Compaction for local models that actually fires and never bricks the session. OpenAI-compatible proxy + DeepSeek Harness engine.
Setup
Choose your client, copy the config, then fill in any required environment variables.
claude mcp add context-guardian -- uvx context-guardian~/.codex/config.toml
[mcp_servers.context-guardian]
command = "uvx"
args = ["context-guardian"]
# codex mcp add context-guardian -- uvx context-guardian~/.cursor/mcp.json
{
"mcpServers": {
"context-guardian": {
"command": "uvx",
"args": [
"context-guardian"
]
}
}
}.vscode/mcp.json
{
"servers": {
"context-guardian": {
"type": "stdio",
"command": "uvx",
"args": [
"context-guardian"
]
}
}
}~/.gemini/settings.json
{
"mcpServers": {
"context-guardian": {
"command": "uvx",
"args": [
"context-guardian"
]
}
}
}claude_desktop_config.json
{
"mcpServers": {
"context-guardian": {
"command": "uvx",
"args": [
"context-guardian"
]
}
}
}.trae/mcp.json
{
"mcpServers": {
"context-guardian": {
"command": "uvx",
"args": [
"context-guardian"
]
}
}
}