crypto-quant-signal-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| TRANSPORT | No | Transport mode for the MCP server, e.g., 'stdio' for local use or 'http' for remote. | stdio |
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
} |
| resources | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_trade_callA | Returns a composite verdict — BUY SELL HOLD trade call with confidence and market regime — for one crypto or tokenized-stock perpetual futures. One asset only; whole-market scan: scan_trade_calls. Read-only: live exchange APIs, no orders. Verified track record: get_track_record or performance://signal-performance; on-chain verified merkle anchor. |
| get_trade_signalA | Returns a composite verdict — BUY SELL HOLD trade call with confidence and market regime — for one crypto or tokenized-stock perpetual futures. One asset only; whole-market scan: scan_trade_calls. Read-only: live exchange APIs, no orders. Verified track record: get_track_record or performance://signal-performance; on-chain verified merkle anchor. [ALIAS] This tool is an alias of get_trade_call — same behavior, kept for backward compatibility. Prefer get_trade_call for new integrations. |
| get_market_regimeA | Returns the market regime — TRENDING_UP TRENDING_DOWN RANGING VOLATILE — with confidence and a strategy hint, for one crypto perpetual futures. Composite verdict: trend ranging + cross-venue funding rate. Read-only, live exchange APIs. Verified track record: get_track_record or performance://signal-performance; on-chain verified merkle anchor. |
| scan_funding_arbA | Ranked cross-venue funding arbitrage across major crypto perpetual futures venues — funding rate spreads, long one venue short another, as a BUY SELL HOLD composite verdict per pair. AI trading signal for crypto quant and Claude trading agents. Trade call via get_trade_call, market regime via get_market_regime. On-chain verified merkle anchor. |
| scan_trade_callsA | Returns ranked BUY SELL HOLD trade calls across the top crypto perpetual futures by open interest — one scan for whole-market coverage, each with confidence and market regime. Use this for breadth; use get_trade_call for per-coin depth and reasoning. Read-only: reads live exchange APIs, places no orders. |
| scan_market_regimesA | Screens a whole crypto perpetual futures venue by market regime — TRENDING_UP TRENDING_DOWN RANGING VOLATILE — and returns each matching coin with confidence, trend strength, ADX, volatility ratio and how long the regime has held. Rows are the market regime classifier output for the last closed bar, sampled on Binance, Bybit, OKX and Bitget; another venue, or a timeframe a venue cannot serve, is refused with the alternatives. Billing: one call per returned row; non-matching coins are free. For a live single-coin read with cross-venue funding, call get_market_regime. Read-only. |
| pre_trade_checkA | Returns a pre-trade check of a crypto perpetual futures order against your own rules: each passes or fails with its numbers, then GO, CAUTION or WAIT. Adds isolated liquidation distance, whether it hits before your stop, fees, accuracy needed to break even over your hold, funding by venue (cross-venue) and the regime. Read-only: places no orders. |
| chat_knowledgeA | Returns a synthesized natural-language answer with citations, grounded in the AlgoVault knowledge bundle (every MCP tool description, response shape, integration tutorial, and code example). Use when you need an explanation, code pattern, or how-to; for raw ranked snippets without LLM synthesis use search_knowledge (faster, no quota cost). Read-only: calls an LLM, no other side effects. Quota: Free 10/month, Starter 50, Pro 200, Enterprise 2000. |
| search_knowledgeA | Returns ranked snippets from the AlgoVault knowledge bundle answering a question about its MCP tools, response shapes, integration patterns (LangChain, LlamaIndex, MAF, CrewAI), or code examples. Call this BEFORE other tool calls to confirm parameter usage and avoid hallucinating tool shapes. Fast: BM25 lexical search, no LLM call, no quota cost. For a synthesized natural-language answer use chat_knowledge. Read-only, no side effects. |
| get_track_recordA | Returns the AlgoVault track record — aggregated PFE win rates by call type, timeframe and asset tier, plus the evaluation methodology and window. The same verified aggregate the performance://signal-performance resource serves, callable from harnesses that bridge tools only. Defaults to the compact aggregate; use include for the per-asset, per-venue or recent-signal breakdowns. Read-only, no side effects. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| usage-stats | Request analytics — call counts, tool breakdown, tier distribution, top assets, response times. Requires Pro or higher. |
| signal-performance | Signal track record — PFE win rates by timeframe, asset, tier, and signal type. Measures whether price moved in the signal direction during the evaluation window. |
| venues | Per-venue lifecycle state machine: shadow / promoted / retired. Each venue carries asset_count, integration + lifecycle timestamps (integrated_at / promoted_at / retired_at), and extension_count. New venues default to 'shadow' (experimental — not yet on the public /track-record dashboard) and are flagged ready-for-promotion when PFE WR clears the internal bar; an operator launches the promotion. Agents querying with a shadow venue's exchange_id should surface an 'experimental' caveat to the end user. |
| skills-analytics | Per-Skill invocation counters (calls_24h, calls_7d, calls_all_time, first/last seen) for the algovault-skills plugin. Public — slug-level aggregates only. |
TDQS
Scored across 10 tools
Most tools have sharply distinct roles: single-coin vs. scan variants (get_trade_call / scan_trade_calls, get_market_regime / scan_market_regimes) and synthesized vs. lexical knowledge (chat_knowledge / search_knowledge) are explicitly contrasted in their descriptions. The one clear overlap is get_trade_signal, which is openly an alias of get_trade_call — same behavior, two entries — mildly inflating the apparent surface.
The set is dominated by predictable verb_noun naming (get_*, scan_*, search_*, chat_*) with clear resource suffixes. Deviations are minor: pre_trade_check is noun-first and chat_knowledge/search_knowledge drop the verb_noun shape, but every name remains readable and self-descriptive.
Ten tools is squarely in the healthy range for a read-only signal/risk server, and each operation (single-asset, scan, risk check, track record, knowledge) maps to a real workflow. The only count bloat is the get_trade_signal alias, which duplicates get_trade_call rather than adding capability.
The surface covers the core lifecycle: per-asset and whole-market trade calls, regime reads and regime scans, cross-venue funding arbitrage, a pre-trade risk gate, verified performance history, and knowledge/documentation retrieval. Gaps are minor — no watchlist/alerting, no historical candle or backtest tool, and funding data is only exposed via arbitrage scans and composite verdicts rather than a dedicated pair-level lookup.