@atlasyield/mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| ATLAS_API_BASE | No | Override the API base | https://api.atlasyield.club/v1 |
| ATLAS_SNAPSHOT_BASE | No | Override the score-history raw base |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| find_vaultsA | 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, whether a deposit can reach it (routable), and a citable page URL. Vaults with no deposit route and rows scored on fallback data are excluded. Ranked by Atlas composite, a ranking and not a recommendation. Take a chosen vaultId/address to check_route_survival before any deposit. Read-only. |
| get_vault_scoreA | 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. Returns found:false when the vault is not in the scored universe. Read-only. |
| get_coverageA | 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. |
| check_route_survivalA | 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. A vault that was never screened returns screened:false with no verdict — never a fabricated one. Call this BEFORE moving money. Read-only. |
| list_open_alertsA | 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. |
| explain_vault_scoreA | 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. |
| compare_vaultsA | 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. Unscored vaults come back found:false rather than silently dropped. Read-only. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 7 tools
Each tool has a distinct entry point (coverage, discovery, route check, comparison, factor explanation, single score, alerts), and the descriptions explicitly say when to use each. However, get_vault_score and explain_vault_score both target a single vault's score and could be confused, with only the '16 factors' vs 'composite + pillars' distinction separating them.
All names are snake_case verb-noun pairs (get_coverage, find_vaults, check_route_survival, compare_vaults, explain_vault_score, get_vault_score, list_open_alerts). The verbs are consistent and predictable, and find_vaults is read as a deliberate search verb rather than an inconsistency.
Seven tools is well-scoped for a vault-scoring index: one per major workflow (discovery, scoring, explanation, comparison, exit safety, alerts, coverage). No tool feels redundant or filler.
The read-only surface covers the full analytic lifecycle: what's covered, discovery, per-vault score, factor breakdown, cross-vault comparison, exit-route safety, and change alerts. Minor gaps exist (no historical score trend or watchlist/notification subscription), but agents can work around them via alerts and timestamps.