vizro-mcp 0.1.1__tar.gz → 0.1.2__tar.gz
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- vizro_mcp-0.1.2/.dockerignore +10 -0
- {vizro_mcp-0.1.1 → vizro_mcp-0.1.2}/CHANGELOG.md +16 -0
- vizro_mcp-0.1.2/Dockerfile +10 -0
- {vizro_mcp-0.1.1 → vizro_mcp-0.1.2}/PKG-INFO +75 -52
- {vizro_mcp-0.1.1 → vizro_mcp-0.1.2}/README.md +73 -50
- {vizro_mcp-0.1.1 → vizro_mcp-0.1.2}/assets/vizro-mcp.gif +0 -0
- {vizro_mcp-0.1.1 → vizro_mcp-0.1.2}/pyproject.toml +1 -1
- {vizro_mcp-0.1.1 → vizro_mcp-0.1.2}/src/vizro_mcp/__init__.py +1 -1
- vizro_mcp-0.1.2/src/vizro_mcp/_schemas/__init__.py +11 -0
- vizro_mcp-0.1.2/src/vizro_mcp/_schemas/schemas.py +214 -0
- {vizro_mcp-0.1.1 → vizro_mcp-0.1.2}/src/vizro_mcp/_utils/__init__.py +24 -5
- vizro_mcp-0.1.2/src/vizro_mcp/_utils/configs.py +142 -0
- vizro_mcp-0.1.2/src/vizro_mcp/_utils/prompts.py +180 -0
- {vizro_mcp-0.1.1 → vizro_mcp-0.1.2}/src/vizro_mcp/_utils/utils.py +63 -146
- vizro_mcp-0.1.2/src/vizro_mcp/server.py +364 -0
- {vizro_mcp-0.1.1 → vizro_mcp-0.1.2}/tests/unit/vizro_mcp/test_server.py +141 -65
- {vizro_mcp-0.1.1 → vizro_mcp-0.1.2}/uv.lock +713 -743
- vizro_mcp-0.1.1/src/vizro_mcp/_schemas/__init__.py +0 -29
- vizro_mcp-0.1.1/src/vizro_mcp/_schemas/schemas.py +0 -297
- vizro_mcp-0.1.1/src/vizro_mcp/server.py +0 -400
- {vizro_mcp-0.1.1 → vizro_mcp-0.1.2}/.gitignore +0 -0
- {vizro_mcp-0.1.1 → vizro_mcp-0.1.2}/LICENSE.txt +0 -0
- {vizro_mcp-0.1.1 → vizro_mcp-0.1.2}/assets/claude_prompt.png +0 -0
- {vizro_mcp-0.1.1 → vizro_mcp-0.1.2}/assets/claude_validate.png +0 -0
- {vizro_mcp-0.1.1 → vizro_mcp-0.1.2}/assets/claude_working.png +0 -0
- {vizro_mcp-0.1.1 → vizro_mcp-0.1.2}/assets/cursor_working.png +0 -0
- /vizro_mcp-0.1.1/changelog.d/20250515_115815_lingyi_zhang_0_1_1.md → /vizro_mcp-0.1.2/changelog.d/20250630_120648_maximilian_schulz_mcp.md +0 -0
- {vizro_mcp-0.1.1 → vizro_mcp-0.1.2}/changelog.d/new_fragment.md.j2 +0 -0
- {vizro_mcp-0.1.1 → vizro_mcp-0.1.2}/changelog.d/scriv.ini +0 -0
- {vizro_mcp-0.1.1 → vizro_mcp-0.1.2}/glama.json +0 -0
- {vizro_mcp-0.1.1 → vizro_mcp-0.1.2}/hatch.toml +0 -0
- {vizro_mcp-0.1.1 → vizro_mcp-0.1.2}/src/vizro_mcp/py.typed +0 -0
|
@@ -1,3 +1,19 @@
|
|
|
1
|
+
<a id='changelog-0.1.2'></a>
|
|
2
|
+
|
|
3
|
+
# 0.1.2 — 2025-06-30
|
|
4
|
+
|
|
5
|
+
## Added
|
|
6
|
+
|
|
7
|
+
- Add Dockerfile for Vizro MCP server to enable containerized local setup. ([#1184](https://github.com/mckinsey/vizro/pull/1184))
|
|
8
|
+
|
|
9
|
+
- Add capability to create custom charts (beyond Plotly Express) with Vizro-MCP. ([#1227](https://github.com/mckinsey/vizro/pull/1227))
|
|
10
|
+
|
|
11
|
+
## Changed
|
|
12
|
+
|
|
13
|
+
- Update Vizro version to `>=0.1.42`. ([#1227](https://github.com/mckinsey/vizro/pull/1227))
|
|
14
|
+
|
|
15
|
+
- Improve usability of MCP server in IDE environments like Cursor. ([#1227](https://github.com/mckinsey/vizro/pull/1227))
|
|
16
|
+
|
|
1
17
|
<a id='changelog-0.1.1'></a>
|
|
2
18
|
|
|
3
19
|
# 0.1.1 — 2025-05-15
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
Metadata-Version: 2.4
|
|
2
2
|
Name: vizro-mcp
|
|
3
|
-
Version: 0.1.
|
|
3
|
+
Version: 0.1.2
|
|
4
4
|
Summary: MCP server to help create Vizro dashboards and charts
|
|
5
5
|
Author: Vizro Team
|
|
6
6
|
License-File: LICENSE.txt
|
|
@@ -14,18 +14,27 @@ Requires-Dist: click>=8.1.7
|
|
|
14
14
|
Requires-Dist: httpx>=0.28.1
|
|
15
15
|
Requires-Dist: mcp[cli]>=1.6.0
|
|
16
16
|
Requires-Dist: pandas[excel,html,parquet]
|
|
17
|
-
Requires-Dist: vizro
|
|
17
|
+
Requires-Dist: vizro>=0.1.42
|
|
18
18
|
Description-Content-Type: text/markdown
|
|
19
19
|
|
|
20
|
-
<a href="https://glama.ai/mcp/servers/@mckinsey/vizro">
|
|
20
|
+
<!-- <a href="https://glama.ai/mcp/servers/@mckinsey/vizro">
|
|
21
21
|
<img width="380" height="200" src="https://glama.ai/mcp/servers/@mckinsey/vizro/badge" />
|
|
22
|
-
</a>
|
|
22
|
+
</a> -->
|
|
23
23
|
|
|
24
24
|
# Vizro MCP server
|
|
25
25
|
|
|
26
26
|
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.
|
|
27
27
|
|
|
28
|
-
|
|
28
|
+
<img src="assets/vizro-mcp.gif" width="600" alt="Vizro MCP Demo">
|
|
29
|
+
|
|
30
|
+
### Quick install
|
|
31
|
+
|
|
32
|
+
| Host | Prerequisite | Link | Notes |
|
|
33
|
+
| ----------------------------------------- | ------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------- |
|
|
34
|
+
| [Cursor](https://www.cursor.com/) | [uv](https://docs.astral.sh/uv/getting-started/installation/) | [](https://cursor.com/install-mcp?name=vizro-mcp&config=eyJjb21tYW5kIjoidXZ4IHZpenJvLW1jcCJ9) | |
|
|
35
|
+
| [VS Code](https://code.visualstudio.com/) | [uv](https://docs.astral.sh/uv/guides/tools/) | [](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) | |
|
|
36
|
+
| [Cursor](https://www.cursor.com/) | [Docker](https://www.docker.com/get-started/) | [](https://cursor.com/install-mcp?name=vizro-mcp&config=eyJjb21tYW5kIjoiZG9ja2VyIHJ1biAtaSAtLXJtIG1jcC92aXpybyJ9) | For local data access, [mount your data directory](#setup-instructions) |
|
|
37
|
+
| [VS Code](https://code.visualstudio.com/) | [Docker](https://www.docker.com/get-started/) | [](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) |
|
|
29
38
|
|
|
30
39
|
## Features of Vizro-MCP
|
|
31
40
|
|
|
@@ -53,23 +62,23 @@ Without Vizro-MCP, if you try to make a dashboard using an LLM, it could choose
|
|
|
53
62
|
|
|
54
63
|
## 🛠️ Get started
|
|
55
64
|
|
|
56
|
-
|
|
57
|
-
|
|
58
|
-
### Prerequisites
|
|
59
|
-
|
|
60
|
-
- [uv](https://docs.astral.sh/uv/getting-started/installation/)
|
|
61
|
-
- [Claude Desktop](https://claude.ai/download) or [Cursor](https://www.cursor.com/downloads)
|
|
65
|
+
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.
|
|
62
66
|
|
|
63
|
-
|
|
67
|
+
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).
|
|
64
68
|
|
|
65
|
-
|
|
69
|
+
### Prerequisites
|
|
66
70
|
|
|
67
|
-
|
|
71
|
+
- [uv](https://docs.astral.sh/uv/getting-started/installation/) **or** [Docker](https://www.docker.com/get-started/)
|
|
72
|
+
- Any LLM application that supports MCP, such as [Claude Desktop](https://claude.ai/download) or [Cursor](https://www.cursor.com/downloads)
|
|
68
73
|
|
|
69
74
|
### Setup Instructions
|
|
70
75
|
|
|
71
76
|
The general server config is mostly the same for all hosts:
|
|
72
77
|
|
|
78
|
+
#### 1. Set up configuration
|
|
79
|
+
|
|
80
|
+
**Using `uvx`**
|
|
81
|
+
|
|
73
82
|
```json
|
|
74
83
|
{
|
|
75
84
|
"mcpServers": {
|
|
@@ -83,62 +92,78 @@ The general server config is mostly the same for all hosts:
|
|
|
83
92
|
}
|
|
84
93
|
```
|
|
85
94
|
|
|
86
|
-
|
|
87
|
-
|
|
88
|
-
<details>
|
|
89
|
-
<summary><strong>Claude Desktop</strong></summary>
|
|
90
|
-
|
|
91
|
-
Add the following to your `claude_desktop_config.json` [found via Developer Settings](https://modelcontextprotocol.io/quickstart/user#2-add-the-filesystem-mcp-server).
|
|
95
|
+
**Using `Docker`**
|
|
92
96
|
|
|
93
97
|
```json
|
|
94
98
|
{
|
|
95
99
|
"mcpServers": {
|
|
96
100
|
"vizro-mcp": {
|
|
97
|
-
"command": "
|
|
101
|
+
"command": "docker",
|
|
98
102
|
"args": [
|
|
99
|
-
"
|
|
103
|
+
"run",
|
|
104
|
+
"-i",
|
|
105
|
+
"--rm",
|
|
106
|
+
"--mount",
|
|
107
|
+
"type=bind,src=</absolute/path/to/allowed/dir>,dst=</absolute/path/to/allowed/dir>",
|
|
108
|
+
"--mount",
|
|
109
|
+
"type=bind,src=</absolute/path/to/data.csv>,dst=</absolute/path/to/data.csv>",
|
|
110
|
+
"mcp/vizro"
|
|
100
111
|
]
|
|
101
112
|
}
|
|
102
113
|
}
|
|
103
114
|
}
|
|
104
115
|
```
|
|
105
116
|
|
|
106
|
-
>
|
|
117
|
+
> 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.
|
|
118
|
+
|
|
119
|
+
#### 2. Add the Configuration to MCP enabled LLM applications
|
|
120
|
+
|
|
121
|
+
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.
|
|
122
|
+
|
|
123
|
+
<details>
|
|
124
|
+
<summary><strong>Claude Desktop</strong></summary>
|
|
125
|
+
|
|
126
|
+
- Add the configuration to your `claude_desktop_config.json` ([found via Developer Settings](https://modelcontextprotocol.io/quickstart/user#2-add-the-filesystem-mcp-server)).
|
|
107
127
|
|
|
108
|
-
|
|
128
|
+
- Restart Claude Desktop. After a few moments, you should see the vizro-mcp menu in the settings/context menu:
|
|
109
129
|
|
|
110
|
-
<img src="assets/claude_working.png" alt="Claude Desktop MCP Server Icon" width="
|
|
130
|
+
<img src="assets/claude_working.png" alt="Claude Desktop MCP Server Icon" width="300"/>
|
|
131
|
+
|
|
132
|
+
> ⚠️ **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.
|
|
111
133
|
|
|
112
134
|
</details>
|
|
113
135
|
|
|
114
136
|
<details>
|
|
115
137
|
<summary><strong>Cursor</strong></summary>
|
|
138
|
+
<br >
|
|
116
139
|
|
|
117
|
-
|
|
140
|
+
[](https://cursor.com/install-mcp?name=vizro-mcp&config=eyJjb21tYW5kIjoidXZ4IHZpenJvLW1jcCJ9)
|
|
118
141
|
|
|
119
|
-
|
|
120
|
-
|
|
121
|
-
|
|
122
|
-
"vizro-mcp": {
|
|
123
|
-
"command": "uvx",
|
|
124
|
-
"args": [
|
|
125
|
-
"vizro-mcp"
|
|
126
|
-
]
|
|
127
|
-
}
|
|
128
|
-
}
|
|
129
|
-
}
|
|
130
|
-
```
|
|
142
|
+
- 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.
|
|
143
|
+
|
|
144
|
+
- After a short pause, you should see a green light in the MCP menu:
|
|
131
145
|
|
|
132
|
-
|
|
146
|
+
|
|
133
147
|
|
|
134
|
-
|
|
148
|
+
</details>
|
|
149
|
+
|
|
150
|
+
<details>
|
|
151
|
+
<summary><strong>Other MCP Clients</strong></summary>
|
|
135
152
|
|
|
136
|
-
<
|
|
153
|
+
<br />
|
|
154
|
+
|
|
155
|
+
[](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)
|
|
156
|
+
|
|
157
|
+
- Add the configuration as per your client's documentation.
|
|
158
|
+
|
|
159
|
+
- Check your client's documentation for where to place the config and how to verify the server is running.
|
|
137
160
|
|
|
138
161
|
</details>
|
|
139
162
|
|
|
140
163
|
## 💻 Usage
|
|
141
164
|
|
|
165
|
+
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.
|
|
166
|
+
|
|
142
167
|
### Use prompt templates to get specific dashboards quickly
|
|
143
168
|
|
|
144
169
|
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`_.
|
|
@@ -165,7 +190,7 @@ In general, it helps to specify Vizro in the prompt and to keep it as precise (a
|
|
|
165
190
|
|
|
166
191
|
### Get a live preview of your dashboard
|
|
167
192
|
|
|
168
|
-
When the LLM chooses to use the tool `
|
|
193
|
+
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.
|
|
169
194
|
|
|
170
195
|
<img src="assets/claude_validate.png" width="300"/>
|
|
171
196
|
|
|
@@ -187,34 +212,32 @@ Alternatively, you can just ask in the chat, for example:
|
|
|
187
212
|
|
|
188
213
|
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.
|
|
189
214
|
|
|
190
|
-
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.
|
|
215
|
+
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.
|
|
191
216
|
|
|
192
|
-
The second most critical part is the `
|
|
217
|
+
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.
|
|
193
218
|
|
|
194
219
|
## Available Tools (if client allows)
|
|
195
220
|
|
|
196
221
|
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.
|
|
197
222
|
|
|
198
223
|
- `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.
|
|
199
|
-
- `
|
|
200
|
-
- `
|
|
201
|
-
- `
|
|
224
|
+
- `get_model_json_schema` - Retrieves the complete JSON schema for any specified Vizro model, useful for understanding required and optional parameters.
|
|
225
|
+
- `validate_dashboard_config` - Tests Vizro model configurations by attempting to instantiate them. Returns Python code and visualization links for valid configurations.
|
|
226
|
+
- `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.
|
|
202
227
|
- `validate_chart_code` - Validates the code created for a chart and returns feedback on its correctness.
|
|
203
228
|
- `get_sample_data_info` - Provides information about sample datasets that can be used for testing and development.
|
|
204
229
|
|
|
205
230
|
## Available Prompts (if client allows)
|
|
206
231
|
|
|
207
232
|
- `create_starter_dashboard` - Use this prompt template to get started with Vizro dashboards.
|
|
208
|
-
- `
|
|
233
|
+
- `create_dashboard` - Use this prompt template to create a dashboard based on a local or remote CSV dataset.
|
|
209
234
|
- `create_vizro_chart` - Use this prompt template to create a Vizro styled plotly chart based on a local or remote CSV dataset.
|
|
210
235
|
|
|
211
236
|
## Development or running from source
|
|
212
237
|
|
|
213
|
-
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
|
|
214
|
-
|
|
215
|
-
**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):
|
|
238
|
+
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:
|
|
216
239
|
|
|
217
|
-
|
|
240
|
+
Add the following to your MCP configuration:
|
|
218
241
|
|
|
219
242
|
```json
|
|
220
243
|
{
|
|
@@ -1,12 +1,21 @@
|
|
|
1
|
-
<a href="https://glama.ai/mcp/servers/@mckinsey/vizro">
|
|
1
|
+
<!-- <a href="https://glama.ai/mcp/servers/@mckinsey/vizro">
|
|
2
2
|
<img width="380" height="200" src="https://glama.ai/mcp/servers/@mckinsey/vizro/badge" />
|
|
3
|
-
</a>
|
|
3
|
+
</a> -->
|
|
4
4
|
|
|
5
5
|
# Vizro MCP server
|
|
6
6
|
|
|
7
7
|
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.
|
|
8
8
|
|
|
9
|
-
|
|
9
|
+
<img src="assets/vizro-mcp.gif" width="600" alt="Vizro MCP Demo">
|
|
10
|
+
|
|
11
|
+
### Quick install
|
|
12
|
+
|
|
13
|
+
| Host | Prerequisite | Link | Notes |
|
|
14
|
+
| ----------------------------------------- | ------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------- |
|
|
15
|
+
| [Cursor](https://www.cursor.com/) | [uv](https://docs.astral.sh/uv/getting-started/installation/) | [](https://cursor.com/install-mcp?name=vizro-mcp&config=eyJjb21tYW5kIjoidXZ4IHZpenJvLW1jcCJ9) | |
|
|
16
|
+
| [VS Code](https://code.visualstudio.com/) | [uv](https://docs.astral.sh/uv/guides/tools/) | [](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) | |
|
|
17
|
+
| [Cursor](https://www.cursor.com/) | [Docker](https://www.docker.com/get-started/) | [](https://cursor.com/install-mcp?name=vizro-mcp&config=eyJjb21tYW5kIjoiZG9ja2VyIHJ1biAtaSAtLXJtIG1jcC92aXpybyJ9) | For local data access, [mount your data directory](#setup-instructions) |
|
|
18
|
+
| [VS Code](https://code.visualstudio.com/) | [Docker](https://www.docker.com/get-started/) | [](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) |
|
|
10
19
|
|
|
11
20
|
## Features of Vizro-MCP
|
|
12
21
|
|
|
@@ -34,23 +43,23 @@ Without Vizro-MCP, if you try to make a dashboard using an LLM, it could choose
|
|
|
34
43
|
|
|
35
44
|
## 🛠️ Get started
|
|
36
45
|
|
|
37
|
-
|
|
38
|
-
|
|
39
|
-
### Prerequisites
|
|
40
|
-
|
|
41
|
-
- [uv](https://docs.astral.sh/uv/getting-started/installation/)
|
|
42
|
-
- [Claude Desktop](https://claude.ai/download) or [Cursor](https://www.cursor.com/downloads)
|
|
46
|
+
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.
|
|
43
47
|
|
|
44
|
-
|
|
48
|
+
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).
|
|
45
49
|
|
|
46
|
-
|
|
50
|
+
### Prerequisites
|
|
47
51
|
|
|
48
|
-
|
|
52
|
+
- [uv](https://docs.astral.sh/uv/getting-started/installation/) **or** [Docker](https://www.docker.com/get-started/)
|
|
53
|
+
- Any LLM application that supports MCP, such as [Claude Desktop](https://claude.ai/download) or [Cursor](https://www.cursor.com/downloads)
|
|
49
54
|
|
|
50
55
|
### Setup Instructions
|
|
51
56
|
|
|
52
57
|
The general server config is mostly the same for all hosts:
|
|
53
58
|
|
|
59
|
+
#### 1. Set up configuration
|
|
60
|
+
|
|
61
|
+
**Using `uvx`**
|
|
62
|
+
|
|
54
63
|
```json
|
|
55
64
|
{
|
|
56
65
|
"mcpServers": {
|
|
@@ -64,62 +73,78 @@ The general server config is mostly the same for all hosts:
|
|
|
64
73
|
}
|
|
65
74
|
```
|
|
66
75
|
|
|
67
|
-
|
|
68
|
-
|
|
69
|
-
<details>
|
|
70
|
-
<summary><strong>Claude Desktop</strong></summary>
|
|
71
|
-
|
|
72
|
-
Add the following to your `claude_desktop_config.json` [found via Developer Settings](https://modelcontextprotocol.io/quickstart/user#2-add-the-filesystem-mcp-server).
|
|
76
|
+
**Using `Docker`**
|
|
73
77
|
|
|
74
78
|
```json
|
|
75
79
|
{
|
|
76
80
|
"mcpServers": {
|
|
77
81
|
"vizro-mcp": {
|
|
78
|
-
"command": "
|
|
82
|
+
"command": "docker",
|
|
79
83
|
"args": [
|
|
80
|
-
"
|
|
84
|
+
"run",
|
|
85
|
+
"-i",
|
|
86
|
+
"--rm",
|
|
87
|
+
"--mount",
|
|
88
|
+
"type=bind,src=</absolute/path/to/allowed/dir>,dst=</absolute/path/to/allowed/dir>",
|
|
89
|
+
"--mount",
|
|
90
|
+
"type=bind,src=</absolute/path/to/data.csv>,dst=</absolute/path/to/data.csv>",
|
|
91
|
+
"mcp/vizro"
|
|
81
92
|
]
|
|
82
93
|
}
|
|
83
94
|
}
|
|
84
95
|
}
|
|
85
96
|
```
|
|
86
97
|
|
|
87
|
-
>
|
|
98
|
+
> 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.
|
|
99
|
+
|
|
100
|
+
#### 2. Add the Configuration to MCP enabled LLM applications
|
|
101
|
+
|
|
102
|
+
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.
|
|
103
|
+
|
|
104
|
+
<details>
|
|
105
|
+
<summary><strong>Claude Desktop</strong></summary>
|
|
106
|
+
|
|
107
|
+
- Add the configuration to your `claude_desktop_config.json` ([found via Developer Settings](https://modelcontextprotocol.io/quickstart/user#2-add-the-filesystem-mcp-server)).
|
|
88
108
|
|
|
89
|
-
|
|
109
|
+
- Restart Claude Desktop. After a few moments, you should see the vizro-mcp menu in the settings/context menu:
|
|
90
110
|
|
|
91
|
-
<img src="assets/claude_working.png" alt="Claude Desktop MCP Server Icon" width="
|
|
111
|
+
<img src="assets/claude_working.png" alt="Claude Desktop MCP Server Icon" width="300"/>
|
|
112
|
+
|
|
113
|
+
> ⚠️ **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.
|
|
92
114
|
|
|
93
115
|
</details>
|
|
94
116
|
|
|
95
117
|
<details>
|
|
96
118
|
<summary><strong>Cursor</strong></summary>
|
|
119
|
+
<br >
|
|
97
120
|
|
|
98
|
-
|
|
121
|
+
[](https://cursor.com/install-mcp?name=vizro-mcp&config=eyJjb21tYW5kIjoidXZ4IHZpenJvLW1jcCJ9)
|
|
99
122
|
|
|
100
|
-
|
|
101
|
-
|
|
102
|
-
|
|
103
|
-
"vizro-mcp": {
|
|
104
|
-
"command": "uvx",
|
|
105
|
-
"args": [
|
|
106
|
-
"vizro-mcp"
|
|
107
|
-
]
|
|
108
|
-
}
|
|
109
|
-
}
|
|
110
|
-
}
|
|
111
|
-
```
|
|
123
|
+
- 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.
|
|
124
|
+
|
|
125
|
+
- After a short pause, you should see a green light in the MCP menu:
|
|
112
126
|
|
|
113
|
-
|
|
127
|
+
|
|
114
128
|
|
|
115
|
-
|
|
129
|
+
</details>
|
|
130
|
+
|
|
131
|
+
<details>
|
|
132
|
+
<summary><strong>Other MCP Clients</strong></summary>
|
|
116
133
|
|
|
117
|
-
<
|
|
134
|
+
<br />
|
|
135
|
+
|
|
136
|
+
[](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)
|
|
137
|
+
|
|
138
|
+
- Add the configuration as per your client's documentation.
|
|
139
|
+
|
|
140
|
+
- Check your client's documentation for where to place the config and how to verify the server is running.
|
|
118
141
|
|
|
119
142
|
</details>
|
|
120
143
|
|
|
121
144
|
## 💻 Usage
|
|
122
145
|
|
|
146
|
+
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.
|
|
147
|
+
|
|
123
148
|
### Use prompt templates to get specific dashboards quickly
|
|
124
149
|
|
|
125
150
|
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`_.
|
|
@@ -146,7 +171,7 @@ In general, it helps to specify Vizro in the prompt and to keep it as precise (a
|
|
|
146
171
|
|
|
147
172
|
### Get a live preview of your dashboard
|
|
148
173
|
|
|
149
|
-
When the LLM chooses to use the tool `
|
|
174
|
+
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.
|
|
150
175
|
|
|
151
176
|
<img src="assets/claude_validate.png" width="300"/>
|
|
152
177
|
|
|
@@ -168,34 +193,32 @@ Alternatively, you can just ask in the chat, for example:
|
|
|
168
193
|
|
|
169
194
|
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.
|
|
170
195
|
|
|
171
|
-
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.
|
|
196
|
+
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.
|
|
172
197
|
|
|
173
|
-
The second most critical part is the `
|
|
198
|
+
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.
|
|
174
199
|
|
|
175
200
|
## Available Tools (if client allows)
|
|
176
201
|
|
|
177
202
|
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.
|
|
178
203
|
|
|
179
204
|
- `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.
|
|
180
|
-
- `
|
|
181
|
-
- `
|
|
182
|
-
- `
|
|
205
|
+
- `get_model_json_schema` - Retrieves the complete JSON schema for any specified Vizro model, useful for understanding required and optional parameters.
|
|
206
|
+
- `validate_dashboard_config` - Tests Vizro model configurations by attempting to instantiate them. Returns Python code and visualization links for valid configurations.
|
|
207
|
+
- `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.
|
|
183
208
|
- `validate_chart_code` - Validates the code created for a chart and returns feedback on its correctness.
|
|
184
209
|
- `get_sample_data_info` - Provides information about sample datasets that can be used for testing and development.
|
|
185
210
|
|
|
186
211
|
## Available Prompts (if client allows)
|
|
187
212
|
|
|
188
213
|
- `create_starter_dashboard` - Use this prompt template to get started with Vizro dashboards.
|
|
189
|
-
- `
|
|
214
|
+
- `create_dashboard` - Use this prompt template to create a dashboard based on a local or remote CSV dataset.
|
|
190
215
|
- `create_vizro_chart` - Use this prompt template to create a Vizro styled plotly chart based on a local or remote CSV dataset.
|
|
191
216
|
|
|
192
217
|
## Development or running from source
|
|
193
218
|
|
|
194
|
-
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
|
|
195
|
-
|
|
196
|
-
**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):
|
|
219
|
+
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:
|
|
197
220
|
|
|
198
|
-
|
|
221
|
+
Add the following to your MCP configuration:
|
|
199
222
|
|
|
200
223
|
```json
|
|
201
224
|
{
|
|
Binary file
|