yieldsentinel is an MCP server published by io.github.agentsherpa, hosted at yieldsentinel-agent-production.up.railway.app. When last checked on 2026-11-21 it was working: it answers and lists its tools. It declares 2 tools, including health, check_position.
Policy check on a described yield position. Complement to yieldhunter. Research only.
12 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 yieldsentinel (yieldsentinel.eth). Returns service status, package version, health schemaVersion (separate from the tool-envelope schemaVersion), policyVersion, feature flags, and the list of available tools. toolStats counts all origins. toolStatsExternal is the external bucket. toolStatsInternal is the internal-test bucket. Send header X-YHYS-Test: 1 on every request (initialize, notifications, and each tools/call). On this stateless server that header is the only working internal-test marker. clientInfo.name prefixes yhys-qa / yhys-feel count only for the same request they appear in. May refresh research vintage via a yieldhunter health ping; a verdict still requires check_position. YH healthy ≠ YS ok. Use this first to verify connectivity, then call check_position with policyPreset treasury-conservative | balanced-research | rwa-selective (or explicit thresholds). Research estimates only — non-custodial; never holds keys or executes transactions. Example input: {}
No parameters.
{
"name": "health",
"title": "Health",
"description": "Liveness and capability check for yieldsentinel (yieldsentinel.eth).\n\nReturns service status, package version, health schemaVersion (separate from the tool-envelope schemaVersion), policyVersion, feature flags, and the list of available tools.\n\ntoolStats counts all origins. toolStatsExternal is the external bucket. toolStatsInternal is the internal-test bucket. Send header X-YHYS-Test: 1 on every request (initialize, notifications, and each tools/call). On this stateless server that header is the only working internal-test marker. clientInfo.name prefixes yhys-qa / yhys-feel count only for the same request they appear in.\n\nMay refresh research vintage via a yieldhunter health ping; a verdict still requires check_position. YH healthy ≠ YS ok.\n\nUse this first to verify connectivity, then call check_position with policyPreset treasury-conservative | balanced-research | rwa-selective (or explicit thresholds). Research estimates only — non-custodial; never holds keys or executes transactions.\n\nExample input: {}",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {},
"additionalProperties": true
},
"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.
Evaluate a described stablecoin yield position against a research policy (pull). Always pass your policy rules (or a preset). Without a policy, no meaningful check is possible — the verdict will be review/unknown, never ok. Pass poolId from yieldhunter list_yields opportunities[].id (also accepted as opportunityId or id). That id is one market. Required for a real check: policyPreset (treasury-conservative | balanced-research | rwa-selective) and/or minScore / maxRewardShare / excludeCategories / maxExitRisk / requireCurated. Presets: treasury-conservative | balanced-research | rwa-selective. rwa-selective does not exclude RWA but is not a free pass (YS policy allowlist + higher bar). requireCurated uses the Yieldsentinel policy allowlist (curated.json), not yieldhunter scoring priors. Scoring ≠ policy approval. Fetches live yieldhunter research (score, APY, TVL, category, rewardShare, exitRisk) and curated flags, then returns a PolicyVerdict plus A2H (summary, suggestedNextSteps, legend). Incomplete or missing data is review/unknown — never a silent ok. A verdict is not an exit signal or execution order. Research only — never holds keys. Example: { "poolId": "43641cf5-a92e-416b-bce9-27113d3c0db6", "policyPreset": "treasury-conservative", "notionalUsd": 10000 }
| Parameter | Type | Description |
|---|---|---|
| id | any | Same as yieldhunter list_yields opportunities[].id. |
| asset | any | Stablecoin symbol, e.g. "USDC". |
| chain | string | ethereum | base | arbitrum. Case-insensitive. Also accepts eth, mainnet, arb, arbitrum-one. |
| poolId | any | yieldhunter list_yields opportunities[].id (DefiLlama pool UUID). Example: "43641cf5-a92e-416b-bce9-27113d3c0db6" |
| minScore | any | Minimum compositeRiskAdjusted (0–100). |
| minNetApy | any | Minimum net APY estimate. |
| minTvlUsd | any | Minimum pool TVL in USD. |
| horizonDays | any | Holding horizon in days for net-yield context (default 30). |
| maxExitRisk | string | Cap on yieldhunter exitRisk heuristic: low | medium | high. Unknown or above the cap → review. |
| notionalUsd | any | Research notional in USD (size hint only). Example: 10000 |
| policyPreset | string | Policy preset: "treasury-conservative" | "balanced-research" | "rwa-selective". treasury-conservative excludes RWA; rwa-selective allows RWA but is not a free pass (YS policy allowlist + higher bar). |
| protocolSlug | any | Yieldhunter protocol slug. Prefer poolId from list_yields opportunities[].id when the protocol has more than one market. |
| riskAppetite | string | conservative | balanced | aggressive (research posture only). |
| opportunityId | any | Alias for poolId / id. |
| maxRewardShare | any | Maximum incentive share of gross APY (0–1). |
| requireCurated | any | If true, the protocol/pool must be on the Yieldsentinel policy allowlist (curated.json), not yieldhunter scoring priors. Missing allowlist entry → review. Scoring ≠ policy approval. |
| minProtocolScore | any | Minimum yieldhunter protocol risk score (0–100, higher = safer). |
| excludeCategories | any | Exclude categories, e.g. ["rwa"]. |
{
"name": "check_position",
"title": "Check position (research policy)",
"description": "Evaluate a described stablecoin yield position against a research policy (pull).\n\nAlways pass your policy rules (or a preset). Without a policy, no meaningful check is possible — the verdict will be review/unknown, never ok.\n\nPass poolId from yieldhunter list_yields opportunities[].id (also accepted as opportunityId or id). That id is one market. Required for a real check: policyPreset (treasury-conservative | balanced-research | rwa-selective) and/or minScore / maxRewardShare / excludeCategories / maxExitRisk / requireCurated. Presets: treasury-conservative | balanced-research | rwa-selective. rwa-selective does not exclude RWA but is not a free pass (YS policy allowlist + higher bar). requireCurated uses the Yieldsentinel policy allowlist (curated.json), not yieldhunter scoring priors. Scoring ≠ policy approval.\n\nFetches live yieldhunter research (score, APY, TVL, category, rewardShare, exitRisk) and curated flags, then returns a PolicyVerdict plus A2H (summary, suggestedNextSteps, legend).\n\nIncomplete or missing data is review/unknown — never a silent ok. A verdict is not an exit signal or execution order. Research only — never holds keys.\n\nExample:\n{ \"poolId\": \"43641cf5-a92e-416b-bce9-27113d3c0db6\", \"policyPreset\": \"treasury-conservative\", \"notionalUsd\": 10000 }",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"id": {
"description": "Same as yieldhunter list_yields opportunities[].id."
},
"asset": {
"description": "Stablecoin symbol, e.g. \"USDC\"."
},
"chain": {
"enum": [
"ethereum",
"base",
"arbitrum"
],
"type": "string",
"description": "ethereum | base | arbitrum. Case-insensitive. Also accepts eth, mainnet, arb, arbitrum-one."
},
"poolId": {
"description": "yieldhunter list_yields opportunities[].id (DefiLlama pool UUID). Example: \"43641cf5-a92e-416b-bce9-27113d3c0db6\""
},
"minScore": {
"description": "Minimum compositeRiskAdjusted (0–100)."
},
"minNetApy": {
"description": "Minimum net APY estimate."
},
"minTvlUsd": {
"description": "Minimum pool TVL in USD."
},
"horizonDays": {
"description": "Holding horizon in days for net-yield context (default 30)."
},
"maxExitRisk": {
"enum": [
"low",
"medium",
"high"
],
"type": "string",
"description": "Cap on yieldhunter exitRisk heuristic: low | medium | high. Unknown or above the cap → review."
},
"notionalUsd": {
"description": "Research notional in USD (size hint only). Example: 10000"
},
"policyPreset": {
"enum": [
"treasury-conservative",
"balanced-research",
"rwa-selective"
],
"type": "string",
"description": "Policy preset: \"treasury-conservative\" | \"balanced-research\" | \"rwa-selective\". treasury-conservative excludes RWA; rwa-selective allows RWA but is not a free pass (YS policy allowlist + higher bar)."
},
"protocolSlug": {
"description": "Yieldhunter protocol slug. Prefer poolId from list_yields opportunities[].id when the protocol has more than one market."
},
"riskAppetite": {
"enum": [
"conservative",
"balanced",
"aggressive"
],
"type": "string",
"description": "conservative | balanced | aggressive (research posture only)."
},
"opportunityId": {
"description": "Alias for poolId / id."
},
"maxRewardShare": {
"description": "Maximum incentive share of gross APY (0–1)."
},
"requireCurated": {
"description": "If true, the protocol/pool must be on the Yieldsentinel policy allowlist (curated.json), not yieldhunter scoring priors. Missing allowlist entry → review. Scoring ≠ policy approval."
},
"minProtocolScore": {
"description": "Minimum yieldhunter protocol risk score (0–100, higher = safer)."
},
"excludeCategories": {
"description": "Exclude categories, e.g. [\"rwa\"]."
}
},
"additionalProperties": true
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": true,
"destructiveHint": false
}
}yieldsentinel.eth — non-custodial position-policy research for AI agents. Pull check_position against a research policy. Same verdict contract is intended for a later watch mode. Research only — no execution, no custody, no “exit now”. Never executes transactions.
Names, descriptions and schemas were written by the server and are shown as data.
Shared addresses on big platforms (Cloudflare, Vercel and the like) put unrelated servers together; those are marked shared_infrastructure. A match is a pivot, not a link between operators.