Generates charts by converting Chart.js configurations into chart images through QuickChart.io, supporting multiple chart types including bar, line, pie, doughnut, radar, polar area, scatter, bubble, radial gauge, and speedometer charts
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@QuickChart MCP Server create a bar chart showing monthly sales for Q1"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A Model Context Protocol server for generating charts using QuickChart.io
This is a TypeScript-based MCP server that provides chart generation capabilities. It allows you to create various types of charts through MCP tools.
This server integrates with QuickChart.io's URL-based chart generation service to create chart images using Chart.js configurations. Users can generate various types of charts by providing data and styling parameters, which the server converts into chart URLs or downloadable images.
Related MCP server: Quick Chart MCP Server
generate_chart - Generate a chart URL using QuickChart.io
Supports multiple chart types: bar, line, pie, doughnut, radar, polarArea, scatter, bubble, radialGauge, speedometer
Customizable with labels, datasets, colors, and additional options
Returns a URL to the generated chart
download_chart - Download a chart image to a local file
Takes chart configuration and output path as parameters
Saves the chart image to the specified location
Bar charts: For comparing values across categories
Line charts: For showing trends over time
Pie charts: For displaying proportional data
Doughnut charts: Similar to pie charts with a hollow center
Radar charts: For showing multivariate data
Polar Area charts: For displaying proportional data with fixed-angle segments
Scatter plots: For showing data point distributions
Bubble charts: For three-dimensional data visualization
Radial Gauge: For displaying single values within a range
Speedometer: For speedometer-style value display
The server uses Chart.js configuration format. Here's a basic example:
{
"type": "bar",
"data": {
"labels": ["January", "February", "March"],
"datasets": [{
"label": "Sales",
"data": [65, 59, 80],
"backgroundColor": "rgb(75, 192, 192)"
}]
},
"options": {
"title": {
"display": true,
"text": "Monthly Sales"
}
}
}The server converts your configuration into a QuickChart URL:
https://quickchart.io/chart?c={...encoded configuration...}Install dependencies:
npm installBuild the server:
npm run buildnpm install @gongrzhe/quickchart-mcp-serverTo install QuickChart Server for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @gongrzhe/quickchart-mcp-server --client claudeTo use with Claude Desktop, add the server config:
On MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json
On Windows: %APPDATA%/Claude/claude_desktop_config.json
{
"mcpServers": {
"quickchart-server": {
"command": "node",
"args": ["/path/to/quickchart-server/build/index.js"]
}
}
}or
{
"mcpServers": {
"quickchart-server": {
"command": "npx",
"args": [
"-y",
"@gongrzhe/quickchart-mcp-server"
]
}
}
}This project is licensed under the MIT License.
Download a chart image to a local file
| Name | Required | Description | Default |
|---|---|---|---|
| config | Yes | Chart configuration object | |
| outputPath | Yes | Path where the chart image should be saved |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden for behavioral disclosure. It states the tool downloads to a local file, which implies file system write operations, but doesn't disclose permissions needed, whether it overwrites existing files, supported image formats, error conditions, or any rate limits. The description is minimal and lacks important behavioral context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence with zero wasted words. It's appropriately sized for a simple download operation and front-loads the core purpose immediately. Every word earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool that performs file system writes with no annotations and no output schema, the description is insufficient. It doesn't explain what happens on success/failure, what file formats are supported, whether the config parameter needs to match a previously generated chart, or any error conditions. The minimal description leaves too many operational questions unanswered.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already documents both parameters adequately. The description mentions 'chart image' which aligns with the config parameter's purpose, and 'to a local file' which aligns with outputPath, but adds no additional semantic context beyond what the schema provides. Baseline 3 is appropriate when schema does the heavy lifting.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Download') and resource ('a chart image to a local file'), providing a specific verb+resource combination. However, it doesn't differentiate from the sibling tool 'generate_chart' - we can infer download might follow generation, but this isn't explicitly stated.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided about when to use this tool versus alternatives. The existence of 'generate_chart' as a sibling tool suggests potential workflow relationships, but the description offers no explicit when/when-not instructions or prerequisites for usage.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Generate a chart using QuickChart
| Name | Required | Description | Default |
|---|---|---|---|
| type | Yes | Chart type (bar, line, pie, doughnut, radar, polarArea, scatter, bubble, radialGauge, speedometer) | |
| labels | No | Labels for data points | |
| datasets | Yes | ||
| title | No | ||
| options | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure but provides minimal information. It mentions 'using QuickChart' which hints at an external service dependency, but doesn't describe what the tool actually returns (e.g., URL, image data, error handling), rate limits, authentication needs, or whether it's a read-only or mutating operation. For a tool with complex parameters and no annotations, this is inadequate.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise at just 4 words, with zero wasted language. It's front-loaded with the core functionality and uses minimal space to convey the basic purpose. Every word earns its place in this brief description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with 5 parameters (including complex nested objects), no annotations, no output schema, and a sibling tool, the description is severely incomplete. It doesn't explain what the tool returns, how to interpret results, error conditions, or how it differs from the sibling 'download_chart' tool. The minimal description leaves too many gaps for effective agent usage.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
With only 40% schema description coverage, the description doesn't compensate by explaining any of the 5 parameters. The schema provides some parameter descriptions (like 'labels for data points' and 'chart type'), but the description adds no additional semantic context about what parameters mean, how they interact, or what values are expected beyond what's in the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('generate') and resource ('chart using QuickChart'), making the purpose immediately understandable. However, it doesn't differentiate from the sibling 'download_chart' tool, which appears to be a related but distinct operation. The description is specific about what the tool does but lacks sibling differentiation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus the sibling 'download_chart' tool, nor does it mention any prerequisites, constraints, or alternative approaches. There's no indication of when this tool is appropriate versus other chart generation methods or the sibling tool.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
download_chartgenerate_chartScored across 2 tools
The two tools have clearly distinct purposes: 'download_chart' handles saving a chart to a file, while 'generate_chart' focuses on creating the chart itself. There is no overlap or ambiguity between these operations.
Both tools follow a consistent verb_noun pattern with snake_case naming: 'download_chart' and 'generate_chart'. The naming is predictable and uniform across the set.
With only 2 tools, the server feels thin for a chart generation domain. A more complete surface might include tools for chart customization, listing chart types, or managing chart data, making this count borderline insufficient.
The tool set is severely incomplete for chart generation. It lacks operations for updating or deleting charts, configuring chart parameters, or retrieving chart metadata, which are common needs in this domain and could lead to agent failures.
Renders interactive Chart.js charts and dashboards inline in AI conversations. Supports bar, line, area, pie, doughnut, scatter, and radar charts with multi-chart dashboard grids.
Renders interactive Chart.js charts and dashboards inline in AI conversations.
Create, inspect, manage, and render charts and data visualizations as SVG/PNG or interactive embeds.
Turn rows into bar, line, pie and scatter chart images plus an optional PDF or HTML report.