Bkr instructions

.dockerignore

@@ -0,0 +1,19 @@
+**/__pycache__/
+**/.git
+**/.github
+**/.mypy_cache
+**/.pytest_cache
+**/.vscode
+**/.idea
+**/.coverage
+**/.DS_Store
+**/.python-version
+**/*.bak
+**/*.pyc
+**/node_modules/
+
+tests/
+docs/
+install/
+venv
+.venv

.github/copilot-instructions.md

@@ -0,0 +1 @@
+LLMS.md

.pre-commit-config.yaml

@@ -0,0 +1,13 @@
+repos:
+  - repo: https://github.com/pre-commit/mirrors-mypy
+    rev: v1.15.0
+    hooks:
+      - id: mypy
+        name: mypy
+        args: [--show-error-codes src/]
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.12.4
+    hooks:
+      - id: ruff-format
+      - id: ruff
+        args: [--fix]

CLAUDE.md

@@ -0,0 +1 @@
+LLMS.md

GEMINI.md

@@ -0,0 +1 @@
+LLMS.md

GPT.md

@@ -0,0 +1 @@
+LLMS.md

LLMS.md

@@ -0,0 +1,49 @@
+# LLM Context Guide for Infrahub MCP Server
+
+Infrahub MCP Server connects your AI assistants to Infrahub using the open MCP standard—so agents can read and (optionally) change your infra state through a consistent, audited, human-approved interface.
+
+## Key Directories
+
+```
+infrahub-mcp/
+├── docs/                       # Documentation (UPDATE FOR CHANGES)
+├── src/                        # Python Code
+│   └── infrahub_mcp/
+│       ├── __init__.py
+|       ├── branch.py
+|       ├── constants.py
+|       ├── gql.py
+|       ├── nodes.py
+|       ├── prompts/
+|       │   └── main.md
+|       ├── schema.py
+|       ├── server.py
+|       └── utils.py
+└── tests/                      # Python/integration tests
+```
+
+## Code Standards
+
+### Python Backend
+
+- **Type hints required** for all new code
+- **MyPy compliant** - run `pre-commit run mypy`
+- **Ruf compliant**- run `pre-commit run ruff`
+- **pytest** for testing
+
+## Documentation Requirements
+
+- **docs/**: Update for any user-facing changes
+- **Docstrings**: Required for new functions/classes
+
+## Test Utilities
+
+### Running Tests
+
+## Platform-Specific Instructions
+
+- **[CLAUDE.md](CLAUDE.md)** - For Claude/Anthropic tools
+- **[.github/copilot-instructions.md](.github/copilot-instructions.md)** - For GitHub Copilot
+- **[GEMINI.md](GEMINI.md)** - For Google Gemini tools
+- **[GPT.md](GPT.md)** - For OpenAI/ChatGPT tools
+- **[.cursor/rules/dev-standard.mdc](.cursor/rules/dev-standard.mdc)** - For Cursor editor

README.md

@@ -1,150 +1,19 @@
-# Infrahub MCP Server
+<!-- markdownlint-disable -->
+![Infrahub Logo](https://assets-global.website-files.com/657aff4a26dd8afbab24944b/657b0e0678f7fd35ce130776_Logo%20INFRAHUB.svg)
+<!-- markdownlint-restore -->
 
-MCP server to interact with Infrahub
+# Infrahub MCP
 
-## Requirements
+[Infrahub](https://github.com/opsmill/infrahub) by [OpsMill](https://opsmill.com) acts as a central hub to manage the data, templates and playbooks that powers your infrastructure. At its heart, Infrahub is built on 3 fundamental pillars:
 
-- Python 3.13+
-- fastmcp
-- infrahub_sdk
+- **A Flexible Schema**: A model of the infrastructure and the relation between the objects in the model, that's easily extensible.
+- **Version Control**: Natively integrated into the graph database which opens up some new capabilities like branching, diffing, and merging data directly in the database.
+- **Unified Storage**: By combining a graph database and git, Infrahub stores data and code needed to manage the infrastructure.
 
+## Introduction
 
-## Installation
+Infrahub MCP Server connects your AI assistants to Infrahub using the open MCP standard—so agents can read and (optionally) change your infra state through a consistent, audited, human-approved interface.
 
-1. **Clone the repo**
-
-    ```bash
-    git clone https://github.com/opsmill/infrahub-mcp-server.git
-    cd infrahub-mcp-server
-    ```
-
-2. **Install dependencies**
-
-    ```bash
-    uv sync
-    ```
-
-3. **Run the server**
-
-    ```bash
-    uv run fastmcp run src/infrahub_mcp_server/server.py:mcp
-    ```
-
-
-## Configuration
-
-Set the following environment variables as needed:
-
-| Variable            | Description                         | Default                  |
-|---------------------|-------------------------------------|--------------------------|
-| `INFRAHUB_ADDRESS`  | URL of your Infrahub instance       | `http://localhost:8000`  |
-| `INFRAHUB_API_TOKEN`| API token for Infrahub              | `placeholder UUID`       |
-| `MCP_HOST`          | Host for the web server             | `0.0.0.0`                |
-| `MCP_PORT`          | Port for the web server             | `8001`                   |
-
-
-## Usage
-
-### HTTP API mode
-
-```bash
-poetry run python server.py --web
-```
-
-Send a POST request to the root endpoint (/):
-
-```bash
-curl -X POST http://localhost:8001/ \\
-  -H "Content-Type: application/json" \\
-  -d '{
-    "tool": "infrahub_get_nodes",
-    "params": {
-      "kind": "Tag",
-      "filters": { "any": "blue" },
-      "partial_match": false
-    }
-  }'
-```
-
-### CLI / stdin-stdout mode
-
-```bash
-uv run fastmcp run src/infrahub_mcp_server/server.py:mcp
-```
-
-Then send JSON-RPC requests to stdin:
-
-```bash
-{"jsonrpc":"2.0","method":"tools/discover","params":{}}
-{"jsonrpc":"2.0","method":"tools/call","params":{"name": "infrahub_get_nodes","arguments": {"kind":"Router","filters": {"location":"eu-west"}}}}
-```
-
-Process one-shot request with --oneshot:
-
-```bash
-echo '{"method":"tools/discover"}' | poetry run python server.py --oneshot
-```
-
-## MCP Methods
-
-### infrahub_get_nodes
-Retrieve nodes of a given kind.
-
-Params:
-
-- kind (string, required): node kind (e.g. "Router")
-- branch (string): branch name
-- filters (object): key/value filters
-- simple keys → <key>__value
-- list values → <key>__values
-- use "any" to search across all attributes
-- partial_match (boolean): true for substring matches
-- infrahub_url (string): override via param
-- infrahub_api_token (string): override via param
-
-Response:
-
-```json
-{
-  "success": true,
-  "count": 5,
-  "nodes": [ { ... }, ... ]
-}
-```
-
-### infrahub_get_schema
-
-Retrieve schema details.
-
-Params:
-
-- kind (string): kind name; omit to fetch all schemas
-- branch (string)
-- exclude_profiles (boolean)
-- exclude_templates (boolean)
-- infrahub_url (string)
-- infrahub_api_token (string)
-
-Response (single kind):
-
-```json
-{
-  "success": true,
-  "kind": "Tag",
-  "namespace": "...",
-  "name": "...",
-  "attributes": [ { "name": "...", "type": "...", "description": "..." }, ... ],
-  "relationships": [ { "name": "...", "rel_kind": "...", "cardinality": "...", "description": "..." }, ... ]
-}
-```
-
-Response (all schemas):
-
-```json
-{
-  "success": true,
-  "count": 12,
-  "schemas": [ { ... }, ... ]
-}
-```
+## Using Infrahub MCP
 
+Documentation for using Infrahub Sync is available [here](https://docs.infrahub.app/mcp/)