Native Soil is answering right now. Last checked 2 min ago.
Save an AI chat's working state, load it in any other model or provider. Verified, secret-safe.
Today is the operative word: we check Native Soil 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 2 min ago.
claude mcp add soil --transport http https://mcp.nativesoil.dev/mcp/soil
{
"mcpServers": {
"soil": {
"url": "https://mcp.nativesoil.dev/mcp/soil"
}
}
}
[mcp_servers.soil]
url = "https://mcp.nativesoil.dev/mcp/soil"
{
"mcpServers": {
"soil": {
"url": "https://mcp.nativesoil.dev/mcp/soil"
}
}
}
{
"mcpServers": {
"soil": {
"url": "https://mcp.nativesoil.dev/mcp/soil"
}
}
}
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://mcp.nativesoil.dev/mcp/soil | streamable-http | sign-in | 166 ms | 2 min ago |
Git-native project memory for AI coding agents: Markdown source of truth, reviewable, secret-safe.
Deterministic security scanning, no model or API key, plus offline-verifiable proof a fix worked.
An MCP server that provides interaction with StackHawk's security scanning platform.
Verified cloud storage provider facts: prices, storage, encryption. Dated and source-cited.
Email safety for AI agents: scan inbound for prompt-injection/phishing + outbound for secret leaks.
Autonomous on-chain security detective for Base, exposed over the Model Context Protocol (MCP).
Pre-install security scanner for AI agent skills (local stdio MCP). Offline static scan; no upload.
Zero-knowledge MCP secrets vault for AI agents: secrets injected at runtime, never seen by the model
Answers built from our own checks of this server.