{
  "markdown": "# Sutra\n\nmcp-name: io.github.4rgon4ut/sutra\n\n**The MCP Context Engineering Engine**\n\nSutra is a Model Context Protocol (MCP) server that transforms how LLMs handle reasoning, memory, and orchestration. It provides a \"Standard Library\" of cognitive tools (Thinking Models), memory structures (Cells), and multi-agent patterns (Organs).\n\n## Installation\n\n### Using `uv` (Recommended)\n```bash\nuv tool install context-engineering-mcp\n```\n\n### Using `pip`\n```bash\npip install context-engineering-mcp\n```\n\n## Configuration\n\nSelect your agent below and copy-paste the config.\n\n<details>\n<summary>Claude Desktop</summary>\n\nAdd to `claude_desktop_config.json`:\n```json\n{\n  \"mcpServers\": {\n    \"sutra\": {\n      \"command\": \"uv\",\n      \"args\": [\"tool\", \"run\", \"context-engineering-mcp\"]\n    }\n  }\n}\n```\n</details>\n\n<details>\n<summary>Claude Code</summary>\n\nRun this in your terminal:\n```bash\nclaude mcp add sutra uv tool run context-engineering-mcp\n```\n</details>\n\n<details>\n<summary>Aider</summary>\n\nRun aider with the mcp flag:\n```bash\naider --mcp \"uv tool run context-engineering-mcp\"\n```\nOr add to `.aider.conf.yml`:\n```yaml\nmcp: [\"uv tool run context-engineering-mcp\"]\n```\n</details>\n\n<details>\n<summary>Gemini CLI</summary>\n\nAdd to `~/.gemini/settings.json`:\n```json\n{\n  \"mcpServers\": {\n    \"sutra\": {\n      \"command\": \"uv\",\n      \"args\": [\"tool\", \"run\", \"context-engineering-mcp\"]\n    }\n  }\n}\n```\n</details>\n\n<details>\n<summary>Cursor / Windsurf</summary>\n\nIn MCP settings, add a new server:\n- **Name**: Sutra\n- **Type**: command\n- **Command**: `uv tool run context-engineering-mcp`\n</details>\n\n<details>\n<summary>Codex</summary>\n\nAdd to your config (TOML):\n```toml\n[mcp_servers.sutra]\ncommand = \"uv\"\nargs = [\"tool\", \"run\", \"context-engineering-mcp\"]\n```\n</details>\n\n## Core Features (v0.1.0)\n\n### 1. The Gateway (Router)\nSutra automatically analyzes your request to decide the best strategy:\n- **YOLO Mode**: For immediate tasks (\"Fix this bug\"), it routes to specific cognitive tools.\n- **Constructor Mode**: For system design (\"Build a bot\"), it routes to the Architect.\n\n### 2. The Architect\nGenerates blueprints for custom agents, combining:\n- **Thinking Models**: `understand_question`, `verify_logic`, `backtracking`, `symbolic_abstract`.\n- **Memory Cells**: `key_value` (State), `windowed` (Short-term), `episodic` (Long-term).\n- **Organs**: `debate_council` (Multi-perspective), `research_synthesis` (Deep Dive).\n\n### 3. The Librarian\nA manual discovery tool (`get_technique_guide`) that lets you or the agent browse the full catalog of Context Engineering techniques.\n\n## Development\n\n**Requirements**: Python 3.10+, `uv` (optional but recommended).\n\n1. Clone the repo:\n   ```bash\n   git clone https://github.com/4rgon4ut/sutra.git\n   cd sutra\n   ```\n2. Install dependencies:\n   ```bash\n   uv sync --all-extras\n   # OR\n   pip install -e \".[dev]\"\n   ```\n3. Run tests:\n   ```bash\n   pytest\n   ```\n\n## License\nMIT",
  "bytes": 2915,
  "sha": "81d2ee196d161aad7e7047a29c794b0ff2d0dcf94cfe0f43681775157165647b",
  "repo_slug": "4rgon4ut/sutra",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_4rgon4ut_sutra_10652953/readme"
}