# Contextful MCP server

> Provides a local search engine and memory layer for coding agents to efficiently retrieve, compress, and remember project context.

- Repository: https://github.com/Inferensys/contextful
- Page: https://hostedmcp.org/servers/inferensys/contextful
- Transport: stdio
- Stars: 6
- License: MIT
- Latest version: 0.1.0

## Install

### Claude Code

```sh
claude mcp add contextful -- npx -y @inferensys/contextful
```

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

```json
{
  "mcpServers": {
    "contextful": {
      "command": "npx",
      "args": [
        "-y",
        "@inferensys/contextful"
      ]
    }
  }
}
```

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

```json
{
  "servers": {
    "contextful": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@inferensys/contextful"
      ]
    }
  }
}
```

### VS Code CLI

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

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

```json
{
  "mcpServers": {
    "contextful": {
      "command": "npx",
      "args": [
        "-y",
        "@inferensys/contextful"
      ]
    }
  }
}
```

### Codex

```sh
codex mcp add contextful -- npx -y @inferensys/contextful
```

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

```toml
[mcp_servers.contextful]
command = "npx"
args = ["-y", "@inferensys/contextful"]
```

### Gemini CLI

```sh
gemini mcp add -s user contextful npx -- -y @inferensys/contextful
```

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

```json
{
  "mcpServers": {
    "contextful": {
      "command": "npx",
      "args": [
        "-y",
        "@inferensys/contextful"
      ]
    }
  }
}
```

## Tools (7)

- `context_pack`
- `search_code`
- `trace_path`
- `impact_analysis`
- `why_changed`
- `recall_memory`
- `write_lesson`

## FAQ

### What is Contextful?

Contextful is a runtime contextual layer and local search engine for agents that helps them find, compress, cite, and remember project context.

### Is my code sent to external servers?

No, the tool is local-only and does not upload source code or call external embedding APIs.

### How does the memory system work?

Agents can store lessons and project facts in a memory ledger that requires evidence references from files, symbols, or commits to prevent loose notes.

### Which coding tools are supported?

It integrates with Codex, Claude Code, Cursor, Windsurf, GitHub Copilot, VS Code, Cline, Roo Code, Continue, and Zed.
