# Santismm Knowledge — Harness Engineering, Agentic AI & Governance

This MCP server lets an agent search Santismm knowledge, Harness Engineering material, and Homeric Atlas data. Use it to explore agent architecture and AI governance.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 1
- Author: santismm
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/santismm/santismm-knowledge-mcp
- Updated: 2026-10-18
- HTML: https://affpapa.org/en/nevibecode/mcp/santismm-knowledge-harness-engineering-agentic-ai-governance

## What it does

The server gives agents read-only tools for searching knowledge, patterns, architectures, and governance material, along with the Harness Engineering Handbook, articles, Labs, and benchmarks. Results use structured data. The corpus covers seven languages.

To connect it to Claude Code, run both commands in the FAQ. A local run uses `npm ci && npm run build && npm start`; tools backed by files in the corpus can then work offline. Articles, Labs, and benchmarks call APIs over HTTPS. The npm package contains a snapshot from its release, while the hosted endpoint keeps updating, so use the endpoint when current content matters.

## Requirements
- Remote server: `https://santismm.com/mcp`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http knowledge https://santismm.com/mcp
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add santismm-knowledge-harness-engineering-agentic-ai-governance --url https://santismm.com/mcp
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "santismm-knowledge-harness-engineering-agentic-ai-governance": {
            "url": "https://santismm.com/mcp"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "santismm-knowledge-harness-engineering-agentic-ai-governance": {
            "type": "http",
            "url": "https://santismm.com/mcp"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http santismm-knowledge-harness-engineering-agentic-ai-governance https://santismm.com/mcp
```

## When to use it
- look up Harness Engineering guidance
- compare approaches to AI agent architecture
- explore AI governance material
- retrieve Homeric Atlas data

## Example prompts
- Find guidance on Harness Engineering that applies to this project.
- Compare the available material on AI agent architecture.
- Show Homeric Atlas data relevant to my question.

## Similar
- [REA](https://affpapa.org/en/nevibecode/mcp/rea.md) — MCP server · ★ 392262
- [GitHub](https://affpapa.org/en/nevibecode/mcp/github.md) — MCP server · ★ 33989
- [Netdata](https://affpapa.org/en/nevibecode/mcp/netdata.md) — MCP server · ★ 81163
- [browser-use](https://affpapa.org/en/nevibecode/mcp/browser-use.md) — MCP server · ★ 119231
- [Codebase Memory](https://affpapa.org/en/nevibecode/mcp/codebase-memory.md) — MCP server · ★ 47577
- [mcp-server](https://affpapa.org/en/nevibecode/mcp/mcp-server.md) — MCP server · ★ 43902

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md