FactorWeave
Server Details
A quant-factor brain for your AI — factor scores, similarity search, and risk-coherence analogues for 14,684 tickers across 6 asset classes
- Status
- Healthy
- Last Tested
- Transport
- Streamable HTTP
- URL
Glama MCP Gateway
Connect through Glama MCP Gateway for full control over tool access and complete visibility into every call.
Full call logging
Every tool call is logged with complete inputs and outputs, so you can debug issues and audit what your agents are doing.
Tool access control
Enable or disable individual tools per connector, so you decide what your agents can and cannot do.
Managed credentials
Glama handles OAuth flows, token storage, and automatic rotation, so credentials never expire on your clients.
Usage analytics
See which tools your agents call, how often, and when, so you can understand usage patterns and catch anomalies.
Tool Definition Quality
Average 4.1/5 across 14 of 14 tools scored.
Each tool has a clearly distinct purpose. For example, get_features returns factor rows, get_labels returns forward-return labels, find_similar performs similarity search, and get_market_context provides broad market analytics. No two tools overlap; even get_report_card and get_risk_cluster are distinct (digest vs. standalone risk signal).
Most tools follow the 'get_' prefix pattern (e.g., get_features, get_alerts), which is consistent and clear. Two tools deviate: find_similar and list_futures, but they use different descriptive verbs. The naming is all lowercase snake_case and readable, with only minor inconsistencies.
14 tools are well-scoped for a financial factor analysis API. Each tool serves a specific function without redundancy, covering data retrieval, similarity search, market context, alerts, and usage. The count is neither too few nor excessive for the domain.
The tool surface covers the full lifecycle of factor-based analysis: raw data (get_features, get_labels, get_embedding), similarity search (find_similar), market context (get_market_context, get_market_regime, get_vx_term_structure), risk assessment (get_risk_cluster), top tickers (get_top), and user utilities (get_alerts, get_usage). There are no obvious gaps for the stated purpose.
Available Tools
14 toolsfind_similarRead-onlyIdempotentInspect
Find historical (ticker, date) setups most similar to a query ticker today. Four similarity methods are available: cosine (default, all tiers) ranks by cosine similarity of 32-D regime-aware embeddings; label_aware (PRO+) restricts the backbook to dates in the same SPY volatility regime; supervised (QUANT) projects embeddings through a PLS regression fit on forward-return labels so neighbors are ones whose factor profile most-strongly-predicted realized returns; dtw (HOBBY+) cosine-shortlists then reranks by dynamic-time-warping distance over the rolling return window. Each returned neighbor row carries the analogue's factor row and forward-return labels at that historical (ticker, date) — pre-joined for honest backtests, no extra fetches needed. Use min_lookback_days=30 to filter out same-day correlated tickers. Pass conditioner=vx_term_structure (QUANT only) to additionally filter analogues to dates with a VIX-curve regime similar to today.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| method | No | Similarity method. Tier-gated: FREE=cosine; HOBBY=cosine+dtw; PRO=cosine+dtw+label_aware; QUANT=all four. | cosine |
| ticker | Yes | ||
| tolerance | No | Max |conditioner_query − conditioner_neighbor|. Only used when conditioner is set. | |
| conditioner | No | QUANT only. Filter analogues to dates with a similar regime conditioner value. Currently only vx_term_structure is supported. Limits: analogues older than 252 trading days are passed through unverified. | |
| min_lookback_days | No | Require neighbor_date to be at least this many days before query_date. Default 30 strips co-traded same-day ETFs. |
Output Schema
| Name | Required | Description |
|---|---|---|
| method | Yes | |
| neighbors | Yes | |
| tolerance | No | Echo of conditioner tolerance. |
| query_date | No | |
| conditioner | No | Present only when conditioner is requested (QUANT). |
| query_ticker | Yes | |
| conditioner_note | No | Notes about the conditioner filter — matched count, unverified count. |
| min_lookback_days | No |
get_alertsRead-onlyIdempotentInspect
List active alert rules belonging to the current authenticated user.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Output Schema
| Name | Required | Description |
|---|---|---|
| count | No | |
| rules | Yes |
get_embeddingRead-onlyIdempotentInspect
The raw 32-D regime-aware factor-state embedding vector for a ticker — the representation the similarity search itself runs on. Build your own models / similarity on it. QUANT tier only.
| Name | Required | Description | Default |
|---|---|---|---|
| ticker | Yes |
Output Schema
| Name | Required | Description |
|---|---|---|
| dim | No | Vector dimensionality (currently 32). |
| as_of | No | |
| ticker | Yes | |
| embedding | Yes | The raw factor-state embedding. |
get_featuresRead-onlyIdempotentInspect
Get factor row for a ticker. With no date arg, returns the most recent row. With date / start_date / end_date, returns the historical row(s) — useful for honest analogue-backtests (querying a setup as it was on a specific historical date, not as it looks today). History is the last 252 trading days. Stock/ETF = FREE+; futures = PRO+ (adds Open Interest features). PRO+ subscribers automatically get intraday-derived columns (overnight_ret, intraday_ret, or_high_30, or_low_30, or_breakout_pct, vwap, vwap_dev_close, intraday_rv, late_drift) on the stock row.
| Name | Required | Description | Default |
|---|---|---|---|
| date | No | Single ISO date YYYY-MM-DD. Returns one row. | |
| ticker | Yes | Ticker symbol, e.g. AAPL or SPY | |
| end_date | No | Inclusive ISO end date for a range query. | |
| start_date | No | Inclusive ISO start date for a range query. |
Output Schema
| Name | Required | Description |
|---|---|---|
No output parameters | ||
get_labelsRead-onlyIdempotentInspect
Forward-return labels (1d/5d/20d) and binary targets for backtesting. PRO tier or higher.
| Name | Required | Description | Default |
|---|---|---|---|
| ticker | Yes |
Output Schema
| Name | Required | Description |
|---|---|---|
| count | No | |
| labels | Yes | |
| ticker | Yes |
get_manifestRead-onlyIdempotentInspect
Bundle metadata: latest_date, ticker_count, regime distribution. Public — no auth needed.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Output Schema
| Name | Required | Description |
|---|---|---|
| files | No | |
| latest_date | No | Most-recent trading-day for which factor data is available. |
| generated_at | No | |
| ticker_count | No | |
| schema_version | No | |
| labels_history_days | No | |
| neighbor_shard_count | No | |
| features_history_days | No |
get_market_contextRead-onlyIdempotentInspect
Whole-universe derived market analytics: factor dispersion (10-90 percentile spreads of momentum / composite / RSI), breadth (% of the universe positive / overbought / oversold), and the current SPY-volatility regime with empirical next-day transition odds. FREE gets today's reading; HOBBY+ can also get the 252-day history (pass history=true).
| Name | Required | Description | Default |
|---|---|---|---|
| history | No | Include the 252-day history (HOBBY tier or higher). |
Output Schema
| Name | Required | Description |
|---|---|---|
| date | No | |
| regime | No | |
| breadth | No | Per-factor % positive / overbought / oversold. |
| history | No | 252-day history (HOBBY+ only). Each row carries the per-day cross-asset z-scores + vx_term_structure for charting. |
| dispersion | No | Per-factor 10–90 percentile spread. |
| cross_asset | No | DXY / VIX / VVIX / VIX9D / TNX / XAU / VX-continuous closes + 20d log-return z-scores, plus vx_term_structure = (VX_continuous − VIX_cash) / VIX_cash. |
| regime_transition_odds | No | Empirical next-day regime-transition probabilities. |
get_market_regimeRead-onlyIdempotentInspect
Current SPY-realized-volatility regime classification (low/mid/high) and recent regime history for context.
| Name | Required | Description | Default |
|---|---|---|---|
| days | No |
Output Schema
| Name | Required | Description |
|---|---|---|
| today | No | |
| history | No | |
| distribution | No | low/mid/high → count in the window |
| history_days | No |
get_report_cardRead-onlyIdempotentInspect
Per-ticker derived digest: factor snapshot, cross-sectional percentile ranks, risk-cluster tag, current market regime, and an unusualness score (z-score of today's factor state vs the ticker's own 252-day history). HOBBY tier or higher; the risk-cluster block requires PRO.
| Name | Required | Description | Default |
|---|---|---|---|
| ticker | Yes |
Output Schema
| Name | Required | Description |
|---|---|---|
| as_of | No | |
| ranks | No | Cross-sectional percentile ranks per factor. |
| regime | No | |
| ticker | Yes | |
| snapshot | No | |
| risk_cluster | No | |
| unusualness_score | No | Z-score of today's factor state vs the ticker's own 252-day history. |
get_risk_clusterRead-onlyIdempotentInspect
The volatility regime a ticker's factor analogues historically landed in — calm / normal / stressed — derived from the realized forward volatility of its cosine neighbours. A risk-coherence / screening signal, NOT a volatility forecast. PRO tier or higher.
| Name | Required | Description | Default |
|---|---|---|---|
| ticker | Yes |
Output Schema
| Name | Required | Description |
|---|---|---|
| as_of | No | |
| ticker | Yes | |
| cluster | Yes | |
| confidence | No | 0–1 confidence. |
| realized_vol_fwd_20d | No |
get_topRead-onlyIdempotentInspect
Top-N tickers ranked by a factor on the latest available date. Common factors: mom (momentum), meanrev, comp_score, rsi, z_52w, beta_spy.
| Name | Required | Description | Default |
|---|---|---|---|
| n | No | ||
| factor | No | mom | |
| direction | No | desc |
Output Schema
| Name | Required | Description |
|---|---|---|
| rows | Yes | |
| factor | Yes | |
| direction | No |
get_usageRead-onlyIdempotentInspect
Current daily/monthly API usage and tier limits for the authenticated user.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Output Schema
| Name | Required | Description |
|---|---|---|
| mtd | No | Month-to-date usage. |
| tier | No | |
| today | No | |
| daily_quota | No |
get_vx_term_structureRead-onlyIdempotentInspect
VIX futures contango/backwardation read: (VX_continuous − VIX_cash) / VIX_cash. Negative = backwardation (near-term realized vol > expected forward vol — classic stress / vol-panic signal). Positive = contango (term structure normal, calm regime). Pass history=true (HOBBY+) for the 252-day series for charting. Single-number version of the vol-curve regime that traders watch every day.
| Name | Required | Description | Default |
|---|---|---|---|
| history | No | Include the 252-day history (HOBBY tier or higher). |
Output Schema
| Name | Required | Description |
|---|---|---|
| as_of | No | |
| regime | Yes | |
| history | No | 252-day history (HOBBY+ only). |
| vx_close | No | |
| vix_close | No | |
| vix9d_close | No | |
| vx_term_structure | Yes | (VX_continuous − VIX_cash) / VIX_cash. Negative = backwardation; positive = contango. |
list_futuresRead-onlyIdempotentInspect
List the top-30 futures contracts that have per-ticker factor decomposition available. Returns ticker, the asset family (equity-index / energy / metals / rates / fx / crypto), and the latest snapshot (close, mom, rsi, oi_z20, oi_vol_ratio, comp_score). PRO tier or higher for the snapshot block; ticker list itself is FREE. Use the returned tickers with get_features to pull the full factor row (e.g. get_features(ticker="VX") for the VIX futures continuous contract).
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Output Schema
| Name | Required | Description |
|---|---|---|
| count | Yes | |
| tickers | Yes | |
| snapshot_locked | No | true for non-PRO tiers — snapshot fields are absent. |
Claim this connector by publishing a /.well-known/glama.json file on your server's domain with the following structure:
{
"$schema": "https://glama.ai/mcp/schemas/connector.json",
"maintainers": [{ "email": "your-email@example.com" }]
}The email address must match the email associated with your Glama account. Once published, Glama will automatically detect and verify the file within a few minutes.
Control your server's listing on Glama, including description and metadata
Access analytics and receive server usage reports
Get monitoring and health status updates for your server
Feature your server to boost visibility and reach more users
For users:
Full audit trail – every tool call is logged with inputs and outputs for compliance and debugging
Granular tool control – enable or disable individual tools per connector to limit what your AI agents can do
Centralized credential management – store and rotate API keys and OAuth tokens in one place
Change alerts – get notified when a connector changes its schema, adds or removes tools, or updates tool definitions, so nothing breaks silently
For server owners:
Proven adoption – public usage metrics on your listing show real-world traction and build trust with prospective users
Tool-level analytics – see which tools are being used most, helping you prioritize development and documentation
Direct user feedback – users can report issues and suggest improvements through the listing, giving you a channel you would not have otherwise
The connector status is unhealthy when Glama is unable to successfully connect to the server. This can happen for several reasons:
The server is experiencing an outage
The URL of the server is wrong
Credentials required to access the server are missing or invalid
If you are the owner of this MCP connector and would like to make modifications to the listing, including providing test credentials for accessing the server, please contact support@glama.ai.
Discussions
No comments yet. Be the first to start the discussion!