@atlasyield/mcp
This is a read-only AtlasYield MCP server for vault judgment and safety checks, with no key, custody, or execution.
Find ranked vaults for an asset or list of assets on a chain, filtered by APY/score/TVL, including what filters removed.
Get one vault’s latest 16-factor Atlas Score, label, pillars, APY/TVL, and data quality.
View coverage: scored vault count, TVL, score spread, and breakdowns by protocol/chain.
Check whether a deposit can be exited at size today via same-chain route survival;
blocking:truemeans refuse.List open blowup-monitor alerts from the daily snapshot.
Explain why a vault has its score: all 16 factors, weights, raw inputs, and weakest factors.
Compare 2–8 vaults side by side, keeping unscored vaults visible as
found:false.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@@atlasyield/mcp Is Morpho WETH on Base safe to enter at $10k?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
@atlasyield/mcp
Read-only MCP server for the AtlasYield judgment layer. Seven tools, no key, no custody, no execution: an agent asks for judgment and is told when a route is unsafe.
Tool | Answers |
| No vault address yet? A short ranked list for an asset (or a list of assets) and chain ( |
| Latest 16-factor Atlas Score for one vault (composite, label, 4 pillars, live APY/TVL). |
| What is scored right now: vault count, TVL, score spread, by protocol and chain. |
| Can a deposit be exited at size, measured today? |
| Open blowup-monitor alerts from the published daily snapshot. |
| Why: all 16 factors by pillar (sub-score, weight, raw input, label) and the three weakest. |
| 2-8 vaults side by side, ranked by composite; unscored ones stay visible as |
Data comes from the public API https://api.atlasyield.club/v1 and the published score
history https://github.com/gveshk/atlasyield-score-history. Scored every 4 hours, snapshot
published daily. Research and information, not investment advice.
Hosted: nothing to install
https://atlasyield.club/mcpStreamable HTTP, read-only, no key and no sign-in. Claude Code:
claude mcp add --transport http atlasyield https://atlasyield.club/mcp. For Claude on the web and
desktop, ChatGPT, Gemini CLI, Cursor and VS Code, see
https://docs.atlasyield.club/api-reference/mcp.
Related MCP server: agentcrush
Install (local, over stdio)
Claude Code:
claude mcp add atlasyield -- npx -y @atlasyield/mcpClaude Desktop / Cursor / any stdio client (mcp.json or claude_desktop_config.json):
{
"mcpServers": {
"atlasyield": { "command": "npx", "args": ["-y", "@atlasyield/mcp"] }
}
}From a checkout: npm install && npm run build then use "command": "node", "args": ["<checkout>/dist/index.js"].
Docker: docker build -t atlasyield-mcp . then "command": "docker", "args": ["run", "-i", "--rm", "atlasyield-mcp"].
Try it
Is Morpho WETH on Base (0x09832347586e238841f49149c84d121bc2191c53) safe to enter at $10k?
The agent calls get_vault_score, then check_route_survival. A NO_ROUTE verdict comes
back as blocking: true and a plain-English refusal.
Without an MCP client: npm run build && node scripts/smoke.mjs check_route_survival '{"chainId":8453,"address":"0x..."}'
speaks raw JSON-RPC to the binary over stdio.
Environment
ATLAS_API_BASE— override the API base (defaulthttps://api.atlasyield.club/v1)ATLAS_SNAPSHOT_BASE— override the score-history raw base
What this is not
No deposit, sign, or send tool exists here and none will be added. Execution, if offered, is a
separate API with its own guards (recipient-safety, assertRouteValue) — never an MCP tool.
Docs: https://docs.atlasyield.club/api-reference/mcp · Licence: MIT · Data licence: https://atlasyield.club/data-license
Available Tools
7 toolscheck_route_survivalCheck route survivalARead-onlyIdempotentInspect
Can a deposit into this vault be exited at size, measured today? Returns the daily round-trip route screen (USDC -> position -> USDC): verdict, USD in/out, fraction retained, the path probed, and when. blocking:true means refuse the deposit (NO_ROUTE, DANGEROUS, UNPRICEABLE). reasonClass says why: protocol_refused (the protocol's own router refuses, the vault is dead) vs no_aggregator_quote (no same-chain swap into the underlying, common for LP vaults; redeeming by hand may still work). The probe is SAME-CHAIN only: USDC on the vault's own chain. It says nothing about bridging in from elsewhere. Route tracking covers EVM chains only: a Solana vault returns tracked:false (not tracked, neither a pass nor a failure). A vault that was never screened returns screened:false with no verdict — never a fabricated one. Call this BEFORE moving money. Read-only.
Inputs: address (required), chainId (required).
compare_vaultsCompare vaultsARead-onlyIdempotentInspect
Side-by-side Atlas Scores for 2-8 vaults: composite, label, four pillars, live APY/TVL, data quality, yieldQuality and exitSafety, with a ranking by composite, vaults flagged notYieldProduct ranked after the others (each entry also has notYieldProduct: true when the vault earns about nothing; null when the API does not report it). Unscored vaults come back found:false rather than silently dropped. Read-only.
Inputs: vaults (required).
explain_vault_scoreExplain vault scoreARead-onlyIdempotentInspect
Why a vault has its Atlas Score: all 16 factors (15 additive across four pillars + the multiplicative exploit-history modifier), each with sub-score (0-100), weight, raw input and a plain-English label, grouped by pillar, plus the three weakest factors. Exactly what the engine computed at scoredAt, not a recomputation. Returns found:false when unscored. Read-only.
Inputs: address (required), chainId (required).
find_vaultsFind vaultsARead-onlyIdempotentInspect
Start here when you do not already have a vault address. Answers "which vaults for this asset on this chain?": returns a short ranked list (default 5, max 10) of scored vaults with composite, label, live APY/TVL, risk flags (thin_tvl, apy_outlier, no_yield, ...), whether a deposit can reach it (routable), and a citable page URL. It also returns what the filters REMOVED: counts per filter, the best-ranked dropped vaults with reasons, near-miss asset symbols, and whether more matched than were returned. Vaults with no deposit route and rows scored on fallback data are excluded. Ranked by the chosen metric, a ranking and not a recommendation. A flag is a caution, not a verdict, and no flag does not mean safe. Take a chosen vaultId/address to check_route_survival before any deposit. Read-only.
Inputs: asset, chain, limit, minApy, +4 more.
get_coverageGet coverageARead-onlyIdempotentInspect
What the Atlas Score Index covers right now: number of scored vaults, total TVL, composite score spread, and counts by protocol and chain. Use it before asking about a vault to learn whether a protocol or chain is in the scored universe at all. Read-only.
Inputs: chainId, protocolId.
get_vault_scoreGet vault scoreARead-onlyIdempotentInspect
Latest Atlas Score for one vault: composite (0-100), label, the four pillar scores (yield, safety, liquidity, sustainability), live APY/TVL, data quality and the scoring timestamp. Each vault also carries holdingsScore: the score from what it holds, with its cap; published:false means it is not yet the headline composite. notYieldProduct: true means it earns essentially nothing; do not present the score as a reason to deposit for yield. Returns found:false when the vault is not in the scored universe. Read-only.
Inputs: address (required), chainId (required).
list_open_alertsList open alertsARead-onlyIdempotentInspect
Open blowup-monitor alerts from the published daily snapshot: score-band exits, fast composite breaks, yield collapse, TVL flight, exploit flags, delistings. Each event carries score before/after and pillar deltas. Published once a day; the date field says when. Read-only.
Inputs: chainId, minSeverity.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 7 tools
Each tool maps to a distinct step in the vault workflow: universe coverage, discovery, single-vault score, factor explanation, multi-vault comparison, route screening, and alerts. The only mild overlap is among get_vault_score, explain_vault_score, and compare_vaults, which all surface the composite and pillars at different granularities, but the descriptions spell out the differences (headline score vs. 16-factor breakdown vs. 2-8 vault ranking) well enough to guide selection.
All seven names use snake_case with a clear verb_noun structure (get_coverage, find_vaults, get_vault_score, check_route_survival, list_open_alerts, explain_vault_score, compare_vaults). Verbs are used accurately and consistently, with no style mixing or ambiguous bare nouns.
Seven tools is well-scoped for a read-only vault analytics surface, with each tool earning its place as a distinct query type. Nothing feels redundant or padded, and no obvious capability is crammed into a catch-all tool.
The surface covers the full read-only lifecycle: discover the universe, find candidate vaults, score a vault, explain the score, compare vaults, screen exit routes, and check alerts. Gaps are minor — there is no historical score/trend tool beyond the before/after deltas in alerts, and no direct lookup of a vault you already know the address of without going through find_vaults or get_vault_score.
Maintenance
Related MCP Connectors
Read-only Hyperliquid vault search, risk, drawdown, rankings, TVL, alerts, and comparisons.
Read-only smart-contract security intelligence for autonomous agents.
Pay-per-call x402 services for agents: risk scoring, DeFi, wallet and market data.
Search 700+ DeFi vaults, compare risk scores, analyze protocols. No API key needed.
Related MCP Servers
- FlicenseNot gradedqualityCmaintenanceEnables read-only research on live Hyperliquid vaults through search, ranking, comparison, risk explanation, HLP metrics, and alert tools with timestamped evidence and caveats.-
- FlicenseNot gradedqualityBmaintenanceProvides protocol-neutral market intelligence for the AI agent economy, with read-only tools to search agents, retrieve details and histories, compare agents, list categories, view category rankings, and access methodology.-
- AlicenseAqualityBmaintenanceEnables AI assistants and agents to perform read-only lookups of dated on-record facts about agents, wallets, and endpoints, including evidence levels and history, so they can assess what is known before paying or relying on them.4121 npmMIT

ASPERNofficial
FlicenseNot gradedqualityCmaintenanceEnables agents and capital allocators to query read-only on-chain and venue evidence about a counterparty before paying or hiring it, and about a vault before depositing, with each figure timestamped and sourced.-