mcp

<div align="center">

# AlgoVesta MCP Server

**Trade 16 crypto exchanges and MetaTrader 5 from your AI assistant — over one MCP connection.**

[![MCP Registry](https://img.shields.io/badge/MCP%20Registry-com.algovesta%2Ftrading-1f6feb)](https://registry.modelcontextprotocol.io)
[![Transport](https://img.shields.io/badge/transport-Streamable%20HTTP-0b7285)](https://modelcontextprotocol.io)
[![Auth](https://img.shields.io/badge/auth-OAuth%202.1%20%C2%B7%20PKCE%20S256-5f3dc4)](docs/AUTHENTICATION.md)
[![Tools](https://img.shields.io/badge/tools-20-2b8a3e)](docs/TOOLS.md)
[![Docs license](https://img.shields.io/badge/docs-CC%20BY%204.0-495057)](LICENSE)

[Documentation](https://algovesta.com/mcp-docs.html) · [Tool reference](docs/TOOLS.md) · [Safety model](docs/SAFETY.md) · [Tool schemas (JSON)](https://algovesta.com/mcp/tools.json) · [Product overview](https://algovesta.com/features-mcp.html)

</div>

---

AlgoVesta runs a hosted [Model Context Protocol](https://modelcontextprotocol.io) 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](#at-a-glance) · [How it works](#how-it-works) · [Quick start](#quick-start) · [Connect your client](#connect-your-client) · [Supported AI clients](#supported-ai-clients) · [In use](#what-it-looks-like-in-use) · [Tools](#tools) · [Safety model](#safety-model) · [Venues](#venues) · [Performance and limits](#performance-and-limits) · [Endpoints](#endpoints) · [FAQ](#faq)

## At a glance

| | |
|---|---|
| **Transport** | Remote MCP over Streamable HTTP |
| **Authentication** | Secret link, or OAuth 2.1 with mandatory PKCE (`S256`) and Dynamic Client Registration (RFC 7591) |
| **Tools** | 20 — 13 read-only, 3 write, 4 destructive ([reference](docs/TOOLS.md)) |
| **Venues** | 16 crypto exchanges · MetaTrader 5 · built-in paper engine |
| **Default scope** | `paper` — $5,000 virtual balance, identical toolset |
| **Live scope** | Issued only after a second factor, enforced server-side |
| **Risk policy** | Compiled to JSON, evaluated deterministically on the server |
| **Audit** | ed25519-signed, hash-chained receipt per action, independently verifiable |
| **Install** | None. Hosted endpoint. |
| **Registry** | [`com.algovesta/trading`](https://registry.modelcontextprotocol.io) — [server.json](server.json) is that manifest |

## How it works

```mermaid
flowchart LR
    A["AI client<br/>Claude, ChatGPT, Cursor, and more"]
    B["AlgoVesta MCP server<br/>scope, rate limit, idempotency"]
    C{"Policy wall<br/>evaluated server-side"}
    R["Refusal<br/>plus audit entry"]
    D["Execution"]
    E["16 crypto exchanges"]
    F["MetaTrader 5<br/>managed terminals"]
    G["Paper engine<br/>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.

## Quick start

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](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

Settings -> Connectors -> **Add custom connector**, paste the URL, then allow the tools when Claude asks. [Walkthrough](examples/claude.md)

### Claude Code

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

[Walkthrough](examples/claude-code.md)

### ChatGPT

Settings -> Connectors -> **Advanced** -> Developer mode -> **Create**, transport **Streamable HTTP**. Custom connectors are a paid-plan feature on OpenAI's side. [Walkthrough](examples/chatgpt.md)

### Cursor

`~/.cursor/mcp.json`, or `.cursor/mcp.json` inside a project — [file](examples/cursor/mcp.json)

```json
{
  "mcpServers": {
    "algovesta": { "url": "https://api.algovesta.com/u/avmcp_<your-key>/mcp" }
  }
}
```

### VS Code — GitHub Copilot

`.vscode/mcp.json` — [file](examples/vscode/mcp.json)

```json
{
  "servers": {
    "algovesta": {
      "type": "http",
      "url": "https://api.algovesta.com/u/avmcp_<your-key>/mcp"
    }
  }
}
```

### Gemini CLI

`~/.gemini/settings.json` — [file](examples/gemini-cli/settings.json). CLI only; the Gemini web app does not accept custom MCP servers.

```json
{
  "mcpServers": {
    "algovesta": { "httpUrl": "https://api.algovesta.com/u/avmcp_<your-key>/mcp" }
  }
}
```

### Anything else

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

<details>
<summary><b>Assistants and chat apps</b> — 8</summary>

| Client | MCP documentation |
|---|---|
| Claude — web, desktop, iOS, Android | [Custom connectors](https://support.claude.com/en/articles/11175166-about-custom-connectors-remote-mcp-servers) |
| ChatGPT — Developer mode connectors | [OpenAI MCP docs](https://platform.openai.com/docs/mcp) |
| Microsoft Copilot Studio agents | [Extend with MCP](https://learn.microsoft.com/en-us/microsoft-copilot-studio/agent-extend-action-mcp) |
| Goose (Block) | [block.github.io/goose](https://block.github.io/goose/) |
| LibreChat | [MCP in LibreChat](https://www.librechat.ai/docs/features/mcp) |
| Open WebUI | [docs.openwebui.com](https://docs.openwebui.com/) |
| Cherry Studio | [docs.cherry-ai.com](https://docs.cherry-ai.com/) |
| Raycast | [raycast.com](https://www.raycast.com/) |

</details>

<details>
<summary><b>Coding agents and IDEs</b> — 19</summary>

| Client | MCP documentation |
|---|---|
| Claude Code | [Claude Code MCP](https://docs.anthropic.com/en/docs/claude-code/mcp) |
| OpenAI Codex CLI | [Codex MCP](https://developers.openai.com/codex/mcp/) |
| Gemini CLI | [MCP servers in Gemini CLI](https://google-gemini.github.io/gemini-cli/docs/tools/mcp-server.html) |
| Cursor | [Cursor MCP](https://cursor.com/docs/context/mcp) |
| VS Code — GitHub Copilot | [MCP servers in VS Code](https://code.visualstudio.com/docs/copilot/customization/mcp-servers) |
| Windsurf | [Cascade MCP](https://docs.windsurf.com/windsurf/cascade/mcp) |
| Zed | [Zed MCP](https://zed.dev/docs/ai/mcp) |
| Cline | [Connecting to a remote server](https://docs.cline.bot/mcp/connecting-to-a-remote-server) |
| Roo Code | [Using MCP in Roo](https://docs.roocode.com/features/mcp/using-mcp-in-roo) |
| Kilo Code | [Using MCP in Kilo Code](https://kilocode.ai/docs/features/mcp/using-mcp-in-kilo-code) |
| Continue | [MCP deep dive](https://docs.continue.dev/customize/deep-dives/mcp) |
| JetBrains AI Assistant | [MCP in JetBrains IDEs](https://www.jetbrains.com/help/ai-assistant/mcp.html) |
| Warp | [Warp MCP](https://docs.warp.dev/knowledge-and-collaboration/mcp) |
| Amazon Q Developer | [MCP with Amazon Q](https://docs.aws.amazon.com/amazonq/latest/qdeveloper-ug/qdev-mcp.html) |
| Kiro (AWS) | [Kiro MCP](https://kiro.dev/docs/mcp/) |
| Sourcegraph Amp | [Amp manual](https://ampcode.com/manual#mcp) |
| Trae | [Trae MCP](https://docs.trae.ai/ide/model-context-protocol) |
| PostHog Code | [posthog.com/code](https://posthog.com/code/) |
| Archestra.AI | [archestra.ai](https://www.archestra.ai/) |

</details>

<details>
<summary><b>Frameworks, automation and developer tools</b> — 6</summary>

| Client | MCP documentation |
|---|---|
| OpenAI Agents SDK | [MCP in the Agents SDK](https://openai.github.io/openai-agents-python/mcp/) |
| fast-agent | [evalstate/fast-agent](https://github.com/evalstate/fast-agent) |
| n8n — MCP Client Tool node | [docs.n8n.io](https://docs.n8n.io/) |
| Postman | [MCP requests](https://learning.postman.com/docs/postman-ai-agent-builder/mcp-requests/overview/) |
| MCP Inspector | [modelcontextprotocol/inspector](https://github.com/modelcontextprotocol/inspector) |
| MCPJam | [mcpjam.com](https://www.mcpjam.com/) |

</details>

> **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 connec