| Name | mcp-memgraph JSON |
| Version |
0.1.4
JSON |
| download |
| home_page | None |
| Summary | MCP integration and utilities for Memgraph MCP server |
| upload_time | 2025-08-06 11:35:41 |
| maintainer | None |
| docs_url | None |
| author | None |
| requires_python | >=3.13 |
| license | MIT |
| keywords |
graph
integration
mcp
memgraph
toolkit
|
| VCS |
 |
| bugtrack_url |
|
| requirements |
No requirements were recorded.
|
| Travis-CI |
No Travis.
|
| coveralls test coverage |
No coveralls.
|
# 🚀 Memgraph MCP Server
Memgraph MCP Server is a lightweight server implementation of the Model Context Protocol (MCP) designed to connect Memgraph with LLMs.
## Run Memgraph MCP server with Claude
1. Install [`uv`](https://docs.astral.sh/uv/getting-started/installation/)
2. Install [Claude for Desktop](https://claude.ai/download).
3. Add the Memgraph server to Claude config
You can do it in the UI, by opening your Claude desktop app navigate to `Settings`, under the `Developer` section, click on `Edit Config` and add the
following content:
```
{
"mcpServers": {
"mpc-memgraph": {
"command": "uv",
"args": [
"run",
"--with",
"mcp-memgraph",
"--python",
"3.13",
"mcp-memgraph"
]
}
}
}
```
Or you can open the config file in your favorite text editor. The location of the config file depends on your operating system:
**MacOS/Linux**
```
~/Library/Application\ Support/Claude/claude_desktop_config.json
```
**Windows**
```
%APPDATA%/Claude/claude_desktop_config.json
```
> [!NOTE]
> You may need to put the full path to the uv executable in the command field. You can get this by running `which uv` on MacOS/Linux or `where uv` on Windows. Make sure you pass in the absolute path to your server.
### Chat with the database
1. Run Memgraph MAGE:
```
docker run -p 7687:7687 memgraph/memgraph-mage --schema-info-enabled=True
```
The `--schema-info-enabled` configuration setting is set to `True` to allow LLM to run `SHOW SCHEMA INFO` query.
2. Open Claude Desktop and see the Memgraph tools and resources listed. Try it out! (You can load dummy data from [Memgraph Lab](https://memgraph.com/docs/data-visualization) Datasets)
## 🔧Tools
The Memgraph MCP Server exposes the following tools over MCP. Each tool runs a Memgraph‐toolbox operation and returns a list of records (dictionaries).
### run_query(query: str)
Run any arbitrary Cypher query against the connected Memgraph database.
Parameters:
- `query`: A valid Cypher query string.
### get_configuration()
Fetch the current Memgraph configuration settings.
Equivalent to running `SHOW CONFIGURATION`.
### get_index()
Retrieve information about existing indexes.
Equivalent to running `SHOW INDEX INFO`.
### get_constraint()
Retrieve information about existing constraints.
Equivalent to running `SHOW CONSTRAINT INFO`.
### get_schema()
Fetch the graph schema (labels, relationships, property keys).
Equivalent to running `SHOW SCHEMA INFO`.
### get_storage()
Retrieve storage usage metrics for nodes, relationships, and properties.
Equivalent to running `SHOW STORAGE INFO`.
### get_triggers()
List all database triggers.
Equivalent to running `SHOW TRIGGERS`.
### get_betweenness_centrality()
Compute betweenness centrality on the entire graph.
Uses `BetweennessCentralityTool` under the hood.
### get_page_rank()
Compute PageRank scores for all nodes.
Uses `PageRankTool` under the hood.
## 🐳 Run Memgraph MCP server with Docker
### Building Memgraph MCP image
To build the Docker image using your local `memgraph-toolbox` code, run from the root of the monorepo:
```bash
cd /path/to/ai-toolkit
docker build -f integrations/mcp-memgraph/Dockerfile -t mcp-memgraph:latest .
```
This will include your local `memgraph-toolbox` and install it inside the image.
### Running the Docker image
#### 1. Streamable HTTP mode (recommended for most users)
To connect to local Memgraph containers, by default the MCP server will be available at `http://localhost:8000/mcp/`:
```bash
docker run --rm mcp-memgraph:latest
```
#### 2. Stdio mode (for integration with MCP stdio clients)
Configure your MCP host to run the docker command and utilize stdio:
```bash
docker run --rm -i -e MCP_TRANSPORT=stdio mcp-memgraph:latest
```
> 📄 Note: By default, the server will connect to a Memgraph instance running on localhost docker network `bolt://host.docker.internal:7687`. If you have a Memgraph instance running on a different host or port, you can specify it using environment variables.
#### 3. Custom Memgraph connection (external instance, no host network)
To avoid using host networking, or to connect to an external Memgraph instance:
```bash
docker run --rm \
-p 8000:8000 \
-e MEMGRAPH_URL=bolt://memgraph:7687 \
-e MEMGRAPH_USER=myuser \
-e MEMGRAPH_PASSWORD=password \
mcp-memgraph:latest
```
## ⚙️ Configuration
### Environment Variables
The following environment variables can be used to configure the Memgraph MCP Server, whether running with Docker or directly (e.g., with `uv` or `python`).
- `MEMGRAPH_URL`: The Bolt URL of the Memgraph instance to connect to. Default: `bolt://host.docker.internal:7687`
- The default value allows you to connect to a Memgraph instance running on your host machine from within the Docker container.
- `MEMGRAPH_USER`: The username for authentication. Default: `memgraph`
- `MEMGRAPH_PASSWORD`: The password for authentication. Default: empty
- `MEMGRAPH_DATABASE`: The database name to connect to. Default: `memgraph`
- `MCP_TRANSPORT`: The transport protocol to use. Options: `http` (default), `stdio`
You can set these environment variables in your shell, in your Docker run command, or in your deployment environment.
### Connecting from VS Code (HTTP server)
If you are using VS Code MCP extension or similar, your configuration for an HTTP server would look like:
```json
{
"servers": {
"mcp-memgraph-http": {
"url": "http://localhost:8000/mcp/"
}
}
}
```
> **Note:** The URL must end with `/mcp/`.
---
#### Running the Docker image in Visual Studio Code using stdio
You can also run the server using stdio for integration with MCP stdio clients:
1. Open Visual Studio Code, open Command Palette (Ctrl+Shift+P or Cmd+Shift+P on Mac), and select `MCP: Add server...`.
2. Choose `Command (stdio)`
3. Enter `docker` as the command to run.
4. For Server ID enter `mcp-memgraph`.
5. Choose "User" (adds to user-space `settings.json`) or "Workspace" (adds to `.vscode/mcp.json`).
When the settings open, enhance the args as follows:
```json
{
"servers": {
"mcp-memgraph": {
"type": "stdio",
"command": "docker",
"args": [
"run",
"--rm",
"-i",
"-e", "MCP_TRANSPORT=stdio",
"mcp-memgraph:latest"
]
}
}
}
```
To connect to a remote Memgraph instance with authentication, add environment variables to the `args` list:
```json
{
"servers": {
"mcp-memgraph": {
"type": "stdio",
"command": "docker",
"args": [
"run",
"--rm",
"-i",
"-e", "MCP_TRANSPORT=stdio",
"-e", "MEMGRAPH_URL=bolt://memgraph:7687",
"-e", "MEMGRAPH_USER=myuser",
"-e", "MEMGRAPH_PASSWORD=mypassword",
"mcp-memgraph:latest"
]
}
}
}
```
---
Open GitHub Copilot in Agent mode and you'll be able to interact with the Memgraph MCP server.
Raw data
{
"_id": null,
"home_page": null,
"name": "mcp-memgraph",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.13",
"maintainer_email": null,
"keywords": "graph, integration, mcp, memgraph, toolkit",
"author": null,
"author_email": "antejavor <ante.javor@memgraph.io>",
"download_url": "https://files.pythonhosted.org/packages/69/19/6670f4df4af2729a41fdfe3f8855a46c8195a941858a6a817469d717f7b7/mcp_memgraph-0.1.4.tar.gz",
"platform": null,
"description": "# \ud83d\ude80 Memgraph MCP Server\n\nMemgraph MCP Server is a lightweight server implementation of the Model Context Protocol (MCP) designed to connect Memgraph with LLMs.\n\n\n\n## Run Memgraph MCP server with Claude\n\n1. Install [`uv`](https://docs.astral.sh/uv/getting-started/installation/)\n2. Install [Claude for Desktop](https://claude.ai/download).\n3. Add the Memgraph server to Claude config\n\nYou can do it in the UI, by opening your Claude desktop app navigate to `Settings`, under the `Developer` section, click on `Edit Config` and add the\nfollowing content:\n\n```\n{\n \"mcpServers\": {\n \"mpc-memgraph\": {\n \"command\": \"uv\",\n \"args\": [\n \"run\",\n \"--with\",\n \"mcp-memgraph\",\n \"--python\",\n \"3.13\",\n \"mcp-memgraph\"\n ]\n }\n }\n}\n```\n\nOr you can open the config file in your favorite text editor. The location of the config file depends on your operating system:\n\n**MacOS/Linux**\n\n```\n~/Library/Application\\ Support/Claude/claude_desktop_config.json\n```\n\n**Windows**\n\n```\n%APPDATA%/Claude/claude_desktop_config.json\n```\n\n> [!NOTE] \n> You may need to put the full path to the uv executable in the command field. You can get this by running `which uv` on MacOS/Linux or `where uv` on Windows. Make sure you pass in the absolute path to your server.\n\n### Chat with the database\n\n1. Run Memgraph MAGE:\n ```\n docker run -p 7687:7687 memgraph/memgraph-mage --schema-info-enabled=True\n ```\n The `--schema-info-enabled` configuration setting is set to `True` to allow LLM to run `SHOW SCHEMA INFO` query.\n2. Open Claude Desktop and see the Memgraph tools and resources listed. Try it out! (You can load dummy data from [Memgraph Lab](https://memgraph.com/docs/data-visualization) Datasets)\n\n## \ud83d\udd27Tools\n\nThe Memgraph MCP Server exposes the following tools over MCP. Each tool runs a Memgraph\u2010toolbox operation and returns a list of records (dictionaries).\n\n### run_query(query: str)\n\nRun any arbitrary Cypher query against the connected Memgraph database. \nParameters:\n\n- `query`: A valid Cypher query string.\n\n### get_configuration()\n\nFetch the current Memgraph configuration settings. \nEquivalent to running `SHOW CONFIGURATION`.\n\n### get_index()\n\nRetrieve information about existing indexes. \nEquivalent to running `SHOW INDEX INFO`.\n\n### get_constraint()\n\nRetrieve information about existing constraints. \nEquivalent to running `SHOW CONSTRAINT INFO`.\n\n### get_schema()\n\nFetch the graph schema (labels, relationships, property keys). \nEquivalent to running `SHOW SCHEMA INFO`.\n\n### get_storage()\n\nRetrieve storage usage metrics for nodes, relationships, and properties. \nEquivalent to running `SHOW STORAGE INFO`.\n\n### get_triggers()\n\nList all database triggers. \nEquivalent to running `SHOW TRIGGERS`.\n\n### get_betweenness_centrality()\n\nCompute betweenness centrality on the entire graph. \nUses `BetweennessCentralityTool` under the hood.\n\n### get_page_rank()\n\nCompute PageRank scores for all nodes. \nUses `PageRankTool` under the hood.\n\n## \ud83d\udc33 Run Memgraph MCP server with Docker\n\n### Building Memgraph MCP image\n\nTo build the Docker image using your local `memgraph-toolbox` code, run from the root of the monorepo:\n\n```bash\ncd /path/to/ai-toolkit\ndocker build -f integrations/mcp-memgraph/Dockerfile -t mcp-memgraph:latest .\n```\n\nThis will include your local `memgraph-toolbox` and install it inside the image.\n\n### Running the Docker image\n\n#### 1. Streamable HTTP mode (recommended for most users)\n\nTo connect to local Memgraph containers, by default the MCP server will be available at `http://localhost:8000/mcp/`:\n\n```bash\ndocker run --rm mcp-memgraph:latest\n```\n\n#### 2. Stdio mode (for integration with MCP stdio clients)\n\nConfigure your MCP host to run the docker command and utilize stdio:\n\n```bash\ndocker run --rm -i -e MCP_TRANSPORT=stdio mcp-memgraph:latest\n```\n\n> \ud83d\udcc4 Note: By default, the server will connect to a Memgraph instance running on localhost docker network `bolt://host.docker.internal:7687`. If you have a Memgraph instance running on a different host or port, you can specify it using environment variables.\n\n#### 3. Custom Memgraph connection (external instance, no host network)\n\nTo avoid using host networking, or to connect to an external Memgraph instance:\n\n```bash\ndocker run --rm \\\n -p 8000:8000 \\\n -e MEMGRAPH_URL=bolt://memgraph:7687 \\\n -e MEMGRAPH_USER=myuser \\\n -e MEMGRAPH_PASSWORD=password \\\n mcp-memgraph:latest\n```\n\n\n## \u2699\ufe0f Configuration\n\n### Environment Variables\n\nThe following environment variables can be used to configure the Memgraph MCP Server, whether running with Docker or directly (e.g., with `uv` or `python`).\n\n- `MEMGRAPH_URL`: The Bolt URL of the Memgraph instance to connect to. Default: `bolt://host.docker.internal:7687`\n - The default value allows you to connect to a Memgraph instance running on your host machine from within the Docker container.\n- `MEMGRAPH_USER`: The username for authentication. Default: `memgraph`\n- `MEMGRAPH_PASSWORD`: The password for authentication. Default: empty\n- `MEMGRAPH_DATABASE`: The database name to connect to. Default: `memgraph`\n- `MCP_TRANSPORT`: The transport protocol to use. Options: `http` (default), `stdio`\n\nYou can set these environment variables in your shell, in your Docker run command, or in your deployment environment. \n\n### Connecting from VS Code (HTTP server)\n\nIf you are using VS Code MCP extension or similar, your configuration for an HTTP server would look like:\n\n```json\n{\n \"servers\": {\n \"mcp-memgraph-http\": {\n \"url\": \"http://localhost:8000/mcp/\"\n }\n }\n}\n```\n\n> **Note:** The URL must end with `/mcp/`.\n\n---\n\n#### Running the Docker image in Visual Studio Code using stdio\n\nYou can also run the server using stdio for integration with MCP stdio clients:\n\n1. Open Visual Studio Code, open Command Palette (Ctrl+Shift+P or Cmd+Shift+P on Mac), and select `MCP: Add server...`.\n2. Choose `Command (stdio)`\n3. Enter `docker` as the command to run.\n4. For Server ID enter `mcp-memgraph`.\n5. Choose \"User\" (adds to user-space `settings.json`) or \"Workspace\" (adds to `.vscode/mcp.json`).\n\nWhen the settings open, enhance the args as follows:\n\n```json\n{\n \"servers\": {\n \"mcp-memgraph\": {\n \"type\": \"stdio\",\n \"command\": \"docker\",\n \"args\": [\n \"run\",\n \"--rm\",\n \"-i\",\n \"-e\", \"MCP_TRANSPORT=stdio\",\n \"mcp-memgraph:latest\"\n ]\n }\n }\n}\n```\n\nTo connect to a remote Memgraph instance with authentication, add environment variables to the `args` list:\n\n```json\n{\n \"servers\": {\n \"mcp-memgraph\": {\n \"type\": \"stdio\",\n \"command\": \"docker\",\n \"args\": [\n \"run\",\n \"--rm\",\n \"-i\",\n \"-e\", \"MCP_TRANSPORT=stdio\",\n \"-e\", \"MEMGRAPH_URL=bolt://memgraph:7687\",\n \"-e\", \"MEMGRAPH_USER=myuser\",\n \"-e\", \"MEMGRAPH_PASSWORD=mypassword\",\n \"mcp-memgraph:latest\"\n ]\n }\n }\n}\n```\n\n---\n\nOpen GitHub Copilot in Agent mode and you'll be able to interact with the Memgraph MCP server.",
"bugtrack_url": null,
"license": "MIT",
"summary": "MCP integration and utilities for Memgraph MCP server",
"version": "0.1.4",
"project_urls": {
"Homepage": "https://github.com/memgraph/ai-toolkit",
"Issues": "https://github.com/memgraph/ai-toolkit/issues",
"Source": "https://github.com/memgraph/ai-toolkit/tree/main/integrations/mcp-memgraph"
},
"split_keywords": [
"graph",
" integration",
" mcp",
" memgraph",
" toolkit"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "ae3914424bfdb445087e9dc51fe5365ca10dcd76c62504e2767b69018b58c55c",
"md5": "90190d657df5d503af0d9ca0c923bd99",
"sha256": "caa9eff204495dcbddc826f0249aeae8cadbf2e67a37b92e233a749e00b6bfd2"
},
"downloads": -1,
"filename": "mcp_memgraph-0.1.4-py3-none-any.whl",
"has_sig": false,
"md5_digest": "90190d657df5d503af0d9ca0c923bd99",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.13",
"size": 6865,
"upload_time": "2025-08-06T11:35:40",
"upload_time_iso_8601": "2025-08-06T11:35:40.714312Z",
"url": "https://files.pythonhosted.org/packages/ae/39/14424bfdb445087e9dc51fe5365ca10dcd76c62504e2767b69018b58c55c/mcp_memgraph-0.1.4-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "69196670f4df4af2729a41fdfe3f8855a46c8195a941858a6a817469d717f7b7",
"md5": "c6dd6a3d51f128b0c7ab3502db16c5ae",
"sha256": "192f82eccfaba58615acd30e17beeadea69d99efb5bfcbf93e4a1d6e951fc468"
},
"downloads": -1,
"filename": "mcp_memgraph-0.1.4.tar.gz",
"has_sig": false,
"md5_digest": "c6dd6a3d51f128b0c7ab3502db16c5ae",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.13",
"size": 92165,
"upload_time": "2025-08-06T11:35:41",
"upload_time_iso_8601": "2025-08-06T11:35:41.837385Z",
"url": "https://files.pythonhosted.org/packages/69/19/6670f4df4af2729a41fdfe3f8855a46c8195a941858a6a817469d717f7b7/mcp_memgraph-0.1.4.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-08-06 11:35:41",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "memgraph",
"github_project": "ai-toolkit",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"lcname": "mcp-memgraph"
}
