Skip to main content
Glama

upload_template

Upload a template file to create a reusable versioned template. Use the returned Template ID with render_document to generate documents.

Instructions

Upload and store a reusable Carbone template. Once uploaded, use render_document with the returned Template ID to generate documents from it. Supports versioning: multiple versions can live under a single stable Template ID, with deployedAt controlling which version is active. Accepted formats: DOCX, XLSX, PPTX, ODT, ODS, ODP, ODG, HTML, XHTML, IDML, XML, Markdown, PDF, and more.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
templateYesThe template file. Accepts a local file path (e.g. /home/user/invoice.docx), a URL (https://example.com/template.docx), or a base64-encoded string. Supported formats: DOCX, XLSX, PPTX, ODT, ODS, ODP, ODG, HTML, XHTML, IDML, XML, Markdown (MD), PDF, and more. Full list: https://carbone.io/documentation/developer/http-api/generate-reports.html#output-file-type
nameYesDisplay name for the template (e.g. "Invoice Template", "NDA Contract").
idNoExisting Template ID (64-bit format) to add this upload to its version history. If omitted, a new Template ID is generated. Providing a Version ID (SHA-256) is not allowed and will cause an error.
versioningNoEnable template versioning (default: true). When true, a stable Template ID is generated and multiple versions can be managed under it. When false, behaves as legacy mode and returns only a templateId (SHA-256 hash).
categoryNoGroup templates into folders/categories (e.g. "invoices", "legal", "hr").
commentNoFree-text comment to describe the template version or its purpose.
tagsNoTags for searchability and filtering (e.g. ["sales", "billing", "v2"]).
sampleNoSample input data attached to the template for testing in Carbone Studio. Each item must include data, complement, translations, and enum objects.
deployedAtNoUTC Unix timestamp (seconds) to set as the deployment time for this version. Carbone uses the version with the most recent deployedAt when rendering via Template ID. Use 42000000000 to deploy immediately (special "NOW" sentinel value).
expireAtNoUTC Unix timestamp (seconds) at which this template will be automatically deleted. Use 42000000000 to delete immediately (special "NOW" sentinel value).

Implementation Reference

  • The handleUploadTemplate function that executes the upload_template tool logic. It resolves the template file (path/URL/base64), calls the Carbone client's uploadTemplate, and formats the result (versioned or legacy).
    export async function handleUploadTemplate(
      args: {
        template:    string;
        name:        string;
        id?:         string;
        versioning?: boolean;
        category?:   string;
        comment?:    string;
        tags?:       string[];
        sample?:     Array<{ data: Record<string, unknown>; complement: Record<string, unknown>; translations: Record<string, unknown>; enum: Record<string, unknown> }>;
        deployedAt?: number;
        expireAt?:   number;
      },
      client: CarboneClient,
      options?: CallOptions
    ) {
      try {
        const template = await resolveFileInput(args.template);
        const result: UploadTemplateResult = await client.uploadTemplate({ ...args, template }, options);
    
        // The API returns different shapes depending on whether versioning is enabled
        const lines: string[] = ['Template uploaded successfully!', ''];
        if ('id' in result) {
          lines.push(`Template ID : ${result.id}`);
          lines.push(`Version ID  : ${result.versionId}`);
          if (result.type) lines.push(`Type        : ${result.type}`);
          if (result.size) lines.push(`Size        : ${result.size} bytes`);
        } else {
          // Legacy / versioning disabled response
          lines.push(`Template ID : ${result.templateId}`);
        }
        lines.push(`Name        : ${args.name}`);
    
        return { content: [{ type: 'text' as const, text: lines.join('\n') }] };
      } catch (error) {
        return {
          isError: true,
          content: [{ type: 'text' as const, text: formatError(error) }],
        };
      }
    }
  • uploadTemplateSchema defines the input schema for the upload_template tool using Zod: template (file path/URL/base64), name, optional id, versioning, category, comment, tags, sample data, deployedAt, expireAt.
    export const uploadTemplateSchema = {
      template: z
        .string()
        .min(1)
        .describe(
          'The template file. Accepts a local file path (e.g. /home/user/invoice.docx), ' +
          'a URL (https://example.com/template.docx), or a base64-encoded string. ' +
          'Supported formats: DOCX, XLSX, PPTX, ODT, ODS, ODP, ODG, HTML, XHTML, IDML, XML, Markdown (MD), PDF, and more. ' +
          'Full list: https://carbone.io/documentation/developer/http-api/generate-reports.html#output-file-type'
        ),
      name: z
        .string()
        .min(1)
        .describe('Display name for the template (e.g. "Invoice Template", "NDA Contract").'),
      id: z
        .string()
        .optional()
        .describe(
          'Existing Template ID (64-bit format) to add this upload to its version history. ' +
          'If omitted, a new Template ID is generated. ' +
          'Providing a Version ID (SHA-256) is not allowed and will cause an error.'
        ),
      versioning: z
        .boolean()
        .optional()
        .default(true)
        .describe(
          'Enable template versioning (default: true). ' +
          'When true, a stable Template ID is generated and multiple versions can be managed under it. ' +
          'When false, behaves as legacy mode and returns only a templateId (SHA-256 hash).'
        ),
      category: z
        .string()
        .optional()
        .describe('Group templates into folders/categories (e.g. "invoices", "legal", "hr").'),
      comment: z
        .string()
        .optional()
        .describe('Free-text comment to describe the template version or its purpose.'),
      tags: z
        .array(z.string())
        .optional()
        .describe('Tags for searchability and filtering (e.g. ["sales", "billing", "v2"]).'),
      sample: z
        .array(
          z.object({
            data:         z.record(z.string(), z.unknown()).describe('JSON dataset for {d.} tags.'),
            complement:   z.record(z.string(), z.unknown()).describe('Extra data for {c.} tags.'),
            translations: z.record(z.string(), z.unknown()).describe('Localization map for {t()} tags.'),
            enum:         z.record(z.string(), z.unknown()).describe('Enumerations for :convEnum() formatter.'),
          })
        )
        .optional()
        .describe(
          'Sample input data attached to the template for testing in Carbone Studio. ' +
          'Each item must include data, complement, translations, and enum objects.'
        ),
      deployedAt: z
        .number()
        .int()
        .optional()
        .describe(
          'UTC Unix timestamp (seconds) to set as the deployment time for this version. ' +
          'Carbone uses the version with the most recent deployedAt when rendering via Template ID. ' +
          'Use 42000000000 to deploy immediately (special "NOW" sentinel value).'
        ),
      expireAt: z
        .number()
        .int()
        .optional()
        .describe(
          'UTC Unix timestamp (seconds) at which this template will be automatically deleted. ' +
          'Use 42000000000 to delete immediately (special "NOW" sentinel value).'
        ),
    };
  • Registration of upload_template tool on the MCP server via server.registerTool with the tool name, description, schema, and handler callback.
    server.registerTool(
      uploadTemplateToolName,
      { description: uploadTemplateDescription, inputSchema: uploadTemplateSchema },
      (args, extra) => handleUploadTemplate(args, client, { apiKey: extra.authInfo?.token })
    );
  • Alternative Zod schema for upload_template validation (UploadTemplateSchema) used for general validation purposes.
    export const UploadTemplateSchema = z.object({
      template:   z.string().min(1, 'Template content required'),
      name:       z.string().min(1, 'Template name required'),
      id:         z.string().optional(),
      versioning: z.boolean().optional().default(true),
      category:   z.string().optional(),
      comment:    z.string().optional(),
      tags:       z.array(z.string()).optional(),
      sample:     z.array(SampleItemSchema).optional(),
      deployedAt: z.number().int().optional(),
      expireAt:   z.number().int().optional(),
    });
  • resolveFileInput helper that converts local file paths, URLs, or base64 strings into base64 content for upload. Used by handleUploadTemplate to resolve the template argument.
    export async function resolveFileInput(input: string): Promise<string> {
      // Remote URL
      if (input.startsWith('http://') || input.startsWith('https://')) {
        const response = await fetch(input);
        if (!response.ok) {
          throw new Error(
            `Failed to download file from URL: ${response.status} ${response.statusText}`
          );
        }
        const buffer = Buffer.from(await response.arrayBuffer());
        return buffer.toString('base64');
      }
    
      // Local file path: absolute (/…), relative (./… or ../…), home (~), or Windows (C:\…)
      const isLocalPath =
        input.startsWith('/') ||
        input.startsWith('./') ||
        input.startsWith('../') ||
        input.startsWith('~') ||
        /^[A-Za-z]:[/\\]/.test(input);
    
      if (isLocalPath) {
        const resolvedPath = input.startsWith('~')
          ? input.replace('~', process.env['HOME'] ?? process.env['USERPROFILE'] ?? '~')
          : input;
        const buffer = await readFile(resolvedPath);
        return buffer.toString('base64');
      }
    
      // Already base64
      return input;
    }
Behavior2/5

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

No annotations are provided, so the description must carry full burden. It mentions versioning and error on Version ID but lacks details on return values, auth requirements, rate limits, or file size limits. Insufficient for a complex tool with 10 parameters.

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 a single paragraph of 4 sentences, concise and front-loaded with the main purpose. No wasted words, but could be more structured with bullet points for clarity.

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 complexity (10 params, no output schema, no annotations), the description is incomplete. It omits return value details (only implies Template ID), error handling, and edge cases like oversized files. More context needed for full agent guidance.

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

Parameters4/5

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

Schema description coverage is 100% with detailed param descriptions. The tool description adds value by explaining versioning and deployedAt context, supplementing the schema without redundancy.

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 action (upload and store), resource (Carbone template), and subsequent usage (render with returned Template ID). It differentiates from sibling tools like download_template or delete_template by focusing on upload and versioning.

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

Usage Guidelines4/5

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

The description explicitly says to use render_document after upload and explains versioning with deployedAt. While it doesn't list when not to use it, it implies usage context and distinguishes from siblings implicitly.

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/carboneio/carbone-mcp'

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