# fortemi-react MCP server

> Enables AI clients to perform local-first knowledge management using a browser-based PostgreSQL engine with semantic search and SKOS tagging.

- Repository: https://github.com/Fortemi/fortemi-react
- Page: https://hostedmcp.org/servers/fortemi/fortemi-react
- Transport: stdio
- Stars: 5
- License: AGPL-3.0

## Install

### Claude Code

```sh
claude mcp add fortemi-react -- npx -y @fortemi/core
```

### Cursor (`~/.cursor/mcp.json`)

```json
{
  "mcpServers": {
    "fortemi-react": {
      "command": "npx",
      "args": [
        "-y",
        "@fortemi/core"
      ]
    }
  }
}
```

### VS Code (`.vscode/mcp.json`)

```json
{
  "servers": {
    "fortemi-react": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@fortemi/core"
      ]
    }
  }
}
```

### VS Code CLI

```sh
code --add-mcp '{"name":"fortemi-react","type":"stdio","command":"npx","args":["-y","@fortemi/core"]}'
```

### Claude Desktop (`claude_desktop_config.json`)

```json
{
  "mcpServers": {
    "fortemi-react": {
      "command": "npx",
      "args": [
        "-y",
        "@fortemi/core"
      ]
    }
  }
}
```

### Codex

```sh
codex mcp add fortemi-react -- npx -y @fortemi/core
```

### Codex config.toml (`~/.codex/config.toml`)

```toml
[mcp_servers.fortemi-react]
command = "npx"
args = ["-y", "@fortemi/core"]
```

### Gemini CLI

```sh
gemini mcp add -s user fortemi-react npx -- -y @fortemi/core
```

### Gemini settings.json (`~/.gemini/settings.json`)

```json
{
  "mcpServers": {
    "fortemi-react": {
      "command": "npx",
      "args": [
        "-y",
        "@fortemi/core"
      ]
    }
  }
}
```

## FAQ

### Does this require a backend server?

No, it is a local-first solution that runs the schema entirely in the browser with no backend or account required.

### What kind of search capabilities are available?

It supports full-text search using PostgreSQL tsvector, as well as hybrid semantic search using pgvector HNSW and BM25 reciprocal-rank fusion.

### Can I use my own AI models?

Yes, you can use local providers like Ollama, LM Studio, or llama.cpp, or route to a provider you control.

### How is data stored in the browser?

It uses PGlite-backed local storage with support for OPFS, IndexedDB, and memory persistence modes.
