BotSpot: AI Trading, Backtests and Bots

Account status and current AI models

account

Read-only

Read account billing, provider-aware current and historical subscriptions with billing states and management actions, and usage with status, or read the current database AI model catalog with models. Models includes supported effort and speed settings, plan availability, all token rates and sourced benchmarks. These are read-only operations; model discovery does not switch models or spend credits.

Set "action" to choose the operation. Only send the fields listed for that action.

action="status": Get BotSpot account and billing status

No other fields required. Returns payment status, active products, backtest usage, current cycle limits, and provider-aware current and historical subscription billing with billing states and management actions for this authenticated MCP user. Billing inventory availability is explicit; accessActive reports row entitlement, while effective authorization also applies payment suspension and permission checks. Stripe changes use the authenticated management link; App Store rows include Apple management links.

action="models": Get current AI models, capabilities, prices and benchmarks

No other fields required. Read the current database catalog before choosing or recommending an AI model for chat or an AI-powered strategy. Returns exact chat ids and valid strategyModelId values, allowed reasoning efforts, Standard/Fast service tiers, plan availability, USD token prices including cache and long context, and sourced benchmark results. Empty benchmarks mean unknown; different benchmarks are not comparable. A catalog entry is advertised capability, not evidence of a successful runtime test. If runtime logs reject advertised settings, explain the observed runtime/gateway rejection and preserve the requested model/settings. Unless the error names a rejected field, do not guess one or propose changing a valid strategy identifier merely because it differs from the chat id. The useful next check is verification of that exact model, effort and service tier through the failing runtime adapter before another unchanged retry; catalog support alone does not verify a compatibility repair. This read does not run models, change a selection, start a backtest or spend credits.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "action": "<action>"
    },
    "name": "account"
  }
}

Input Schema

Name	Required	Description	Default
`action`	Yes	Which operation to run: "status", "models". See the tool description for each one.

Schema Changelog

Changes observed during successful MCP inspections.

AddedOct 28, 2026

TDQS

A4.1/5.0

Behavior5/5

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

Annotations only declare readOnlyHint, but the description goes well beyond that: it states these are read-only, that model discovery does not switch models or spend credits, that status returns provider-aware billing states, entitlement vs. effective authorization semantics, and where Stripe/App Store management links come from. That is exactly the extra context annotations do not carry.

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?

Headers and front-loaded per-action sections make it scannable, but the models section drifts into runtime troubleshooting instructions (preserve requested settings, don't guess rejected fields, verify through the failing adapter) that are operational advice rather than tool-selection information. Roughly a third of the text does not help an agent decide to call this tool or how to invoke it.

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

Completeness4/5

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

With no output schema, the description does the work of explaining return contents for both actions, including billing states, plan availability, token price categories and benchmark provenance, which is sufficient to call it correctly. It stops short of covering ordering, volume or size of the catalog response, and the sibling overlap noted above remains unresolved.

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 single enum parameter, so the baseline is 3. The description adds real meaning by devoting a dedicated section to each enum value describing what that operation returns and how to treat the results (empty benchmarks mean unknown, benchmarks are not comparable, catalog entry is advertised capability not runtime proof), which the enum one-liner in the schema does not convey.

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

Purpose4/5

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

The description names both operations precisely: billing/subscription/usage status for the authenticated user, and the AI model catalog with effort, tiers, prices and benchmarks. Each is a specific verb+resource. It loses a point because the tool name 'account' only fits the first action, so an agent looking purely at the name would not expect model-catalog discovery here.

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?

Per-action guidance is explicit: use action="models" before choosing or recommending a model, and only send the fields listed for each action. What is missing is differentiation from siblings — 'show_account_overview', 'purchases' and 'create_billing_portal_link' exist but are never referenced, so an agent cannot tell from the description when to prefer those over action="status".

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

All BotSpot: AI Trading, Backtests and Bots tools Inspect

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.