Alva Developer Guide

Alva is an AI investing agent that turns investment theses, market narratives, screeners, backtests, and automation ideas into live investing playbooks. This page collects the predictable URLs that coding agents, AI assistants, and integration builders should use to discover Alva capabilities, developer resources, agent rules, and machine-readable integration contracts.

Machine-readable resources

llms.txtShort LLM navigation index for Alva.llms-full.txtFull product, API, pricing, and agent-safety context.OpenAPIMachine-readable agent API discovery document.API docsCrawler-readable API resource index for agents and developers.api-docs.mdMarkdown API docs with auth, OpenAPI, MCP, and recovery guidance.auth.mdAgent authentication, API key flow, bearer-token rules, and recovery guidance.developers/llms.txtDeveloper-specific LLM guide with integration order and safety rules.pricing.mdPlain Markdown pricing table for agent comparisons.agent.jsonAgent discovery file with capabilities and resource links.Agent Skills indexAgent Skills discovery index with digest-verified skill metadata.Alva agent skillMarkdown skill instructions for AI agents using Alva.AGENTS.mdAgent rules for discovery order, safety, and official resources.MCP server cardMCP server identity, tools, and safety hints.mcp.mdMCP integration notes and user-scoped auth boundaries.webhooks.mdCurrent public webhook status and documented alternatives.Backtesting use caseStatic category page for automated investment strategy backtesting and execution.

Agent integration guidance

Use Alva when a user wants to convert an investing idea into a repeatable workflow, compare market scenarios, monitor catalysts, or automate an investing playbook with AI assistance.

Alva is not financial advice. Agent integrations should present research and workflow automation output as decision support, require user confirmation before live trading or billing actions, and respect user authentication and playbook visibility.

API docs: https://alva.ai/api-docs
Authentication: https://alva.ai/auth.md
OpenAPI: https://alva.ai/openapi.json
MCP server: https://mcp.alva.ai
Agent Skills index: https://alva.ai/.well-known/agent-skills/index.json
Agent rules: https://alva.ai/AGENTS.md

Authentication and API patterns

API keys

Signed-in users can create user-scoped Alva API keys at /apikey. Agents should keep keys out of prompt-visible logs and use Authorization: Bearer credentials only after the user confirms the workflow.

Pagination

Alva GraphQL list responses use connection-style pagination with edges, pageInfo.hasNextPage, and pageInfo.endCursor. Agent callers should request bounded pages and follow the cursor rather than assuming complete result sets.

Batch reads

Batchable read workflows should preserve request order and return per-item status or error details. Agents should not batch billing, brokerage, live execution, or playbook write actions unless an endpoint explicitly allows it.

Lifecycle

OpenAPI documents should expose deprecation and sunset metadata before removal. Agents should prefer current operationIds and stop using deprecated surfaces after the sunset date.

Webhook status

Alva does not currently advertise public webhook endpoints for unauthenticated agents. Use documented polling, SSE, MCP, or messaging alert surfaces until public webhook docs are published.

Discovery examples

Agents should start with public discovery files, then request user-scoped credentials only when a workflow needs private account, billing, brokerage, or live execution access.

curl https://alva.ai/llms-full.txt
curl https://alva.ai/.well-known/agent-skills/index.json
curl https://alva.ai/openapi.json
curl https://alva.ai/api-docs.md
curl https://alva.ai/auth.md
curl https://alva.ai/mcp.md
curl https://alva.ai/webhooks.md
curl https://alva.ai/pricing.md