Skip to main content
Glama
loaditoutadmin

loaditout-mcp-server

Official

install_pack

Install all skills from a curated agent pack in a single call. Choose a pack like 'research-agent' to set up multiple tools for a specific role.

Instructions

Install all skills from a curated Agent Pack in a single call. Returns a formatted text response listing each skill in the pack with its name, type, slug, and platform-specific install config. Packs are pre-built collections for specific workflows (e.g., 'research-agent' has browser, search, and memory tools). Use this instead of installing skills individually when setting up for a specific role. Do not use this if you only need one specific skill (use install_skill instead).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
slugYesPack slug. Examples: 'research-agent', 'full-stack-developer', 'devops-engineer', 'data-engineer', 'browser-automation'
agentYesTarget agent platform

Implementation Reference

  • The handler function that executes the install_pack tool logic. It calls the API endpoint /pack/{slug} with the agent parameter and formats the result showing pack name, outcome, skills list, and install command.
    async function handleInstallPack(args: {
      slug: string;
      agent: string;
    }): Promise<string> {
      const params = new URLSearchParams({ agent: args.agent });
      const result = (await fetchJSON(
        `${API_BASE}/pack/${encodeURIComponent(args.slug)}?${params.toString()}`
      )) as {
        name?: string;
        slug?: string;
        target_outcome?: string;
        skills?: Array<{
          slug?: string;
          name?: string;
          type?: string;
          install_config?: Record<string, unknown>;
        }>;
        install_all_command?: string;
        error?: string;
      };
    
      if (result.error) {
        return `Pack not found: ${result.error}`;
      }
    
      const packSkills = result.skills ?? [];
      const lines = [
        `Agent Pack: ${result.name ?? result.slug}`,
        `Outcome: ${result.target_outcome ?? "N/A"}`,
        `Skills: ${packSkills.length}`,
        `Install all: ${result.install_all_command ?? `npx loaditout add-pack ${args.slug}`}`,
        "",
        "Skills in this pack:",
        "",
      ];
    
      packSkills.forEach((s, i) => {
        lines.push(`${i + 1}. ${s.name ?? s.slug} (${s.type ?? "unknown"})`);
        lines.push(`   Slug: ${s.slug}`);
        if (s.install_config) {
          lines.push(`   Config: ${JSON.stringify(s.install_config)}`);
        }
        lines.push("");
      });
    
      return lines.join("\n");
    }
  • Input schema definition for the install_pack tool, specifying slug (string) and agent (enum with values: claude-code, cursor, codex-cli, windsurf, generic) as required parameters.
    name: "install_pack",
    description:
      "Install an entire Agent Pack (curated skill bundle). Returns install configs for all skills in the pack. Use this to quickly set up your agent for a specific role like research, full-stack development, DevOps, etc.",
    inputSchema: {
      type: "object" as const,
      properties: {
        slug: {
          type: "string",
          description:
            "Pack slug. Examples: 'research-agent', 'full-stack-developer', 'devops-engineer', 'data-engineer', 'browser-automation'",
        },
        agent: {
          type: "string",
          enum: ["claude-code", "cursor", "codex-cli", "windsurf", "generic"],
          description: "Target agent platform",
        },
      },
      required: ["slug", "agent"],
    },
  • Registration of the install_pack tool in the main switch/case dispatch block, routing tool calls to handleInstallPack with typed args.
    case "install_pack":
      resultText = await handleInstallPack(
        toolArgs as { slug: string; agent: string }
      );
  • The fetchJSON helper used by handleInstallPack to make HTTP GET requests to the API.
    function fetchJSON(url: string, extraHeaders?: Record<string, string>): Promise<unknown> {
      return new Promise((resolve, reject) => {
        const headers: Record<string, string> = {
          "User-Agent": `loaditout-mcp/${SERVER_VERSION}`,
          ...extraHeaders,
        };
        https
          .get(
            url,
            { headers },
            (res) => {
              if (res.statusCode === 301 || res.statusCode === 302) {
                const location = res.headers.location;
                if (location) {
                  fetchJSON(location).then(resolve, reject);
  • The API_BASE constant (https://loaditout.ai/api/agent) used to construct the pack API endpoint URL.
    const API_BASE = "https://loaditout.ai/api/agent";
Behavior4/5

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

Describes the return format (formatted text with skill details) and mentions packs are pre-built collections. With no annotations, this is sufficient behavioral disclosure for a non-destructive install action.

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?

Three well-structured sentences: purpose, return format, usage guidance. No filler or repetition. Front-loaded with action.

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

Completeness5/5

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

Covers all necessary aspects for a simple installation tool: what it does, what it returns, when to use it, parameter examples. No output schema needed.

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?

Both parameters are already described in schema (100% coverage). The description adds value by explaining the concept of packs and providing examples for the slug parameter, making the agent better informed.

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?

Clearly states it installs all skills from a curated pack in one call, and distinguishes from individual installation. Provides concrete examples of packs and their contents.

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

Usage Guidelines5/5

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

Explicitly states when to use this tool (setting up for a specific role) and when not to (only need one skill), including the alternative tool name (install_skill).

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/loaditoutadmin/loaditout-mcp-server'

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