vizro-mcp 0.1.0__py3-none-any.whl → 0.1.2__py3-none-any.whl

{vizro_mcp-0.1.0.dist-info → vizro_mcp-0.1.2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: vizro-mcp
-Version: 0.1.0
+Version: 0.1.2
 Summary: MCP server to help create Vizro dashboards and charts
 Author: Vizro Team
 License-File: LICENSE.txt
@@ -14,13 +14,28 @@ Requires-Dist: click>=8.1.7
 Requires-Dist: httpx>=0.28.1
 Requires-Dist: mcp[cli]>=1.6.0
 Requires-Dist: pandas[excel,html,parquet]
-Requires-Dist: vizro==0.1.38
+Requires-Dist: vizro>=0.1.42
 Description-Content-Type: text/markdown
 
+<!-- <a href="https://glama.ai/mcp/servers/@mckinsey/vizro">
+  <img width="380" height="200" src="https://glama.ai/mcp/servers/@mckinsey/vizro/badge" />
+</a> -->
+
 # Vizro MCP server
 
 Vizro-MCP is a [Model Context Protocol (MCP)](https://modelcontextprotocol.io/) server, which works alongside a LLM to help you create Vizro dashboards and charts.
 
+<img src="assets/vizro-mcp.gif" width="600" alt="Vizro MCP Demo">
+
+### Quick install
+
+| Host                                      | Prerequisite                                                  | Link                                                                                                                                                                                                                                                                                                                                   | Notes                                                                   |
+| ----------------------------------------- | ------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------- |
+| [Cursor](https://www.cursor.com/)         | [uv](https://docs.astral.sh/uv/getting-started/installation/) | [![Install with UVX in Cursor](https://img.shields.io/badge/Cursor-Install-0098FF?style=flat-square&logo=visualstudiocode&logoColor=white)](https://cursor.com/install-mcp?name=vizro-mcp&config=eyJjb21tYW5kIjoidXZ4IHZpenJvLW1jcCJ9)                                                                                                 |                                                                         |
+| [VS Code](https://code.visualstudio.com/) | [uv](https://docs.astral.sh/uv/guides/tools/)                 | [![Install with UVX in VS Code](https://img.shields.io/badge/VS_Code-Install-0098FF?style=flat-square&logo=visualstudiocode&logoColor=white)](https://insiders.vscode.dev/redirect/mcp/install?name=vizro-mcp&config=%7B%22command%22%3A%22uvx%22%2C%22args%22%3A%5B%22vizro-mcp%22%5D%7D)                                             |                                                                         |
+| [Cursor](https://www.cursor.com/)         | [Docker](https://www.docker.com/get-started/)                 | [![Install with Docker in Cursor](https://img.shields.io/badge/Cursor-Install-0098FF?style=flat-square&logo=visualstudiocode&logoColor=white)](https://cursor.com/install-mcp?name=vizro-mcp&config=eyJjb21tYW5kIjoiZG9ja2VyIHJ1biAtaSAtLXJtIG1jcC92aXpybyJ9)                                                                          | For local data access, [mount your data directory](#setup-instructions) |
+| [VS Code](https://code.visualstudio.com/) | [Docker](https://www.docker.com/get-started/)                 | [![Install with Docker in VS Code](https://img.shields.io/badge/VS_Code-Install-0098FF?style=flat-square&logo=visualstudiocode&logoColor=white)](https://insiders.vscode.dev/redirect/mcp/install?name=vizro-mcp&config=%7B%22command%22%3A%22docker%22%2C%22args%22%3A%5B%22run%22%2C%22-i%22%2C%22--rm%22%2C%22mcp%2Fvizro%22%5D%7D) | For local data access, [mount your data directory](#setup-instructions) |
+
 ## Features of Vizro-MCP
 
 Vizro-MCP provides tools and templates to create a functioning Vizro chart or dashboard step by step. Benefits include:
@@ -47,25 +62,22 @@ Without Vizro-MCP, if you try to make a dashboard using an LLM, it could choose
 
 ## 🛠️ Get started
 
-If you are a **developer** and need instructions for running Vizro-MCP from source, skip to the end of this page to [Development or running from source](#development-or-running-from-source).
-
-### Prerequisites
+Vizro-MCP can be run in two ways: using [`uvx`](https://docs.astral.sh/uv/guides/tools/) or using [`Docker`](https://www.docker.com/get-started/). It works with any MCP-enabled LLM client such as Cursor or Claude Desktop.
 
-- [uv](https://docs.astral.sh/uv/getting-started/installation/)
-- [Claude Desktop](https://claude.ai/download) or [Cursor](https://www.cursor.com/downloads)
+If you want to run Vizro-MCP directly from source, skip to the end of this page to [Development or running from source](#development-or-running-from-source).
 
-In principle, the Vizro MCP server works with _any_ MCP enabled LLM applications but we recommend Claude Desktop or Cursor as popular choices.
+### Prerequisites
 
-> 🐛 **Note:** There are currently some known issues with [VS Code](https://code.visualstudio.com/) but we are working on this and hope to have Copilot working soon.
+- [uv](https://docs.astral.sh/uv/getting-started/installation/) **or** [Docker](https://www.docker.com/get-started/)
+- Any LLM application that supports MCP, such as [Claude Desktop](https://claude.ai/download) or [Cursor](https://www.cursor.com/downloads)
 
-> ⚠️ **Warning:** In some hosts (like Claude Desktop) the free plan might be less performant, which may cause issues when the request is too complex. In cases where the request causes the UI to crash, opt for using a paid plan, or reduce your request's complexity.
+### Setup Instructions
 
-## Setup Instructions
+The general server config is mostly the same for all hosts:
 
-<details>
-<summary><strong>Claude</strong></summary>
+#### 1. Set up configuration
 
-Add the following to your `claude_desktop_config.json` [found via Developer Settings](https://modelcontextprotocol.io/quickstart/user#2-add-the-filesystem-mcp-server).
+**Using `uvx`**
 
 ```json
 {
@@ -80,44 +92,78 @@ Add the following to your `claude_desktop_config.json` [found via Developer Sett
 }
 ```
 
-> ⚠️ **Warning:** In some cases you may need to provide the full path to your `uvx` executable, so instead of `uvx` would use something like `/Users/<your-username>/.local/bin/uvx`. To discover the path of `uvx` on your machine, in your terminal app, type `which uvx`.
-
-If you are using Claude Desktop, restart it, and after a few moments, you should see the vizro-mcp menu when opening the settings/context menu:
-
-<img src="assets/claude_working.png" alt="Claude Desktop MCP Server Icon" width="150"/>
-
-</details>
-
-<details>
-<summary><strong>Cursor</strong></summary>
-
-Add the following to `mcp.json` [found via the Cursor Settings](https://docs.cursor.com/context/model-context-protocol#configuration-locations).
+**Using `Docker`**
 
 ```json
 {
   "mcpServers": {
     "vizro-mcp": {
-      "command": "uvx",
+      "command": "docker",
       "args": [
-        "vizro-mcp"
+        "run",
+        "-i",
+        "--rm",
+        "--mount",
+        "type=bind,src=</absolute/path/to/allowed/dir>,dst=</absolute/path/to/allowed/dir>",
+        "--mount",
+        "type=bind,src=</absolute/path/to/data.csv>,dst=</absolute/path/to/data.csv>",
+        "mcp/vizro"
       ]
     }
   }
 }
 ```
 
-> ⚠️ **Warning:** In some cases you may need to provide the full path to your `uvx` executable, so instead of `uvx` would use something like `/Users/<your-username>/.local/bin/uvx`. To discover the path of `uvx` on your machine, in your terminal app, type `which uvx`.
+> To use local data with Vizro-MCP, mount your data directory or directories into the container. Replace `</absolute/path/to/allowed/dir>` (syntax for folders) or `</absolute/path/to/data.csv>` (syntax for files) with the absolute path to your data on your machine. For consistency, it is recommended that the `dst` path matches the `src` path.
+
+#### 2. Add the Configuration to MCP enabled LLM applications
 
-Similarly, when using Cursor, after a short pause, you should see a green light in the MCP menu:
+In principle, the Vizro MCP server works with _any_ MCP enabled LLM applications but we recommend Claude Desktop or Cursor as popular choices (see more detailed instructions below). Different AI tools may use different setup methods or connection settings. Check each tool's docs for details.
+
+<details>
+<summary><strong>Claude Desktop</strong></summary>
 
-<img src="assets/cursor_working.png" alt="Cursor MCP Server Icon" width="400"/>
+- Add the configuration to your `claude_desktop_config.json` ([found via Developer Settings](https://modelcontextprotocol.io/quickstart/user#2-add-the-filesystem-mcp-server)).
+
+- Restart Claude Desktop. After a few moments, you should see the vizro-mcp menu in the settings/context menu:
+
+    <img src="assets/claude_working.png" alt="Claude Desktop MCP Server Icon" width="300"/>
+
+> ⚠️ **Warning:** In some hosts (like Claude Desktop) the free plan might be less performant, which may cause issues when the request is too complex. In cases where the request causes the UI to crash, opt for using a paid plan, or reduce your request's complexity.
+
+</details>
+
+<details>
+<summary><strong>Cursor</strong></summary>
+<br >
+
+[![Install with UVX in Cursor](https://img.shields.io/badge/Cursor-Install-0098FF?style=flat-square&logo=visualstudiocode&logoColor=white)](https://cursor.com/install-mcp?name=vizro-mcp&config=eyJjb21tYW5kIjoidXZ4IHZpenJvLW1jcCJ9)
+
+- Add the above configuration to your `mcp.json` ([see Cursor Settings](https://docs.cursor.com/context/model-context-protocol#configuration-locations)) or click the button above.
+
+- After a short pause, you should see a green light in the MCP menu:
+
+    ![Cursor MCP Server Icon](assets/cursor_working.png)
 
 </details>
 
-In principle, the Vizro MCP server works with _any_ MCP enabled LLM applications but we recommend Claude Desktop or Cursor as popular choices. Different AI tools may use different setup methods or connection settings. Check each tool's docs for details.
+<details>
+<summary><strong>Other MCP Clients</strong></summary>
+
+<br />
+
+[![Install with UVX in VS Code](https://img.shields.io/badge/VS_Code-Install_all-0098FF?style=flat-square&logo=visualstudiocode&logoColor=white)](https://insiders.vscode.dev/redirect/mcp/install?name=vizro-mcp&config=%7B%22command%22%3A%22uvx%22%2C%22args%22%3A%5B%22vizro-mcp%22%5D%7D)
+
+- Add the configuration as per your client's documentation.
+
+- Check your client's documentation for where to place the config and how to verify the server is running.
+
+</details>
 
 ## 💻 Usage
 
+The MCP server is designed to get you started on Vizro dashboards and charts by creating beautiful working dashboards based on the core Vizro features. It is not designed to replace a human developer when going beyond the core features, e.g. when building an application that requires custom CSS or bespoke Dash components.
+
 ### Use prompt templates to get specific dashboards quickly
 
 Prompt templates are not available in all MCP hosts, but when they are, you can use them to get specific dashboards quickly. To access them (e.g. in Claude Desktop), click on the plus icon below the chat, and choose _`Add from vizro-mcp`_.
@@ -144,7 +190,7 @@ In general, it helps to specify Vizro in the prompt and to keep it as precise (a
 
 ### Get a live preview of your dashboard
 
-When the LLM chooses to use the tool `validate_model_config`, and the tool executes successfully, the LLM will return a link to a live preview of the dashboard if only public data accessed via URL is used. By default, the LLM will even open the link in your browser for you unless you tell it not to. In Claude Desktop, you can see the output of the tool by opening the tool collapsible and scrolling down to the very bottom.
+When the LLM chooses to use the tool `validate_dashboard_config`, and the tool executes successfully, the LLM will return a link to a live preview of the dashboard if only public data accessed via URL is used. By default, the LLM will even open the link in your browser for you unless you tell it not to. In Claude Desktop, you can see the output of the tool by opening the tool collapsible and scrolling down to the very bottom.
 
 <img src="assets/claude_validate.png" width="300"/>
 
@@ -166,34 +212,32 @@ Alternatively, you can just ask in the chat, for example:
 
 MCP servers are a relatively new concept, and it is important to be transparent about what the tools are capable of so you can make an informed choice as a user. Overall, the Vizro MCP server only reads data, and never writes, deletes or modifies any data on your machine.
 
-In general the most critical part of the process is the `load_and_analyze_data` tool. This tool, running on your machine, will load local or remote data into a pandas DataFrame and provide a detailed analysis of its structure and content. It only uses `pd.read_xxx`, so in general there is no need to worry about privacy or data security.
+In general the most critical part of the process is the `load_and_analyze_data` tool. This tool, running on your machine, will load local or remote data into a pandas DataFrame and provide a detailed analysis of its structure and content. It only uses `pd.read_xxx`, so in general there is no need to worry about privacy or data security. However, you should only run Vizro-MCP locally, not as a hosted server, because there is currently no authentication to manage access.
 
-The second most critical part is the `validate_model_config` tool. This tool will attempt to instantiate the Vizro model configuration and return the Python code and visualization link for valid configurations. If the configuration is valid, it will also return and attempt to open a link to a live preview of the dashboard, which will take you to [PyCafe](https://py.cafe). If you don't want to open the link, you can tell the LLM to not do so.
+The second most critical part is the `validate_dashboard_config` tool. This tool will attempt to instantiate the Vizro model configuration and return the Python code and visualization link for valid configurations. If the configuration is valid, it will also return and attempt to open a link to a live preview of the dashboard, which will take you to [PyCafe](https://py.cafe). If you don't want to open the link, you can tell the LLM to not do so.
 
 ## Available Tools (if client allows)
 
 The Vizro MCP server provides the following tools. In general you should not need to use them directly, but in special cases you could ask the LLM to call them directly to help it find its way.
 
 - `get_vizro_chart_or_dashboard_plan` - Get a structured step-by-step plan for creating either a chart or dashboard. Provides guidance on the entire creation process.
-- `get_model_JSON_schema` - Retrieves the complete JSON schema for any specified Vizro model, useful for understanding required and optional parameters.
-- `validate_model_config` - Tests Vizro model configurations by attempting to instantiate them. Returns Python code and visualization links for valid configurations.
-- `load_and_analyze_csv` - Loads a CSV file from a local path or URL into a pandas DataFrame and provides detailed analysis of its structure and content.
+- `get_model_json_schema` - Retrieves the complete JSON schema for any specified Vizro model, useful for understanding required and optional parameters.
+- `validate_dashboard_config` - Tests Vizro model configurations by attempting to instantiate them. Returns Python code and visualization links for valid configurations.
+- `load_and_analyze_data` - Loads a CSV file from a local path or URL into a pandas DataFrame and provides detailed analysis of its structure and content.
 - `validate_chart_code` - Validates the code created for a chart and returns feedback on its correctness.
 - `get_sample_data_info` - Provides information about sample datasets that can be used for testing and development.
 
 ## Available Prompts (if client allows)
 
 - `create_starter_dashboard` - Use this prompt template to get started with Vizro dashboards.
-- `create_EDA_dashboard` - Use this prompt template to create an Exploratory Data Analysis (EDA) dashboard based on a local or remote CSV dataset.
+- `create_dashboard` - Use this prompt template to create a dashboard based on a local or remote CSV dataset.
 - `create_vizro_chart` - Use this prompt template to create a Vizro styled plotly chart based on a local or remote CSV dataset.
 
 ## Development or running from source
 
-If you are a developer, or if you are running Vizro-MCP from source, you need to clone the Vizro repo. To configure the Vizro MCP server details:
-
-**For Claude**: Add the following to your `claude_desktop_config.json` [found via Developer Settings](https://modelcontextprotocol.io/quickstart/user#2-add-the-filesystem-mcp-server):
+If you are a developer, or if you are running Vizro-MCP from source, you need to clone the Vizro repo. To configure the Vizro-MCP server details:
 
-**For Cursor**: Add the following to `mcp.json` [found via the Cursor Settings](https://docs.cursor.com/context/model-context-protocol#configuration-locations):
+Add the following to your MCP configuration:
 
 ```json
 {

vizro_mcp-0.1.2.dist-info/RECORD

@@ -0,0 +1,14 @@
+vizro_mcp/__init__.py,sha256=7rO7QeDAQXQ4DcfmJpU0uGgW7R0TMp2xgbAYNViFACE,379
+vizro_mcp/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+vizro_mcp/server.py,sha256=m4IQQlYve1p4fCkAPa5Cgtv9hnxykA7UHItrRVCVBWQ,12647
+vizro_mcp/_schemas/__init__.py,sha256=sCAIowgWm-qq8N3aMpVPx9WnbgoBal15AR3cg9rw8Yw,154
+vizro_mcp/_schemas/schemas.py,sha256=fWsx7iz99kIlff0d2TUGGUnlQ8lHez--gXkIFwbQ1pQ,8348
+vizro_mcp/_utils/__init__.py,sha256=ucPbfXe8kEFT7chz6ed_BeqAw71MnoWlZTYyCp4tPYY,1130
+vizro_mcp/_utils/configs.py,sha256=28ALgRgKYzRnPunSTjZxHFz2kyQy8yW4ZLhDgCUkE0s,3627
+vizro_mcp/_utils/prompts.py,sha256=YPk7fEVWkb1VGcRQ5uoFG8mGBnln65IK87GB0MXw9Fk,9754
+vizro_mcp/_utils/utils.py,sha256=XQcUBtyEd7eHCxQp4N92VUGsJ7bLwj9jSJVTgYCFRSc,7990
+vizro_mcp-0.1.2.dist-info/METADATA,sha256=fvXDcNLZq5Z1JEWjIFoId-shcR-6b-yOo-YoGUlGfS0,20077
+vizro_mcp-0.1.2.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+vizro_mcp-0.1.2.dist-info/entry_points.txt,sha256=iSUzPHvx4Ogsn91tK2C0OHxI44SNCHT1F1zUqbTj5O0,45
+vizro_mcp-0.1.2.dist-info/licenses/LICENSE.txt,sha256=z8d0m5b2O9McPEK1xHG_dWgUBT6EfBDz6wA0F7xSPTA,11358
+vizro_mcp-0.1.2.dist-info/RECORD,,

vizro_mcp-0.1.0.dist-info/RECORD

@@ -1,12 +0,0 @@
-vizro_mcp/__init__.py,sha256=mWzCq5I_M0tVM84u9mqQodTK6fEBxngAYGTEHvnmaUU,379
-vizro_mcp/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-vizro_mcp/server.py,sha256=cINRBPr0hkN5S5tD_Gf6dYu8vC7QviYCOrCtiAxYYwU,14813
-vizro_mcp/_schemas/__init__.py,sha256=przXt7ukurnDlj3SLRW-K0VO1ksnDDFuS8Njf80xepo,610
-vizro_mcp/_schemas/schemas.py,sha256=r_0i9fRtyMh7W3q3KgnpCbRUDlBaFjG6XQjCtahgEXc,11625
-vizro_mcp/_utils/__init__.py,sha256=q-xdwiyRCaOWWTeG5NC_1CzHWXBH4sUKpIBXbUaKg_Y,670
-vizro_mcp/_utils/utils.py,sha256=gIuKXONR2SvOgA3Vo3ONnkh8Qcc-RLfrexJAjan12zk,9217
-vizro_mcp-0.1.0.dist-info/METADATA,sha256=QaRxZjEcQy0n3_WKPfd6t3Eon_VR1QIVwrR__HGpl8M,15591
-vizro_mcp-0.1.0.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-vizro_mcp-0.1.0.dist-info/entry_points.txt,sha256=iSUzPHvx4Ogsn91tK2C0OHxI44SNCHT1F1zUqbTj5O0,45
-vizro_mcp-0.1.0.dist-info/licenses/LICENSE.txt,sha256=z8d0m5b2O9McPEK1xHG_dWgUBT6EfBDz6wA0F7xSPTA,11358
-vizro_mcp-0.1.0.dist-info/RECORD,,