keel-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| KEEL_API_URL | No | Point at another deployment, or at the contract mock (http://localhost:4010) | https://api.keels.app/v1 |
| KEEL_TIMEOUT_MS | No | Per request timeout | 15000 |
| KEEL_CACHE_TTL_MS | No | Cache for the asset list and methodology. Scans run every 15 minutes | 60000 |
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
} |
| prompts | {
"listChanged": true
} |
| resources | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| keel_statusA | Whether the Keel engine is healthy, the ledger of its latest scan, how many Stellar assets it monitors, and the methodology version its numbers follow. Call this first when freshness matters. |
| list_assetsA | Lists the Stellar assets Keel monitors with their risk band, band confidence, recommended maximum safe collateral size (USDC) and fired flags. Filter by band (e.g. CRITICAL) or by a single flag (e.g. MANIPULATION_CHEAP) to find risky collateral. |
| find_assetA | Resolves an asset code such as USDY or AQUA to the full CODE:ISSUER ids Keel monitors. When one code has several issuers, ALL of them are returned and none is chosen: ask the user which issuer they mean rather than picking one, because the same ticker from a different issuer is a different asset. |
| get_asset_riskA | The full Keel risk reading for one asset: risk band and its confidence, fired and unevaluated flags, executable depth at +/-2%, 5% and 10% (SDEX order book plus AMM pools), recommended maximum safe collateral size with its liquidation and manipulation terms, holder concentration, volume to supply, and the last genuine trade. Pass ledger to read a historical reconstruction instead of the latest scan. Always quote the provenance line with the numbers. |
| check_collateral_sizeA | Compares a proposed collateral amount with Keel's recommended maximum safe collateral size for the asset, and says which limit binds: liquidation (the book cannot absorb a forced sale) or manipulation (pushing the price up is cheaper than the loan it would unlock). Answers within, exceeds, or unknown. Unknown is not safe and not unsafe. This is a comparison with published figures, not a credit decision. |
| estimate_trade_depthA | For traders and market makers: places a buy or sell size (in the quote asset, USDC) between the measured rungs of Keel's depth ladder, answering 'this moves the price by at most 2% / 5% / 10%' or 'this exceeds the measured depth'. It is a bracket, never a point estimate, because the methodology defines no interpolation between rungs. Depth combines the SDEX order book and AMM pools. |
| get_risk_historyA | A time series of band, flags, depth and max safe collateral for one asset, from ONE data source. Give from and to (ledger sequences, at most 90 days apart) for a window, or omit both to list every stored reading of that source. Reconstructions such as the February 2026 USTRY series live under source offers-implied and are reachable only with both bounds omitted. Band changes are summarised. |
| compare_assetsA | Side-by-side comparison of 2 to 10 assets: band and confidence, max safe collateral, depth at 5% on both sides, and fired flags, each with its own ledger. Useful for choosing between collateral candidates. Figures are all in USDC. |
| get_methodologyA | The methodology version and every threshold Keel uses to fire flags and size collateral, with the link to the full documentation. The thresholds are chosen, not calibrated against a set of incidents; mention that when explaining why an asset got its band. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| assess_collateral | A guided assessment of whether an asset can back a loan of a given size, using Keel figures only. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| methodology | The active methodology version, its thresholds, and the calibration note, as JSON. |
| blend-backtest-report | The open, reproducible report asking whether Keel could have warned about the USTRY oracle manipulation that drained a Blend pool on 22 February 2026. Markdown, fetched from the public repository. |
TDQS
Scored across 9 tools
Each tool targets a distinct query: engine status, asset inventory, code resolution, per-asset risk, collateral comparison, trade depth, history, comparison, and methodology. The only mild overlap is between get_asset_risk (full reading including depth rungs) and estimate_trade_depth (bracket for a given size), but their stated purposes differ enough to guide selection.
Nearly all names follow a verb_noun pattern (list_assets, find_asset, get_asset_risk, check_collateral_size, estimate_trade_depth, get_risk_history, compare_assets, get_methodology). The lone exception is keel_status, which uses a server-name prefix instead of a verb, a minor deviation.
Nine tools is well-scoped for a read-only risk analytics server, with each tool covering a distinct query type (inventory, detail, history, comparison, methodology). No redundant or filler tools.
The surface covers the full read lifecycle for the domain: health, asset discovery, resolution, risk readings, historical reconstruction, comparison, collateral sizing, depth estimation, and methodology. There is no alert/watchlist or portfolio-level monitoring capability, but for a query-oriented analytics server the coverage is strong.