feat: Add data visualization for Anthropic

.github/workflows/dockerhub.yml

@@ -1,51 +1,48 @@
-name: build | Build and Push Docker Image to DockerHub
+name: build | Build and Push Docker Image to dockerhub
 
 on:
   push:
     branches:
+      - dev
       - main
 
 jobs:
   docker-build-and-push:
     runs-on: ubuntu-latest
 
     steps:
-    - name: Checkout repository
-      uses: actions/checkout@v4
-
-    - name: Set up Docker Buildx
-      uses: docker/setup-buildx-action@v3
-
-    - name: Log in to Docker Hub
-      uses: docker/login-action@v3
-      with:
-        username: ${{ secrets.DOCKER_USERNAME }}
-        password: ${{ secrets.DOCKER_PASSWORD }}
-
-    - name: Extract Git information
-      id: git-info
-      run: |
-        echo "BRANCH_NAME=${GITHUB_REF_NAME}" >> "$GITHUB_ENV"
-        echo "COMMIT_SHA=${GITHUB_SHA::7}" >> "$GITHUB_ENV"
-
-    - name: Build and Push Docker Image
-      run: |
-        IMAGE_NAME=cognee/cognee
-        TAG_VERSION="${BRANCH_NAME}-${COMMIT_SHA}"
-
-        echo "Building image: ${IMAGE_NAME}:${TAG_VERSION}"
-        docker buildx build \
-          --platform linux/amd64,linux/arm64 \
-          --push \
-          --tag "${IMAGE_NAME}:${TAG_VERSION}" \
-          --tag "${IMAGE_NAME}:latest" \
-          .
-
-    - name: Verify pushed Docker images
-      run: |
-       # Verify both platform variants
-       for PLATFORM in "linux/amd64" "linux/arm64"; do
-         echo "Verifying image for $PLATFORM..."
-         docker buildx imagetools inspect "${IMAGE_NAME}:${TAG_VERSION}" --format "{{.Manifest.$PLATFORM.Digest}}"
-       done
-       echo "Successfully verified images in Docker Hub"
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Log in to Docker Hub
+        uses: docker/login-action@v3
+        with:
+          username: ${{ secrets.DOCKER_USERNAME }}
+          password: ${{ secrets.DOCKER_PASSWORD }}
+
+      - name: Extract metadata
+        id: meta
+        uses: docker/metadata-action@v5
+        with:
+          images: cognee/cognee
+          tags: |
+            type=ref,event=branch
+            type=sha,prefix={{branch}}-
+            type=raw,value=latest,enable={{is_default_branch}}
+
+      - name: Build and push
+        uses: docker/build-push-action@v5
+        with:
+          context: .
+          platforms: linux/amd64,linux/arm64
+          push: true
+          tags: ${{ steps.meta.outputs.tags }}
+          labels: ${{ steps.meta.outputs.labels }}
+          cache-from: type=registry,ref=cognee/cognee:buildcache
+          cache-to: type=registry,ref=cognee/cognee:buildcache,mode=max
+
+      - name: Image digest
+        run: echo ${{ steps.build.outputs.digest }}

cognee-mcp/README.md

@@ -37,7 +37,15 @@ source .venv/bin/activate
 4. Add the new server to your Claude config:
 
 The file should be located here: ~/Library/Application\ Support/Claude/
+```
+cd ~/Library/Application\ Support/Claude/
+```
 You need to create claude_desktop_config.json in this folder if it doesn't exist
+Make sure to add your paths and LLM API key to the file bellow
+Use your editor of choice, for example Nano:
+```
+nano claude_desktop_config.json
+```
 
 ```
 
@@ -83,3 +91,17 @@ npx -y @smithery/cli install cognee --client claude
 
 Define cognify tool in server.py
 Restart your Claude desktop.
+
+
+To use debugger, run:
+```bash
+npx @modelcontextprotocol/inspector uv --directory /Users/name/folder run cognee
+```
+
+To apply new changes while development you do:
+
+1. Poetry lock in cognee folder
+2. uv sync --dev --all-extras --reinstall 
+3. npx @modelcontextprotocol/inspector uv --directory /Users/vasilije/cognee/cognee-mcp run cognee
+
+

cognee-mcp/cognee_mcp/server.py

@@ -3,13 +3,17 @@
 import asyncio
 from contextlib import redirect_stderr, redirect_stdout
 
+from sqlalchemy.testing.plugin.plugin_base import logging
+
 import cognee
 import mcp.server.stdio
 import mcp.types as types
 from cognee.api.v1.search import SearchType
 from cognee.shared.data_models import KnowledgeGraph
 from mcp.server import NotificationOptions, Server
 from mcp.server.models import InitializationOptions
+from PIL import Image
+
 
 server = Server("cognee-mcp")
 
@@ -87,9 +91,45 @@ async def handle_list_tools() -> list[types.Tool]:
                 },
             },
         ),
+        types.Tool(
+            name="visualize",
+            description="Visualize the knowledge graph.",
+            inputSchema={
+                "type": "object",
+                "properties": {
+                    "query": {"type": "string"},
+                },
+            },
+        ),
     ]
 
 
+def get_freshest_png(directory: str) -> Image.Image:
+    if not os.path.exists(directory):
+        raise FileNotFoundError(f"Directory {directory} does not exist")
+
+    # List all files in 'directory' that end with .png
+    files = [f for f in os.listdir(directory) if f.endswith(".png")]
+    if not files:
+        raise FileNotFoundError("No PNG files found in the given directory.")
+
+    # Sort by integer value of the filename (minus the '.png')
+    # Example filename: 1673185134.png -> integer 1673185134
+    try:
+        files_sorted = sorted(files, key=lambda x: int(x.replace(".png", "")))
+    except ValueError as e:
+        raise ValueError("Invalid PNG filename format. Expected timestamp format.") from e
+
+    # The "freshest" file has the largest timestamp
+    freshest_filename = files_sorted[-1]
+    freshest_path = os.path.join(directory, freshest_filename)
+
+    # Open the image with PIL and return the PIL Image object
+    try:
+        return Image.open(freshest_path)
+    except (IOError, OSError) as e:
+        raise IOError(f"Failed to open PNG file {freshest_path}") from e
+
 @server.call_tool()
 async def handle_call_tool(
     name: str, arguments: dict | None
@@ -154,6 +194,22 @@ async def handle_call_tool(
                         text="Pruned",
                     )
                 ]
+
+    elif name == "visualize":
+        with open(os.devnull, "w") as fnull:
+            with redirect_stdout(fnull), redirect_stderr(fnull):
+                try:
+                    result = await cognee.visualize_graph()
+                    results = retrieved_edges_to_string(result)
+
+                    return [
+                        types.TextContent(
+                            type="text",
+                            text=results,
+                        )
+                    ]
+                except (FileNotFoundError, IOError, ValueError) as e:
+                    raise ValueError(f"Failed to create visualization: {str(e)}")
     else:
         raise ValueError(f"Unknown tool: {name}")
 

cognee-mcp/pyproject.toml

@@ -4,6 +4,7 @@ version = "0.1.0"
 description = "A MCP server project"
 readme = "README.md"
 requires-python = ">=3.10"
+
 dependencies = [
     "mcp>=1.1.1",
     "openai==1.59.4",
@@ -51,7 +52,7 @@ dependencies = [
     "pydantic-settings>=2.2.1,<3.0.0",
     "anthropic>=0.26.1,<1.0.0",
     "sentry-sdk[fastapi]>=2.9.0,<3.0.0",
-    "fastapi-users[sqlalchemy]", # Optional
+    "fastapi-users[sqlalchemy]>=14.0.0", # Optional
     "alembic>=1.13.3,<2.0.0",
     "asyncpg==0.30.0", # Optional
     "pgvector>=0.3.5,<0.4.0", # Optional
@@ -91,4 +92,4 @@ dev = [
 ]
 
 [project.scripts]
-cognee = "cognee_mcp:main"
+cognee = "cognee_mcp:main"

cognee/__init__.py

@@ -4,7 +4,7 @@
 from .api.v1.datasets.datasets import datasets
 from .api.v1.prune import prune
 from .api.v1.search import SearchType, get_search_history, search
-from .api.v1.visualize import visualize
+from .api.v1.visualize import visualize_graph
 from .shared.utils import create_cognee_style_network_with_logo
 
 # Pipelines