Skip to main content
Glama
burkeholland

VS Code MCP Button Generator

by burkeholland

Generate install buttons

make_install_buttons

Generate VS Code Stable and Insiders MCP install button markdown for NPX-based servers to simplify setup instructions.

Instructions

Generate VS Code Stable and Insiders MCP install button markdown for an NPX-based server.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nameYesServer display name (e.g., 'supabase').
inputsNo
configNo

Implementation Reference

  • src/index.ts:106-130 (registration)
    Registers the 'make_install_buttons' tool with the MCP server, providing title, description, input schema, and an async handler that generates button markdown by calling generateButtonsMarkdown.
    server.registerTool(
      "make_install_buttons",
      {
        title: "Generate install buttons",
        description: "Generate VS Code Stable and Insiders MCP install button markdown for an NPX-based server.",
        inputSchema: {
          name: z.string().describe("Server display name (e.g., 'supabase')."),
          inputs: z.array(z.object({
            type: z.string(),
            id: z.string(),
            description: z.string().optional(),
            password: z.boolean().optional(),
          })).default([]),
          config: z.object({
            command: z.string().default("npx"),
            args: z.array(z.string()).default([]),
            env: z.record(z.string()).optional(),
          }).default({ command: "npx", args: [] }),
        }
      },
      async ({ name, inputs, config }) => {
        const markdown = generateButtonsMarkdown(name, inputs, config);
        return { content: [{ type: "text", text: markdown }] };
      }
    );
  • Core handler logic that generates the markdown for VS Code Stable and Insiders install buttons using the provided server name, inputs, and config.
    export function generateButtonsMarkdown(name: string, inputs: MCPInput[], config: CommandConfig): string {
      const base = "https://insiders.vscode.dev/redirect/mcp/install";
      const stableBadge = makeBadge("0098FF", "VS_Code");
      const insidersBadge = makeBadge("24bfa5", "VS_Code_Insiders");
    
      const stableLink = buildInstallLink(base, name, inputs, config, false);
      const insidersLink = buildInstallLink(base, name, inputs, config, true);
    
      const stable = `[![Install with NPX in VS Code](${stableBadge})](${stableLink})`;
      const insiders = `[![Install with NPX in VS Code Insiders](${insidersBadge})](${insidersLink})`;
      return `${stable}\n${insiders}`;
    }
  • Zod schema definitions for the tool inputs: InputSchema for individual inputs, ConfigSchema for command config, and MakeButtonsParams combining them with name.
    const InputSchema = z.object({
      type: z.string(), // "promptString" supported for now
      id: z.string(),
      description: z.string().optional(),
      password: z.boolean().optional(),
    });
    
    const ConfigSchema = z.object({
      command: z.string().default("npx"),
      args: z.array(z.string()).default([]),
      env: z.record(z.string()).optional(),
    });
    
    const MakeButtonsParams = z.object({
      name: z.string().min(1, "name is required"),
      inputs: z.array(InputSchema).default([]),
      config: ConfigSchema.default({ command: "npx", args: [] }),
    });
  • Helper function to build the install link URL parameters for both stable and insiders VS Code versions.
    function buildInstallLink(base: string, name: string, inputs: MCPInput[], config: CommandConfig, insiders = false) {
      const parts: string[] = [];
      parts.push(`name=${encodeURIComponent(name)}`);
      if (inputs && inputs.length) {
        parts.push(`inputs=${encodeURIComponent(JSON.stringify(inputs))}`);
      }
      parts.push(`config=${encodeURIComponent(JSON.stringify(config))}`);
      if (insiders) parts.push(`quality=insiders`);
      return `${base}?${parts.join('&')}`;
    }
  • Helper function to generate the badge image URL for VS Code install buttons.
    function makeBadge(color: string, label: string) {
      return `https://img.shields.io/badge/${encodeURIComponent(label)}-NPM-${color}?style=flat-square&logo=visualstudiocode&logoColor=white`;
    }
Behavior2/5

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. It states the tool generates markdown, implying a read-only output, but doesn't cover aspects like required permissions, rate limits, or what the generated markdown looks like (e.g., format, links). For a tool with no annotation coverage, this leaves significant behavioral gaps.

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, efficient sentence that front-loads the core purpose without unnecessary words. Every part ('Generate', 'VS Code Stable and Insiders MCP install button markdown', 'for an NPX-based server') contributes directly to understanding the tool's function.

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 complexity (3 parameters with nested objects, low schema coverage, no annotations, and no output schema), the description is insufficient. It doesn't explain the output format, parameter interactions, or behavioral constraints, leaving the agent with incomplete context for proper tool invocation.

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 description coverage is low at 33%, with only the 'name' parameter documented. The description adds no parameter-specific information beyond implying NPX-based server configuration, which loosely relates to the 'config' parameter but doesn't detail the 'inputs' array or other fields. This provides marginal value, aligning with the baseline for partial coverage.

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

Purpose4/5

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

The description clearly states the action ('Generate') and the output ('VS Code Stable and Insiders MCP install button markdown') with specific context ('for an NPX-based server'), which distinguishes it from sibling tools like 'copilot_buttons_from_github' that likely generate different types of buttons. However, it doesn't explicitly differentiate from all siblings (e.g., 'from_mcp_config'), keeping it from a perfect score.

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 like the sibling tools listed. It mentions the context ('NPX-based server') but doesn't specify prerequisites, exclusions, or comparisons to other button-generation tools, leaving the agent with minimal usage direction.

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/burkeholland/mcp-vsc-button-gen'

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