Click on "Install 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., "@chartforge-mcp Generate a pie chart of sales by region"
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.
Generate stunning, publication-quality charts and diagrams from natural language — directly inside Claude.
Add this to your claude_desktop_config.json:
{
"mcpServers": {
"chartforge": {
"command": "npx",
"args": ["chartforge-mcp"],
"env": {
"CHARTFORGE_API_KEY": "your_api_key_here"
}
}
}
}Variable | Required | Description |
| Yes | Your API key from chartforgeai.com |
| No | Custom API URL (default: |
Related MCP server: ML Research MCP
generate_chartGenerate a chart from a natural language description.
Parameters:
prompt (required): Description of the chart
style (optional): Style preset — midnight, frost, ember, minimal, corporate, neon, light
width (optional): Width in pixels (default: 1200)
height (optional): Height in pixels (default: 800)
refine_chartModify a previously generated chart.
Parameters:
chartId (required): Chart ID from a previous generation
modification (required): What to change
list_stylesList available style presets with descriptions.
"Create a bar chart showing quarterly revenue from $2M to $18M over 3 years"
"System architecture diagram for a microservices backend"
"Sankey diagram of marketing budget flow through channels to conversions"
Generate a stunning, publication-quality chart or diagram from a natural language description. Returns a PNG image.
| Name | Required | Description | Default |
|---|---|---|---|
| style | No | Visual style preset. Default: auto (AI chooses best style). | |
| width | No | Width in pixels. Default: 1200 | |
| height | No | Height in pixels. Default: 800 | |
| prompt | Yes | Description of the chart or diagram to generate. Be specific about data, labels, and what you want to visualize. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present, so the description carries the full burden. It only states the output format (PNG) but does not disclose behavioral traits like rate limits, authentication, error handling, or generation time.
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?
Two sentences with no redundancy. The first sentence front-loads the purpose with specificity, and the second states the output format. 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?
The tool is complex (generative AI from NL), but the description only covers output format. Missing details on behavior for ambiguous prompts, data handling, or quality expectations. Adequate but not thorough.
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 coverage is 100%, so the baseline is 3. The main description adds no significant parameter details beyond the schema descriptions, which already cover defaults and guidance for the prompt parameter.
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 tool generates a chart or diagram from natural language and returns a PNG. This distinguishes it from sibling tools like list_styles (list styles) and refine_chart (modify existing chart).
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 implies the tool is for generating new charts from descriptions, but does not explicitly mention when to use it vs. list_styles or refine_chart, nor provide any exclusions or prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List available chart style presets with descriptions.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden. It correctly suggests a read-only operation (listing), but does not disclose potential aspects like performance or authentication needs. For a simple list, this is adequate but not thorough.
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, front-loaded sentence with no unnecessary words. It efficiently conveys the tool's purpose.
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?
Given the tool has no parameters and no output schema, the description is complete and sufficient for an agent to understand and invoke the tool correctly.
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?
There are no parameters, so schema coverage is 100% by default. The description adds 'with descriptions' which clarifies the content beyond a bare list, providing marginal added value.
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 ('List') and the resource ('available chart style presets with descriptions'), and it distinguishes this tool from siblings 'generate_chart' and 'refine_chart' by focusing on listing presets.
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 implies usage for discovering styles before chart creation or refinement, but it does not explicitly state when to use or provide alternatives. Given the simplicity, the implied context is acceptable but not explicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Modify an existing chart. Provide the chart ID from a previous generation and describe what to change.
| Name | Required | Description | Default |
|---|---|---|---|
| chartId | Yes | The chart ID from a previous generate_chart call | |
| modification | Yes | What to change about the chart, e.g. 'make the bars blue', 'add a title', 'remove the legend' |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It indicates that the tool modifies an existing chart (mutation), but does not disclose potential side effects, required permissions, or whether changes are reversible. For a simple modification tool, this is adequate but could be more informative.
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 two concise sentences, front-loaded with the action and requirements. No unnecessary information.
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?
Given the tool has two simple parameters and no output schema, the description is sufficiently complete for an AI agent to understand how to use it. It could mention what the tool returns, but the absence is not critical.
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?
The input schema has 100% coverage with descriptions for both parameters. The tool description adds value by providing context: 'chart ID from a previous generate_chart call' for chartId and examples like 'make the bars blue' for modification. This goes beyond the schema descriptions.
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 (modify), resource (existing chart), and required inputs (chart ID from previous generate_chart call and modification description). It distinguishes from sibling tools: generate_chart creates new charts, list_styles lists available styles.
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 explains when to use the tool (when you have an existing chart and want to modify it) and what inputs to provide. It does not explicitly state when not to use or mention alternatives, but the context from sibling tools makes it clear.
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. Dates show when Glama detected each change.
v0.1.2generate_chartlist_stylesrefine_chartEach tool has a clearly distinct purpose: generating a new chart, listing styles, and refining an existing chart. No overlaps or ambiguity.
All tool names follow a consistent verb_noun pattern (generate_chart, list_styles, refine_chart), making them predictable.
3 tools is on the lower end but still reasonable for a focused chart generation domain. The set covers the core workflow without being too thin.
The tools allow creating, refining, and style selection, but lack retrieval or management of previously generated charts. This is a notable gap for a typical lifecycle.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Generate and edit images and create short videos inside Claude. Prepaid credits, no subscription.
Create, inspect, manage, and render charts and data visualizations as SVG/PNG or interactive embeds.
Let Claude, Cursor, or ChatGPT author Mermaid diagrams your team can read and share.
Renders interactive Chart.js charts and dashboards inline in AI conversations.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/crawde/chartforge-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
