Central Command — x402 Trading Intelligence

Bitcoin ETF Flow Tracker

cc.etf_flows

Read-onlyIdempotent

Call cc.etf_flows — Real-time Bitcoin/crypto ETF inflow and outflow data tracking institutional positioning (GBTC, IBIT, FBTC, etc). 60-min cache. Purpose: Real-time Bitcoin/crypto ETF inflow and outflow data tracking institutional positioning (GBTC, IBIT, FBTC, etc). 60-min cache. Behavior: READ-ONLY. Does not place orders, move funds, or mutate your exchange account. Responses may be cached (~3600s). Auth: X-Api-Key or x402 payment proof (X-PAYMENT / __x_payment). Anonymous unauthenticated calls receive HTTP 402 with payment accepts. Cost: $0.002 USDC per successful call (x402 Base USDC pay-per-use or prepaid X-Api-Key balance). Linked Connect keys are free. This is billing, not a side effect. Rate limit: 30/min (per API key). Tier: standard. Returns: Per-ETF daily flow in USD with cumulative totals, showing institutional demand/supply dynamics. Guidelines: Use for research / signal context. Pair with cc.agent_strategy (paper) before any live order. Do not invent fills from this data alone. Tags: etf, institutional, flows, bitcoin, blackrock, grayscale.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`__x_payment`	No	Optional x402 payment proof (same value as X-PAYMENT header). Use when retrying after HTTP 402 if your MCP client cannot set custom headers. Not a business parameter. Optional.

Output Schema

TableJSON Schema

Name	Required	Description
`ok`	Yes	True when the gateway HTTP status is 2xx.
`data`	No	Parsed JSON body from the endpoint (shape varies by slug).
`error`	No	Error message when ok is false.
`status`	Yes	Upstream HTTP status from x402-gateway.
`billing`	No	Optional payment / cost metadata when present.
`endpoint`	Yes	Catalog slug that was invoked (e.g. funding-rates).

TDQS

A4.7/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description discloses behavior beyond annotations: states READ-ONLY, does not place orders/move funds, mentions caching (~3600s), email auth methods, HTTP 402 for anonymous calls, cost per call, and rate limit. This is rich context that annotations do not cover, and it is consistent with readOnlyHint and idempotentHint.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description contains redundancy: the opening sentence and the 'Purpose' section repeat nearly identical content. While structured with labels, the extra tags and duplicated purpose reduce conciseness.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description is exceptionally complete: covers purpose, behavior, auth, cost, rate limits, return format, and usage guidelines. With an existing output schema and no required parameters, the description fully compensates for any missing context and provides operational details.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% for the only parameter (__x_payment), so baseline is 3. The description adds context by explaining that __x_payment is an alternative to X-Api-Key auth and how to use it after an HTTP 402, going beyond the schema's description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's function: real-time Bitcoin/crypto ETF inflow and outflow data tracking institutional positioning, naming specific ETFs (GBTC, IBIT, FBTC). This is a specific verb+resource pair that distinguishes it from sibling data tools like funding rates or open interest.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides explicit usage guidance: use for research/signal context and pair with cc.agent_strategy (paper) before any live order. It also warns not to invent fills from this data alone, clearly delineating when to use this tool vs alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Central Command — x402 Trading Intelligence tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.7/5.0

Disambiguation2/5

Multiple tools have overlapping or unclear boundaries. The AI chat tools cc.squirrel_chat, cc.squirrel_chat_v2, and cc.openclaw_chat all provide conversational trading assistance with near-identical descriptions, while cc.central_signal and cc.external_signal both normalize signals for execution. Additionally, cc.asset_scanner, cc.auto_fetch_market_data, cc.data_tools, and cc.ma_fetch all supply technical indicator data with significant overlap.

Naming Consistency4/5

All tools share the 'cc.' prefix and use snake_case consistently, which creates a uniform feel. However, naming style mixes nouns (cc.asset_scanner, cc.data_tools) with verbs (cc.auto_fetch, cc.list_catalog) and compound forms (cc.strategy_backtest, cc.trade_builder), so it is not a strict verb_noun pattern. Minor deviations keep it from a 5.

Tool Count2/5

With 33 tools, the server is well beyond the typical well-scoped range of 3-15 and even above the 'heavy' 16-25 range. While the trading intelligence domain can be broad, this count feels overstuffed rather than curated, especially given the many overlapping data and AI tools.

Completeness3/5

The core trading workflow is covered: market data, technical analysis, signals, strategy backtesting, paper trading, and live execution all have tools. However, there is no dedicated account management tool (e.g., get_balance, list_positions) and no explicit delete_strategy, with these operations buried inside cc.agent_strategy's action parameter. Notable gaps remain for a complete lifecycle.

Resources

Need Help?