EdgeDepth Research
Server Details
Test crypto and TradFi-perpetual claims using recorded counts, baselines, and replay.
Glama couldn't complete the latest health check. If this server requires authentication, missing or expired test credentials may be the cause. A test profile lets Glama authenticate for health checks and discover tools; it is separate from your personal connections.
If you are the author, claim ownership, then add or update a test profile under Admin → Test Profile.
- Status
- Unhealthy
- Uptime
- 0.0% over 46 days
- OAuth
- Works in Glama
- Last Tested
- Transport
- Streamable HTTP
- URL
- Repository
- edgedepthhq/edgedepth-research-mcp
- GitHub Stars
- 3
- Server Listing
- EdgeDepth Research MCP Server
TDQS
Scored across 9 tools
Each tool has a clearly distinct purpose: base_rate measures condition frequency, commonality analyzes feature agreement across moments, run_scan and run_cohort perform queries and comparisons, while interpret_prose, list_features, get_report, next_page, and snapshot_at handle interpretation, registry, reports, pagination, and state reading. No two tools overlap in function.
Tool names mostly follow a verb_noun or descriptive noun pattern (run_scan, get_report, list_features, interpret_prose), with minor deviations like base_rate and commonality (nouns) and snapshot_at (verb_preposition). Overall consistent and readable.
The 9 tools are well-scoped for a research platform: covering query execution (run_scan, run_cohort, base_rate, commonality), data discovery (list_features, snapshot_at), interpretation (interpret_prose), result retrieval (get_report), and pagination (next_page). Not bloated nor sparse.
Essential operations are covered: scanning, comparison, frequency analysis, feature listing, state inspection, report fetching, and prose interpretation. Minor gaps such as explicit report publishing or feature creation are absent, but these align with the platform's deterministic and registry-based design.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
1 tool update
- Added
run_cohort
8 tool updates
- First observed
base_rate - First observed
commonality - First observed
get_report - First observed
interpret_prose - First observed
list_features - First observed
next_page - First observed
run_scan - First observed
snapshot_at
Related MCP Connectors
Checks crypto trading claims on real data: leverage, drawdown, stop-loss, seasonality, luck.
Crypto backtest statistics: the server owns the trial count, so it cannot be understated.
Check claims against a fact-store: consistent, contradicts, or unverifiable — with a receipt.
Crypto backtesting & Bitcoin cycle analytics. Point-in-time, DSR-corrected, look-ahead-aware.
Related MCP Servers
- AlicenseAqualityAmaintenanceEnables submitting claims and receiving Ed25519-signed, hash-chained verdicts resolved against real external ground truth, supporting resolvers like GitHub PRs, on-chain transactions, URL JSON, HTTP status, and Kalshi markets.5314 npm1MIT
- AlicenseBqualityAmaintenanceVerify a number before an agent asserts it — a Deflated Sharpe Ratio for backtest, plus eval-gap, subset-win, and judge-bias checks, with signed receipts anyone can verify offline.34MIT
- AlicenseNot gradedqualityBmaintenanceRead-only crypto perps microstructure for AI agents: normalized cross-exchange market state (funding + multi-year percentile, OI, volume, CVD, order-book imbalance, liquidations, basis), OHLCV, 15-min state history, and measured conditional outcomes (historical base rates, not predictions) — 6 assets across Binance, Bybit, OKX and Hyperliquid, every metric with self-declared coverage and freshnessMIT
- AlicenseBqualityCmaintenanceEnables auditing and verification of algorithmic trading backtests from coding agents like Claude Code, Cursor, and Windsurf, including look-ahead bias detection, overfitting checks, and sealed audit proof verification.3MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.