algoglide
MCP server for AI coding editors — deploy and manage prediction-market trading agents directly from your editor.
README
<p align="center"> <img src="logo.svg" alt="algoglide" width="72" /> </p>
<p align="center"> MCP server for AI coding editors — deploy and manage prediction-market trading agents directly from your editor. </p>
<p align="center"> <a href="https://algoglide.com">algoglide.com</a> · <a href="https://docs.algoglide.com">Docs</a> · <a href="https://algoglide.com/app/api-keys">Get an API key</a> </p>
<br/>
Prerequisites
- Node.js 18 or later
- An algoglide API key — get one at algoglide.com/app/api-keys
Setup by editor
<table> <tr> <td align="center" width="120"><b>Cursor</b></td> <td>
Create .cursor/mcp.json in your project root (project-scoped) or ~/.cursor/mcp.json (global):
{
"mcpServers": {
"algoglide": {
"command": "npx",
"args": ["-y", "@algoglide/mcp-server"],
"env": {
"ALGOGLIDE_API_KEY": "sk_..."
}
}
}
}
Or open Cursor Settings → Tools & MCP → New MCP Server and paste the config above.
</td> </tr> <tr> <td align="center" width="120"><b>Cline</b></td> <td>
- Click the MCP Servers icon in the Cline sidebar
- Click Configure MCP Servers to open
cline_mcp_settings.json - Add the algoglide server:
{
"mcpServers": {
"algoglide": {
"command": "npx",
"args": ["-y", "@algoglide/mcp-server"],
"env": {
"ALGOGLIDE_API_KEY": "sk_..."
}
}
}
}
Config file location:
- macOS:
~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json - Windows:
%APPDATA%\Code\User\globalStorage\saoudrizwan.claude-dev\settings\cline_mcp_settings.json
</td> </tr> <tr> <td align="center" width="120"><b>Windsurf</b></td> <td>
- Open Windsurf Settings → Cascade → MCP (or Manage Plugins → View raw config)
- Edit
mcp_config.json:
{
"mcpServers": {
"algoglide": {
"command": "npx",
"args": ["-y", "@algoglide/mcp-server"],
"env": {
"ALGOGLIDE_API_KEY": "sk_..."
}
}
}
}
- Click Refresh to connect.
Config file location:
- macOS:
~/.codeium/windsurf/mcp_config.json - Windows:
%USERPROFILE%\.codeium\windsurf\mcp_config.json
</td> </tr> <tr> <td align="center" width="120"><b>Claude Code</b></td> <td>
One-command install via the plugin marketplace:
/plugin marketplace add algoglide/mcp
/plugin install algoglide@algoglide
Then add your API key to .mcp.json or ~/.claude/settings.json:
{
"mcpServers": {
"algoglide": {
"command": "node",
"args": ["/path/to/algoglide/mcp/server/index.js"],
"env": {
"ALGOGLIDE_API_KEY": "sk_...",
"ALGOGLIDE_BASE_URL": "https://api.algoglide.com"
}
}
}
}
</td> </tr> <tr> <td align="center" width="120"><b>Any MCP editor</b></td> <td>
The server uses standard stdio transport and works with any MCP-compatible client:
{
"mcpServers": {
"algoglide": {
"command": "npx",
"args": ["-y", "@algoglide/mcp-server"],
"env": {
"ALGOGLIDE_API_KEY": "sk_...",
"ALGOGLIDE_BASE_URL": "https://api.algoglide.com"
}
}
}
}
</td> </tr> </table>
Tools
| Tool | Description |
|---|---|
list_deployments |
List all deployed agents and their live status |
get_deployment |
Get details and recent signals for a specific agent |
create_deployment |
Deploy a new trading agent from a template |
update_deployment |
Update agent code or configuration |
delete_deployment |
Remove a deployment |
run_backtest |
Run a strategy backtest over historical market data |
get_backtest_results |
Fetch results from a completed backtest |
validate_strategy |
Validate strategy code for syntax and structure errors |
list_markets |
Browse live prediction markets |
get_market |
Get current price, volume, and metadata for a market |
get_analytics |
Fetch PnL curves, drawdown, fill quality, and metrics |
get_positions |
View open positions across all deployments |
get_fills |
View recent order fills |
list_webhooks |
List registered webhooks |
create_webhook |
Register a new webhook endpoint |
Example prompts
Deploy a new momentum strategy on ETH/BTC markets and run a 30-day backtest
Show me the PnL and drawdown for all my active agents this month
Find prediction markets about the Fed rate decision and check my current positions
Validate this strategy code and fix any issues before deploying
Environment variables
| Variable | Required | Default | Description |
|---|---|---|---|
ALGOGLIDE_API_KEY |
Yes | — | Your API key from algoglide.com/app/api-keys |
ALGOGLIDE_BASE_URL |
No | https://api.algoglide.com |
Override for self-hosted deployments |
Run locally
git clone https://github.com/algoglide/mcp
cd mcp
npm install
ALGOGLIDE_API_KEY=sk_... node server/index.js
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.