Skip to main content
Glama

NexusTrade Financial MCP

by io.github.austin-starks
OverviewDiscussionsAdmin

create_agent

⚠ COSTS LLM CREDITS on the NexusTrade account — spins up an Aurora agent via Router V5 classification + ReAct execution loops, billed per token. Manual approval required: do NOT call unless the user explicitly asked to launch an Aurora agent. For strategy creation/backtesting/analysis prefer no-LLM tools: structured create_portfolio (pass full IPortfolio JSON), backtest_portfolio, query_backtest_history, query_*, fetch_portfolios. Create a new autonomous Aurora agent using the same body shape as POST /api/agent. When maxIterations or automationMode are omitted, applies the user's saved ChatSettings. Agent models are product-locked (openai/gpt-5.6-luna planner, openai/gpt-6-luna executor, and the platform tool-role defaults) and cannot be overridden. Pass attachment_ids from upload_chat_attachment (READY) to bind files onto the last user message — same as the web FILES tab. Use this for a method-brief PDF plus a short analyze/report request.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
titleNoOptional user-assigned display name for the new agent (max 100 chars). Enables later lookup via title on get_agent / send_agent_message / etc.
messagesNoChatMessage array, e.g. [{"sender":"User","content":"..."}]
maxIterationsNoMax agent iterations. When omitted, uses the user's saved ChatSettings.agentIterations (same as the web UI).
session_depthNoDeprecated compatibility field. Both values use Aurora's adaptive routing policy.
attachment_idsNoREADY chat-attachment ids from upload_chat_attachment. Bound onto the last user message as fileAttachments (same refs as the web FILES tab).
automationModeNoautomated | semi-automated. When omitted, uses ChatSettings.agentAutomationMode.
conversationIdNoOptional NexusGenAI conversation id
idempotencyKeyNoCaller-chosen token that makes this create retry-safe. Creation runs the router and the planner and regularly takes longer than the transport will wait, so a call that times out has usually SUCCEEDED. Pass a unique key, and if the call appears to fail, retry with the SAME key: you get the agent the first call created, never a second billed run. A key reused for a different prompt is rejected rather than silently replayed.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.9/5.0
Behavior5/5

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

With no annotations, the description carries full behavioral burden, and it delivers: LLM credit billing, model lock-in, ChatSettings defaults, deprecated session_depth, attachment binding behavior, and idempotent retry semantics. These are non-obvious operational facts an agent needs before calling.

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

Conciseness4/5

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

The description is long, but the most critical warning (cost + manual approval) is front-loaded, and paragraphs are organized by concern: cost, usage policy, creation shape, model locking, attachments, and idempotency. It could be tightened slightly, but no sentence is pure filler.

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?

For a complex 8-parameter tool with no annotations, no output schema, and high misuse risk, the description is remarkably complete: it covers when to use, when not to use, cost, authentication-adjacent approval expectations, defaults, constraints, and retry behavior. Nothing essential for calling it correctly is missing.

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

Parameters5/5

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

Schema coverage is 100%, so the baseline is 3, but the description adds high-value semantics beyond the schema: idempotencyKey retry behavior (timeout often means success, same key avoids double billing), attachment_ids READY requirements, and default fallback for maxIterations and automationMode. This materially improves correct invocation.

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 a specific verb and resource: 'Create a new autonomous Aurora agent', and explains the mechanism (Router V5 classification + ReAct execution loops). It clearly separates this tool from the no-LLM portfolio/backtesting siblings by emphasizing the agent-launch intent.

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?

Explicitly says 'do NOT call unless the user explicitly asked to launch an Aurora agent' and names concrete alternatives (create_portfolio, backtest_portfolio, query_*) for non-agent workflows. This gives an agent a clear decision rule and prevents costly misuse.

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

All NexusTrade Financial MCP 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