId\": \"43641cf5-a92e-416b-bce9-27113d3c0db6\", \"horizonDays\": 30 }\nAlso accepts poolId or id with the same value.",
"inputSchema": {
"type": "object",
"anyOf": [
{
"required": [
"id"
]
},
{
"required": [
"opportunityId"
]
},
{
"required": [
"poolId"
]
}
],
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"id": {
"type": "string",
"minLength": 1,
"description": "Same as list_yields opportunities[].id (canonical response field name)."
},
"poolId": {
"type": "string",
"minLength": 1,
"description": "Alias for list_yields opportunities[].id (historical tool field). Same DefiLlama pool UUID. Example: \"43641cf5-a92e-416b-bce9-27113d3c0db6\""
},
"horizonDays": {
"type": "number",
"maximum": 365,
"description": "Holding horizon in days for gas/bridge amortization (default 30). Example: 30",
"exclusiveMinimum": 0
},
"notionalUsd": {
"type": "number",
"description": "Notional USD size for net-yield cost amortization and exitRisk TVL multiples (default 10000). Example: 10000",
"exclusiveMinimum": 0
},
"opportunityId": {
"type": "string",
"minLength": 1,
"description": "Alias for list_yields opportunities[].id (same pool key as poolId / id)."
},
"sourceChainKey": {
"type": "string",
"description": "Agent's current chain for bridge cost estimate: ethereum | base | arbitrum (aliases: eth, ETH, Ethereum, arb, ARB, BASE). Blank/whitespace is VALIDATION_ERROR (omit the field to default). Unknown keys (solana, foo) return VALIDATION_ERROR — no invented bridge fee."
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": true,
"destructiveHint": false
}
}Protocol-level risk card (age, audit signals, curated known issues, category, score 0–100). Chain: pass list_yields opportunities[].protocolSlug as protocol or protocolSlug. Display names also resolve case- and space-insensitively via DefiLlama protocol metadata (e.g. "Compound V3" → compound-v3, "Curve" → curve-dex, "Euler V2" → euler-v2). Unknown names return NOT_FOUND naming the field, with example {"protocolSlug":"aave-v3"} and up to 3 closest slugs. Higher score = lower protocol risk. Uses curated priors plus DefiLlama metadata when available. Research only — non-custodial. Example: { "protocol": "aave-v3" } Also accepts protocolSlug or a display name such as "Compound V3".
| Parameter | Type | Description |
|---|---|---|
| protocol | string | Protocol slug (DefiLlama project id) or display name, e.g. "aave-v3" or "Compound V3". Prefer list_yields opportunities[].protocolSlug. |
| protocolSlug | string | Alias for protocol — list_yields opportunities[].protocolSlug (display names also resolve). |
{
"name": "get_protocol_risk",
"title": "Get protocol risk",
"description": "Protocol-level risk card (age, audit signals, curated known issues, category, score 0–100).\n\nChain: pass list_yields opportunities[].protocolSlug as protocol or protocolSlug. Display names also resolve case- and space-insensitively via DefiLlama protocol metadata (e.g. \"Compound V3\" → compound-v3, \"Curve\" → curve-dex, \"Euler V2\" → euler-v2).\n\nUnknown names return NOT_FOUND naming the field, with example {\"protocolSlug\":\"aave-v3\"} and up to 3 closest slugs.\n\nHigher score = lower protocol risk. Uses curated priors plus DefiLlama metadata when available.\n\nResearch only — non-custodial.\n\nExample:\n{\n \"protocol\": \"aave-v3\"\n}\nAlso accepts protocolSlug or a display name such as \"Compound V3\".",
"inputSchema": {
"type": "object",
"anyOf": [
{
"required": [
"protocol"
]
},
{
"required": [
"protocolSlug"
]
}
],
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"protocol": {
"type": "string",
"minLength": 1,
"description": "Protocol slug (DefiLlama project id) or display name, e.g. \"aave-v3\" or \"Compound V3\". Prefer list_yields opportunities[].protocolSlug."
},
"protocolSlug": {
"type": "string",
"minLength": 1,
"description": "Alias for protocol — list_yields opportunities[].protocolSlug (display names also resolve)."
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": true,
"destructiveHint": false
}
}yieldhunter.eth — non-custodial risk-adjusted stablecoin yield research for AI agents. Rank by compositeRiskAdjusted, not raw APY. Copy-paste path: (1) health {} (2) list_yields {"assets":["USDC"],"sortBy":"risk_adjusted"}. After the list, contrast row #1 (risk-adjusted winner) with row #2 (often higher rate, thinner liquidity, or other chain) — not the max-APY row in the ten. Live names move; any named pair is a snapshot. Tool data stays precise for agents. When the end user is human or asks for an explanation: summarize ranks in plain language (risk vs yield; organic vs temporary rewards); avoid unnecessary jargon; at most one clear risk note per line. After list_yields, prefer explain_score / compare_opportunities / get_protocol_risk using meta.suggestedNextSteps and returned ids when the user may want depth. Research only — no execution, no “put money here”, no guarantees. Never executes transactions.
Names, descriptions and schemas were written by the server and are shown as data.
| Include only these categories: "lending" | "rwa" | "other" |
| horizonDays | number | Holding horizon in days for gas/bridge amortization (default 30). Example: 30 |
| notionalUsd | number | Notional USD size for net-yield cost amortization and exitRisk TVL multiples (default 10000). Example: 10000 |
| riskAppetite | string | Scoring weight profile: "balanced" (default/v1.1) | "conservative" | "aggressive" |
| includeFactors | boolean | If true, each opportunity includes scores.factors compact map (protocolRisk, depegCounterparty, liquidity, yieldQuality, costAdjusted). Default false — omits heavy factors[] rationales. |
| maxRewardShare | any | Incentive-share gate only: max reward/total of gross APY, 0–1 (e.g. 0.3 treasury, 0.25 stricter). Does not remove high base-only APY farms. Capital preservation still needs minScore/riskAppetite/excludeCategories. Omitted = no filter. Unknown share excluded when set. |
| sourceChainKey | string | Agent's current chain for bridge cost estimate: ethereum | base | arbitrum (aliases: eth, ETH, Ethereum, arb, ARB, BASE). Blank/whitespace is VALIDATION_ERROR (omit the field to default). Unknown keys (solana, foo) return VALIDATION_ERROR — no invented bridge fee. |
| excludeCategories | array | Exclude these categories, e.g. ["rwa"] |