Skip to main content
Glama

generate_mermaid_diagram

Convert mermaid syntax into diagrams and charts. Supports themes, background color, and multiple output formats including SVG and PNG.

Instructions

Generate mermaid diagram and chart with mermaid syntax dynamically. Mermaid is a JavaScript based diagramming and charting tool that uses Markdown-inspired text definitions and a renderer to create and modify complex diagrams. The main purpose of Mermaid is to help documentation catch up with development.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
mermaidYesThe mermaid diagram syntax used to be generated, such as, graph TD; A-->B; A-->C; B-->D; C-->D;.
themeNoTheme for the diagram (optional). Default is 'default'.default
backgroundColorNoBackground color for the diagram (optional). Default is 'white'.white
outputTypeNoThe output type of the diagram. Can be 'base64', 'svg', 'mermaid', 'file', 'svg_url', or 'png_url'. Default is 'base64'. 'base64' returns PNG image as base64 encoded string. 'file' saves the PNG image to disk. The *_url options return public mermaid.ink links for remote-friendly sharing.base64

Implementation Reference

  • The tool handler registered on the MCP server. It receives requests for 'generate_mermaid_diagram', validates with zod schema, calls renderMermaid() to generate the diagram, and handles all output types (base64, svg, mermaid, file, svg_url, png_url).
    function setupToolHandlers(server: McpServer): void {
      server.server.setRequestHandler(ListToolsRequestSchema, async () => ({
        tools: [tool],
      }));
    
      server.server.setRequestHandler(CallToolRequestSchema, async (request) => {
        if (request.params.name === tool.name) {
          try {
            const args = request.params.arguments || {};
            // Use safeParse instead of parse and try-catch.
            const result = schema.safeParse(args);
            if (!result.success) {
              throw new McpError(
                ErrorCode.InvalidParams,
                `Invalid parameters: ${result.error.message}`,
              );
            }
    
            const { mermaid, theme, backgroundColor, outputType = "base64" } = args;
            Logger.info(
              `Rendering diagram (outputType=${outputType}, theme=${theme ?? "default"})`,
            );
            const { id, svg, screenshot } = await withRetry(
              () =>
                renderMermaid(
                  mermaid as string,
                  theme as string,
                  backgroundColor as string,
                ),
              { maxAttempts: 3, delayMs: 500 },
            );
    
            if (outputType === "mermaid") {
              return {
                content: [
                  {
                    type: "text",
                    text: mermaid,
                  },
                ],
              };
            }
            if (outputType === "svg") {
              return {
                content: [
                  {
                    type: "text",
                    text: svg,
                  },
                ],
              };
            }
            if (outputType === "svg_url" || outputType === "png_url") {
              const variant = outputType === "svg_url" ? "svg" : "img";
              const url = createMermaidInkUrl(
                mermaid as string,
                variant,
                (theme as string) || "default",
              );
              return {
                content: [
                  {
                    type: "text",
                    text: url,
                  },
                ],
              };
            }
            if (outputType === "file") {
              if (!screenshot) {
                throw new McpError(
                  ErrorCode.InternalError,
                  "Failed to generate screenshot for file output.",
                );
              }
    
              // Create a unique filename with timestamp and random suffix
              const timestamp = new Date().toISOString().replace(/[:.]/g, "-");
              const randomSuffix = Math.random().toString(36).substring(2, 8);
              const filename = `mermaid-${timestamp}-${randomSuffix}.png`;
    
              // Use current working directory to save the file
              const filePath = path.resolve(process.cwd(), filename);
    
              try {
                fs.writeFileSync(filePath, screenshot);
                return {
                  content: [
                    {
                      type: "text",
                      text: `Mermaid diagram saved to file: ${filePath}`,
                    },
                  ],
                };
              } catch (fileError) {
                throw new McpError(
                  ErrorCode.InternalError,
                  `Failed to save file: ${fileError instanceof Error ? fileError.message : "Unknown file error"}`,
                );
              }
            }
            return {
              content: [
                {
                  type: "image",
                  data: screenshot?.toString("base64"),
                  mimeType: "image/png",
                },
              ],
            };
            // biome-ignore lint/suspicious/noExplicitAny: <explanation>
          } catch (error: any) {
            Logger.error("Tool execution failed", error);
            if (error instanceof McpError) throw error;
            throw new McpError(
              ErrorCode.InternalError,
              `Failed to generate mermaid: ${error?.message || "Unknown error."}`,
            );
          }
        } else {
          throw new McpError(
            ErrorCode.MethodNotFound,
            `Unknown tool: ${request.params.name}.`,
          );
        }
      });
    }
  • Zod schema defining the tool's input: mermaid (string, required), theme (enum, optional, default 'default'), backgroundColor (string, optional, default 'white'), outputType (enum, optional, default 'base64').
    export const schema = z.object({
      mermaid: z
        .string()
        .describe(`The mermaid diagram syntax used to be generated, such as, graph TD;
    A-->B;
    A-->C;
    B-->D;
    C-->D;.`)
        .nonempty({ message: "The mermaid string cannot be empty." }),
      theme: z
        .enum(["default", "base", "forest", "dark", "neutral"])
        .describe("Theme for the diagram (optional). Default is 'default'.")
        .optional()
        .default("default"),
      backgroundColor: z
        .string()
        .describe(
          "Background color for the diagram (optional). Default is 'white'.",
        )
        .optional()
        .default("white"),
      outputType: z
        .enum(["base64", "svg", "mermaid", "file", "svg_url", "png_url"])
        .describe(
          "The output type of the diagram. Can be 'base64', 'svg', 'mermaid', 'file', 'svg_url', or 'png_url'. Default is 'base64'. 'base64' returns PNG image as base64 encoded string. 'file' saves the PNG image to disk. The *_url options return public mermaid.ink links for remote-friendly sharing.",
        )
        .optional()
        .default("base64"),
    });
  • Tool registration object with name 'generate_mermaid_diagram', description, and inputSchema derived from the zod schema via zodToJsonSchema.
    export const tool = {
      name: "generate_mermaid_diagram",
      description:
        "Generate mermaid diagram and chart with mermaid syntax dynamically. Mermaid is a JavaScript based diagramming and charting tool that uses Markdown-inspired text definitions and a renderer to create and modify complex diagrams. The main purpose of Mermaid is to help documentation catch up with development.",
      inputSchema: zodToJsonSchema(schema),
    };
  • Core rendering helper function renderMermaid() which uses mermaid-isomorphic to render mermaid syntax to SVG/screenshot with configurable theme and background color.
    export async function renderMermaid(
      mermaid: string,
      theme = "default",
      backgroundColor = "white",
    ): Promise<RenderResult> {
      if (!renderer) renderer = createMermaidRenderer();
      const cssContent = `svg { background: ${backgroundColor}; }`;
      const cssTmpPath = path.join(os.tmpdir(), "mermaid-tmp-css.css");
      fs.writeFileSync(cssTmpPath, cssContent);
    
      const r = await renderer([mermaid], {
        // Image is needed.
        screenshot: true,
        css: cssTmpPath,
        mermaidConfig: {
          // biome-ignore lint/suspicious/noExplicitAny: <explanation>
          theme: theme as any,
        },
      });
      const r0 = r[0] as PromiseSettledResult<RenderResult>;
      return r0.status === "fulfilled" ? r0.value : Promise.reject(r0.reason);
    }
  • Helper that creates public mermaid.ink URLs for svg_url and png_url output types.
    export function createMermaidInkUrl(
      mermaid: string,
      variant: "svg" | "img",
      theme = "default",
    ): string {
      const payload = JSON.stringify({ code: mermaid, mermaid: { theme } });
      const encoded = encodeMermaidToBase64Url(payload);
      return `https://mermaid.ink/${variant}/pako:${encoded}`;
    }
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description fails to disclose behavioral traits such as side effects, performance, or limitations. It only broadly states dynamic generation without specifics.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise with two sentences, but the second sentence focuses on Mermaid's general purpose rather than the tool's specific behavior. No filler words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description does not explain the output format or how to use the returned data. With no output schema, relying on the outputType parameter is insufficient for complete understanding.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 100% description coverage, so the parameters are already well-documented. The description adds no additional meaning beyond what the schema provides.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: generating mermaid diagrams and charts dynamically. It explains what Mermaid is, providing context for the tool's functionality.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool or when not to use it. There are no alternatives mentioned, and the description lacks explicit usage context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/hustcc/mcp-mermaid'

If you have feedback or need assistance with the MCP directory API, please join our Discord server