AlgoVesta MCP Trading

AlgoVesta MCP Server

MCP server for 16 crypto exchanges + MetaTrader 5.

Trade from Claude, ChatGPT, Cursor or any MCP client over one hosted HTTPS connection. Paper by default.

Documentation · Tool reference · Safety model · Tool schemas (JSON) · Product overview

---

AlgoVesta runs a hosted Model Context Protocol server that reaches 16 crypto exchanges and MetaTrader 5 through a single HTTPS endpoint. Claude, ChatGPT, Cursor, Claude Code, Gemini CLI or any other MCP-capable client can read balances, open and close positions, move stop-loss and take-profit, and audit its own actions.

Your risk rules are compiled to JSON and evaluated on the server, after the request leaves the model — outside the reach of anything the model can be persuaded to say. Every new key starts on a $5,000 paper balance, and every action returns an ed25519-signed, hash-chained receipt.

Hosted and closed-source. This repository is the public documentation, tool reference and client configuration set. There is nothing to install, build or self-host — you connect to the hosted endpoint.

Contents — At a glance · How it works · Install in 2 minutes · Connect your client · Supported AI clients · In use · Tools · Safety model · Venues · Performance and limits · Endpoints · FAQ

At a glance

How it works

flowchart LR

A["AI client Claude, ChatGPT, Cursor, and more"] B["AlgoVesta MCP server scope, rate limit, idempotency"] C{"Policy wall evaluated server-side"} R["Refusal plus audit entry"] D["Execution"] E["16 crypto exchanges"] F["MetaTrader 5 managed terminals"] G["Paper engine 5,000 USD virtual"] H["ed25519-signed receipt"]

A -->|MCP over HTTPS| B B --> C C -->|violates a rule| R C -->|allowed| D D --> E D --> F D --> G D --> H

The model is the caller, never the authority. It decides what to ask for; the server decides what happens. Your exchange API keys never leave AlgoVesta and are created without withdrawal permission — the assistant only ever holds a scoped, revocable MCP link.

Install in 2 minutes

There is nothing to install locally: the server is hosted. An AI agent can follow llms-install.md step by step.

1. Create an AlgoVesta account and open the MCP Connection tab in the panel.
2. Generate a key. New keys default to the paper scope; the full link is shown once.
3. Paste the link into your AI client as a custom MCP server.

https://api.algovesta.com/u/avmcp_<your-key>/mcp

That URL is a credential. Treat it like a password. If it leaks, revoke it in the panel — revocation takes effect immediately for new connections and drops open event streams within seconds.

Clients that prefer a full authorization flow can use OAuth 2.1 instead, at https://api.algovesta.com/mcp. PKCE (S256) is mandatory and Dynamic Client Registration is supported, so most clients configure themselves. See docs/AUTHENTICATION.md.

Connect your client

Six walkthroughs below; anything else uses the same URL in whatever field it calls a remote MCP server.

Claude — web, desktop, iOS, Android

Customize -> Connectors -> + -> Add custom connector, paste the URL, then allow the tools when Claude asks. Walkthrough

Claude Code

claude mcp add --transport http algovesta https://api.algovesta.com/u/avmcp_<your-key>/mcp

Walkthrough

ChatGPT

chatgpt.com/plugins -> + -> Add custom MCP server -> public endpoint https://api.algovesta.com/mcp (Streamable HTTP, OAuth). Account and workspace policies on OpenAI's side decide who can add custom MCP servers. Walkthrough

Cursor

~/.cursor/mcp.json, or .cursor/mcp.json inside a project — file

{

"mcpServers": { "algovesta": { "url": "https://api.algovesta.com/u/avmcp_ /mcp" } } }

VS Code — GitHub Copilot

.vscode/mcp.json — file

{

"servers": { "algovesta": { "type": "http", "url": "https://api.algovesta.com/u/avmcp_ /mcp" } } }

Gemini CLI

~/.gemini/settings.json — file. CLI only; the Gemini web app does not accept custom MCP servers.

{

"mcpServers": { "algovesta": { "httpUrl": "https://api.algovesta.com/u/avmcp_ /mcp" } } }

Anything else

The three config shapes you will meet, plus a curl connection check: examples/other-clients.md

Supported AI clients

This is a standard remote MCP server over Streamable HTTP, so anything that speaks remote MCP can connect. The clients below document that support themselves — each row links to the client's own configuration docs, which is where the exact field name lives.

Assistants and chat apps — 8

Coding agents and IDEs — 19

Frameworks, automation and developer tools — 6

Scope of that claim. We have verified Claude end to end against this server. The others are listed because they document remote MCP support — not because we individually tested each one. Client support also moves fast, and a given client may gate custom servers behind account or workspace policy (ChatGPT does) or behind its CLI only (the Gemini web app does not accept custom MCP servers). If a listed client misbehaves with us, or one is missing, open an issue.

What it looks like in use

You never call a tool by name. You ask in plain language; the assistant picks the tool.

| *"Show me the receipt for that last order and verify it."* | verify_receipt — signature and hash chain, against a public key you can fetc