Skip to main content
Glama
rxolve

artscii

by rxolve
OverviewSchemaRelated ServersScoreDiscussions
TypeScript
Remote

diagram

Generate ASCII diagrams for flowcharts, boxes, trees, tables, sequence, timeline, bar, class, ER, mindmap, and gantt charts. Choose from unicode, rounded, or ascii border styles.

Instructions

Generate ASCII diagrams: flowcharts, boxes, trees, tables, sequence, timeline, bar, class, ER, mindmap, and gantt.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
typeYesDiagram type
nodesNoFlowchart: list of step labels
titleNoBox: title text
linesNoBox: body lines
rootNoTree/Mindmap: root node with label and optional children
headersNoTable: column headers
rowsNoTable: data rows
styleNoBorder style: unicode (default), rounded, or asciiunicode
actorsNoSequence: list of actor names
messagesNoSequence: messages between actors
eventsNoTimeline: list of events with label and description
itemsNoBar: list of items with label and numeric value
maxWidthNoBar: maximum bar width in characters (default 20)
classesNoClass: list of classes with name, properties, methods
entitiesNoER: list of entities with name and attributes
relationshipsNoER: relationships between entities (from, to, label like "1:N")
tasksNoGantt: tasks with label, start position, and duration
unitLabelNoGantt: label for time units (e.g. "weeks", "sprints")

Implementation Reference

  • src/mcp.ts:372-490 (registration)
    The 'diagram' tool is registered via server.tool() with Zod schema for all diagram types (flowchart, box, tree, table, sequence, timeline, bar, class, er, mindmap, gantt). The handler validates inputs then calls renderDiagram().
    server.tool(
  'diagram',
  'Generate ASCII diagrams: flowcharts, boxes, trees, tables, sequence, timeline, bar, class, ER, mindmap, and gantt.',
  {
    type: z.enum(['flowchart', 'box', 'tree', 'table', 'sequence', 'timeline', 'bar', 'class', 'er', 'mindmap', 'gantt']).describe('Diagram type'),
    nodes: z.array(z.string()).max(MAX_DIAGRAM_NODES).optional().describe('Flowchart: list of step labels'),
    title: z.string().optional().describe('Box: title text'),
    lines: z.array(z.string()).optional().describe('Box: body lines'),
    root: z.lazy(() => treeNodeSchema).optional().describe('Tree/Mindmap: root node with label and optional children'),
    headers: z.array(z.string()).optional().describe('Table: column headers'),
    rows: z.array(z.array(z.string())).max(MAX_DIAGRAM_ROWS).optional().describe('Table: data rows'),
    style: z.enum(['unicode', 'rounded', 'ascii']).default('unicode').describe('Border style: unicode (default), rounded, or ascii'),
    actors: z.array(z.string()).max(MAX_SEQUENCE_ACTORS).optional().describe('Sequence: list of actor names'),
    messages: z.array(z.object({ from: z.string(), to: z.string(), label: z.string() })).max(MAX_SEQUENCE_MESSAGES).optional().describe('Sequence: messages between actors'),
    events: z.array(z.object({ label: z.string(), description: z.string() })).max(MAX_TIMELINE_EVENTS).optional().describe('Timeline: list of events with label and description'),
    items: z.array(z.object({ label: z.string(), value: z.number() })).max(MAX_BAR_ITEMS).optional().describe('Bar: list of items with label and numeric value'),
    maxWidth: z.number().min(1).max(MAX_BAR_WIDTH).optional().describe('Bar: maximum bar width in characters (default 20)'),
    classes: z.array(classDefSchema).max(MAX_DIAGRAM_NODES).optional().describe('Class: list of classes with name, properties, methods'),
    entities: z.array(entitySchema).max(MAX_DIAGRAM_NODES).optional().describe('ER: list of entities with name and attributes'),
    relationships: z.array(relationshipSchema).max(MAX_SEQUENCE_MESSAGES).optional().describe('ER: relationships between entities (from, to, label like "1:N")'),
    tasks: z.array(ganttTaskSchema).max(MAX_DIAGRAM_ROWS).optional().describe('Gantt: tasks with label, start position, and duration'),
    unitLabel: z.string().optional().describe('Gantt: label for time units (e.g. "weeks", "sprints")'),
  },
  async ({ type, nodes, title, lines, root, headers, rows, style, actors, messages, events, items, maxWidth, classes, entities, relationships, tasks, unitLabel }) => {
    try {
      let input;
      switch (type) {
        case 'flowchart':
          if (!nodes || nodes.length === 0) {
            return { content: [{ type: 'text', text: 'Error: "nodes" is required for flowchart' }], isError: true };
          }
          input = { type: 'flowchart' as const, nodes, style };
          break;
        case 'box':
          if (!title) {
            return { content: [{ type: 'text', text: 'Error: "title" is required for box' }], isError: true };
          }
          input = { type: 'box' as const, title, lines: lines ?? [], style };
          break;
        case 'tree':
          if (!root) {
            return { content: [{ type: 'text', text: 'Error: "root" is required for tree' }], isError: true };
          }
          if (!validateTreeDepth(root, 1)) {
            return { content: [{ type: 'text', text: `Error: tree depth exceeds maximum of ${MAX_TREE_DEPTH}` }], isError: true };
          }
          input = { type: 'tree' as const, root };
          break;
        case 'table':
          if (!headers || headers.length === 0) {
            return { content: [{ type: 'text', text: 'Error: "headers" is required for table' }], isError: true };
          }
          input = { type: 'table' as const, headers, rows: rows ?? [], style };
          break;
        case 'sequence':
          if (!actors || actors.length === 0) {
            return { content: [{ type: 'text', text: 'Error: "actors" is required for sequence' }], isError: true };
          }
          if (!messages || messages.length === 0) {
            return { content: [{ type: 'text', text: 'Error: "messages" is required for sequence' }], isError: true };
          }
          for (const msg of messages) {
            if (!actors.includes(msg.from)) {
              return { content: [{ type: 'text', text: `Error: actor "${msg.from}" not in actors list` }], isError: true };
            }
            if (!actors.includes(msg.to)) {
              return { content: [{ type: 'text', text: `Error: actor "${msg.to}" not in actors list` }], isError: true };
            }
          }
          input = { type: 'sequence' as const, actors, messages };
          break;
        case 'timeline':
          if (!events || events.length === 0) {
            return { content: [{ type: 'text', text: 'Error: "events" is required for timeline' }], isError: true };
          }
          input = { type: 'timeline' as const, events };
          break;
        case 'bar':
          if (!items || items.length === 0) {
            return { content: [{ type: 'text', text: 'Error: "items" is required for bar' }], isError: true };
          }
          input = { type: 'bar' as const, items, maxWidth };
          break;
        case 'class':
          if (!classes || classes.length === 0) {
            return { content: [{ type: 'text', text: 'Error: "classes" is required for class diagram' }], isError: true };
          }
          input = { type: 'class' as const, classes, style };
          break;
        case 'er':
          if (!entities || entities.length === 0) {
            return { content: [{ type: 'text', text: 'Error: "entities" is required for ER diagram' }], isError: true };
          }
          input = { type: 'er' as const, entities, relationships: relationships ?? [] };
          break;
        case 'mindmap':
          if (!root) {
            return { content: [{ type: 'text', text: 'Error: "root" is required for mindmap' }], isError: true };
          }
          if (!validateTreeDepth(root, 1)) {
            return { content: [{ type: 'text', text: `Error: tree depth exceeds maximum of ${MAX_TREE_DEPTH}` }], isError: true };
          }
          input = { type: 'mindmap' as const, root };
          break;
        case 'gantt':
          if (!tasks || tasks.length === 0) {
            return { content: [{ type: 'text', text: 'Error: "tasks" is required for gantt chart' }], isError: true };
          }
          input = { type: 'gantt' as const, tasks, unitLabel };
          break;
      }
      const diagram = renderDiagram(input);
      return { content: [{ type: 'text', text: diagram }] };
    } catch (err: unknown) {
      const e = err as { message?: string };
      return { content: [{ type: 'text', text: `Error: ${e.message ?? 'Diagram generation failed'}` }], isError: true };
    }
  }
);
  • src/diagram.ts:426-451 (handler)
    The renderDiagram() function is the main dispatcher that routes to the specific render function based on the diagram type.
    export function renderDiagram(input: DiagramInput): string {
  switch (input.type) {
    case 'flowchart':
      return renderFlowchart(input.nodes, input.style);
    case 'box':
      return renderBox(input.title, input.lines, input.style);
    case 'tree':
      return renderTree(input.root);
    case 'table':
      return renderTable(input.headers, input.rows, input.style);
    case 'sequence':
      return renderSequence(input.actors, input.messages);
    case 'timeline':
      return renderTimeline(input.events);
    case 'bar':
      return renderBar(input.items, input.maxWidth);
    case 'class':
      return renderClass(input.classes, input.style);
    case 'er':
      return renderER(input.entities, input.relationships);
    case 'mindmap':
      return renderMindmap(input.root);
    case 'gantt':
      return renderGantt(input.tasks, input.unitLabel);
  }
}
  • src/diagram.ts:37-48 (schema)
    The DiagramInput type defines the discriminated union of all supported diagram input types with their required and optional fields.
    export type DiagramInput =
  | { type: 'flowchart'; nodes: string[]; style?: BoxStyle }
  | { type: 'box'; title: string; lines: string[]; style?: BoxStyle }
  | { type: 'tree'; root: TreeNode }
  | { type: 'table'; headers: string[]; rows: string[][]; style?: BoxStyle }
  | { type: 'sequence'; actors: string[]; messages: SequenceMessage[] }
  | { type: 'timeline'; events: { label: string; description: string }[] }
  | { type: 'bar'; items: { label: string; value: number }[]; maxWidth?: number }
  | { type: 'class'; classes: ClassDef[]; style?: BoxStyle }
  | { type: 'er'; entities: Entity[]; relationships: Relationship[] }
  | { type: 'mindmap'; root: TreeNode }
  | { type: 'gantt'; tasks: GanttTask[]; unitLabel?: string };
  • src/diagram.ts:89-111 (helper)
    renderFlowchart() - renders vertical flowcharts with connected boxes (one of the 11 diagram rendering helpers).
    export function renderFlowchart(nodes: string[], style: BoxStyle = 'unicode'): string {
  if (nodes.length === 0) return '';
  const c = BOX_CHARS[style];
  const maxLen = Math.max(...nodes.map((n) => n.length));
  const boxWidth = maxLen + 4; // 2 padding + 2 border
  const inner = boxWidth - 2;
  const centerCol = Math.floor(boxWidth / 2);

  const out: string[] = [];
  for (let i = 0; i < nodes.length; i++) {
    // box
    out.push(c.tl + c.t.repeat(inner) + c.tr);
    out.push(c.l + ' ' + padCenter(nodes[i], inner - 2) + ' ' + c.r);
    out.push(c.bl + c.b.repeat(Math.floor((inner - 1) / 2)) + (i < nodes.length - 1 ? c.mt : c.b) + c.b.repeat(inner - Math.floor((inner - 1) / 2) - 1) + c.br);

    // connector
    if (i < nodes.length - 1) {
      out.push(' '.repeat(centerCol) + c.l);
      out.push(' '.repeat(centerCol) + '\u25BC');
    }
  }
  return out.join('\n');
}
  • src/mcp.ts:336-369 (helper)
    Helper Zod schemas: treeNodeSchema, classDefSchema, entitySchema, relationshipSchema, ganttTaskSchema, and validateTreeDepth() used by the diagram tool.
    const treeNodeSchema: z.ZodType<TreeNode> = z.object({
  label: z.string(),
  children: z.lazy(() => treeNodeSchema.array()).optional(),
});

function validateTreeDepth(node: TreeNode, depth: number): boolean {
  if (depth > MAX_TREE_DEPTH) return false;
  for (const child of node.children ?? []) {
    if (!validateTreeDepth(child, depth + 1)) return false;
  }
  return true;
}

const classDefSchema = z.object({
  name: z.string(),
  properties: z.array(z.string()).optional(),
  methods: z.array(z.string()).optional(),
});

const entitySchema = z.object({
  name: z.string(),
  attributes: z.array(z.string()).optional(),
});

const relationshipSchema = z.object({
  from: z.string(),
  to: z.string(),
  label: z.string(),
});

const ganttTaskSchema = z.object({
  label: z.string(),
  start: z.number().min(0),
  duration: z.number().min(1),

Tool Definition Quality

B3.2/5.0
Behavior2/5

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

With no annotations, the description bears the full burden of disclosing behavior. It only says 'Generate ASCII diagrams' without specifying side effects, output format, required permissions, or any constraints beyond those in the schema. This is insufficient for a tool that accepts many parameters.

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

Conciseness5/5

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

The description is a single, front-loaded sentence that efficiently conveys the tool's purpose and scope without unnecessary words.

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

Completeness2/5

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

Given the tool's 18 parameters and no output schema, the description is too brief. It lacks context on how parameters interact, expected output format (ASCII art string), and example usage, making it insufficient for complex multi-type diagram generation.

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?

Schema coverage is 100% with good descriptions per parameter. The tool description does not add parameter-specific meaning beyond the schema, so it meets the baseline for high coverage.

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 explicitly states 'Generate ASCII diagrams' and lists 11 specific diagram types, making the tool's purpose clear and distinguishing it from sibling tools like 'chart' which likely produce different visual outputs.

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?

The description provides no guidance on when to use this tool versus alternatives, nor does it mention limitations, prerequisites, or when not to use it. An agent would have to infer usage solely from the tool name and description.

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/rxolve/artscii'

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