Foundry MCP code mode is answering right now. Last checked 14 min ago.
Code mode (preview): the AI writes a script against a typed foundry.* API and runs it in a sandbox.
Today is the operative word: we check Foundry MCP code mode every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 14 min ago.
claude mcp add foundry-code --transport http https://foundry-mcp.com/mcp/code
{
"mcpServers": {
"foundry-code": {
"url": "https://foundry-mcp.com/mcp/code"
}
}
}
[mcp_servers.foundry-code]
url = "https://foundry-mcp.com/mcp/code"
{
"mcpServers": {
"foundry-code": {
"url": "https://foundry-mcp.com/mcp/code"
}
}
}
{
"mcpServers": {
"foundry-code": {
"url": "https://foundry-mcp.com/mcp/code"
}
}
}
This endpoint answered with an authorization challenge. The server is running, and it signs you in through your browser: there is no API key to paste.
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://foundry-mcp.com/mcp/code | streamable-http | sign-in | 181 ms | 14 min ago |
Disposable microVM sandboxes for AI agents: run code, read/write files, git, preview URLs.
Catch TypeScript API and OpenAPI contract drift in AI-generated code, then revalidate it in CI.
Code-review MCP: review a GitLab MR or GitHub PR against the whole codebase, not just the diff.
AI software engineer — writes code, opens PRs, reviews code, generates tests, and more.
MCP server for the Google Apps Script API: projects, code, versions, deployments and executions.
Secure code execution sandbox for Claude — run Python, JavaScript, and shell commands
Mechanical write gates, evidence receipts, and adversarial review for AI coding agents.
Checks AI-written SvGrid code against the real API, plus version-pinned Svelte 5 grid docs.
Answers built from our own checks of this server.