# KORE

The KORE MCP server for Claude Code provides 14 agent tools for model routing, context compression, code isolation, and hallucination checks.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · 832 installs
- Author: amonmaly-33
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://smithery.ai/server/amonmaly-33/kore-api
- Updated: 2026-06-30
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/mcp/kore

## What it does

This server exposes an orchestration layer designed for AI agents. The `route` tool scans an 11-provider fallback sequence to dispatch tasks to the lowest-cost LLM that satisfies quality constraints. Context size shrinks up to five times via `compress`, while `guard` and `verify` inspect model output against source files to detect ungrounded claims.

Execution safety relies on `normalize` to filter prompt injections and bad characters. Code runs inside `sandbox` with a 30-second cap and automatic file cleanup. Docker is unnecessary here. Agent memory stores vectors in Qdrant via all-MiniLM embeddings, and tools like `provenance` generate HMAC-SHA256 audit records aligned with the EU AI Act.

An API key is required and generated instantly via `POST /v1/register`. New accounts receive 500 free credits with no credit card attached. A standard six-step processing chain consumes 7 credits per execution.

## Requirements
- Remote server: `https://kore-api--amonmaly-33.run.tools`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http kore-api https://kore-api--amonmaly-33.run.tools
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add kore --url https://kore-api--amonmaly-33.run.tools
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "kore": {
            "url": "https://kore-api--amonmaly-33.run.tools"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "kore": {
            "type": "http",
            "url": "https://kore-api--amonmaly-33.run.tools"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http kore https://kore-api--amonmaly-33.run.tools
```

## When to use it
- Cut context token overhead using semantic text compression
- Dispatch inference requests to the cheapest capable model provider
- Flag hallucinations by cross-checking model drafts against source files
- Execute untrusted Python scripts safely without configuring Docker
- Produce tamper-evident HMAC-SHA256 logs for regulatory compliance

## Example prompts
- Check the generated summary against `sources.txt` with `verify` tool
- Compress this raw log text using `compress` before passing it to the context
- Run this data formatting script via `sandbox` and return the stdout

## Similar
- [setup-auditor](https://affpapa.org/en/nevibecode/skills/setup-auditor.md) — skill · 471 installs
- [config-hardener](https://affpapa.org/en/nevibecode/skills/config-hardener.md) — skill · 469 installs
- [security-audit](https://affpapa.org/en/nevibecode/skills/cloudflare-security-audit.md) — skill · 116100 installs
- [omni-compression](https://affpapa.org/en/nevibecode/skills/omni-compression.md) — skill · 1300 installs
- [ForceDream](https://affpapa.org/en/nevibecode/mcp/forcedream.md) — MCP server · 526 installs
- [context-compressor](https://affpapa.org/en/nevibecode/skills/context-compressor.md) — skill · 274 installs

---
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
