Skip to main content
Glama

Central Command — x402 Trading Intelligence

by io.github.tlefko
OverviewDiscussionsAdmin

Agent Strategy Console

cc.agent_strategy
Destructive

Run the Central Command agent console (strategy lifecycle + account actions). Purpose: guide/whoami, create/update strategies, backtest, deploy STOPPED, paper execute, and (explicitly) live orders. Behavior: READ + WRITE. Deploy without execute does NOT move money. Live place_order/close_position/cancel_order require confirm_live=true. Default force_paper=true. Auth: X-Api-Key (linked Connect keys preferred — free). Do not spoof X-Linked-User-Id. Cost: linked Connect keys free; otherwise prepaid / x402 per catalog price for agent-strategy. Rate limit: plan default. Returns: JSON envelope { ok, endpoint, status, data: { ok, guide|whoami|created|deployed|... } }. Guidelines: Start with action=guide then whoami. Prefer paper. Never invent outbound-proxy failures — report real HTTP status/body.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
idNoStrategy id for get/update/deploy/execute/backtest. Optional.
bodyNoFull JSON body merge/override for advanced fields. Optional.
goalNoNatural-language strategy goal / rules. Optional.
titleNoStrategy title when creating/updating. Optional.
actionYesRequired intent. Safe/read: guide, whoami, strategies, get_strategy, portfolio, positions, orders, balance, results, logs, get_backtest. Write (no live money): create_strategy, update_strategy, deploy, pause, backtest, execute with force_paper=true. Destructive live: place_order, close_position, cancel_order — require confirm_live=true. Example: "guide".
settingsNoFor update_strategy: { strategy_config: {max_leverage, max_risk_per_trade_pct, max_concurrent_positions, asset_universe, ...}, capital_config, check_interval_minutes, trading_permissions }. Hot-editable fields work even while running; cold fields (goal, strategy_notes) require pause first. All changes logged.
task_typeNoTask classification for create_strategy. Prefer "paper". Optional.
__x_paymentNoOptional x402 payment proof (same as X-PAYMENT header) when retrying after 402. Optional.
force_paperNoWhen true (recommended default), execute paths stay on paper. Optional.
confirm_liveNoMust be true to place/cancel LIVE exchange orders. Never set unless the human explicitly confirmed. Optional.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
okYesTrue when the gateway HTTP status is 2xx.
dataNoParsed JSON body from the endpoint (shape varies by slug).
errorNoError message when ok is false.
statusYesUpstream HTTP status from x402-gateway.
billingNoOptional payment / cost metadata when present.
endpointYesCatalog slug that was invoked (e.g. funding-rates).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / settings
      Added value: +{
+  "description": "For update_strategy: { strategy_config: {max_leverage, max_risk_per_trade_pct, max_concurrent_positions, asset_universe, ...}, capital_config, check_interval_minutes, trading_permissions }. Hot-editable fields work even while running; cold fields (goal, strategy_notes) require pause first. All changes logged.",
+  "type": "object"
+}
  2. Added

TDQS

A4.7/5.0
Behavior5/5

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

Description significantly expands on annotations by disclosing READ+WRITE behavior, that deploy without execute does not move money, default force_paper=true, auth requirements (X-Api-Key, no spoofing X-Linked-User-Id), cost implications, rate limit, and specific instruction to report real HTTP errors. This far exceeds the annotation hints.

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

Conciseness5/5

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

The description is dense but every sentence serves a purpose, structured logically from purpose to behavior, safety, auth, cost, returns, and guidelines. It is front-loaded with the primary purpose and uses compact bullet-like phrasing without redundancy.

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?

Given the tool's complexity (10 params, nested objects, output schema), the description covers all key aspects: purpose, side effects, safety gates, auth, cost, rate limit, return envelope, and usage sequence. The output schema and parameter descriptions fill in the remaining 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 covers 100% of parameters with descriptions, so the baseline is 3. The description adds value by clarifying action categories (safe/read vs write vs destructive live), default force_paper behavior, and the confirm_live requirement, which helps interpret parameters. However, it doesn't detail each parameter beyond schema.

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?

States it runs the Central Command agent console covering strategy lifecycle and account actions, listing specific actions (guide/whoami, create/update, backtest, deploy, paper execute, live orders). Clearly distinguishes from sibling data-fetching tools like cc.asset_scanner or cc.coinglass_data.

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

Usage Guidelines4/5

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

Provides explicit guidelines: start with action=guide then whoami, prefer paper, and warns that live orders require confirm_live=true. However, it does not explicitly name alternative tools or specify when not to use this tool, so it falls short of a 5.

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 toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources