Skip to main content
Glama
danielrosehill

Daniel Rosehill's MCP Installer

install_all

Install multiple MCP servers to Claude Code, Cursor, or VS Code clients with optional filtering for essential tools and secret management.

Instructions

Install all MCPs (or just essential ones) to a client. Skips MCPs that need secrets unless provided.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
clientNoTarget client to install toclaude-code
essential_onlyNoOnly install MCPs marked as essential
skip_existingNoSkip MCPs that are already installed
secretsNoKey-value pairs of secrets for all MCPs (keys should match what each MCP needs)

Implementation Reference

  • Handler for the 'install_all' MCP tool call. Parses input arguments and delegates to the installAll helper function, returning the result as JSON.
    case 'install_all': {
      const client = (args?.client as ClientType) || 'claude-code';
      const essentialOnly = args?.essential_only as boolean || false;
      const skipExisting = args?.skip_existing as boolean !== false;
      const secrets = (args?.secrets as Record<string, string>) || {};
    
      const result = await installAll(client, {
        essentialOnly,
        skipExisting,
        providedSecrets: secrets
      });
    
      return {
        content: [{
          type: 'text',
          text: JSON.stringify(result, null, 2)
        }]
      };
    }
  • Input schema and metadata definition for the 'install_all' tool, registered in the tools list.
    {
      name: 'install_all',
      description: 'Install all MCPs (or just essential ones) to a client. Skips MCPs that need secrets unless provided.',
      inputSchema: {
        type: 'object',
        properties: {
          client: {
            type: 'string',
            enum: ['claude-code', 'cursor', 'vscode'],
            description: 'Target client to install to',
            default: 'claude-code'
          },
          essential_only: {
            type: 'boolean',
            description: 'Only install MCPs marked as essential',
            default: false
          },
          skip_existing: {
            type: 'boolean',
            description: 'Skip MCPs that are already installed',
            default: true
          },
          secrets: {
            type: 'object',
            description: 'Key-value pairs of secrets for all MCPs (keys should match what each MCP needs)',
            additionalProperties: { type: 'string' }
          }
        }
      }
    },
  • Core helper function that implements the logic to install all (or essential) MCPs to a specified client, handling secrets, skips, and aggregating results.
    export async function installAll(
      client: ClientType,
      options: {
        essentialOnly?: boolean;
        skipExisting?: boolean;
        providedSecrets?: Record<string, string>;
      } = {}
    ): Promise<BatchInstallResult> {
      const mcps = await listMcps({
        essentialOnly: options.essentialOnly,
        enabledOnly: true
      });
    
      const results: InstallResult[] = [];
      let installed = 0;
      let skipped = 0;
      let failed = 0;
      let secretsRequired = 0;
    
      for (const mcp of mcps) {
        const result = await installMcp(
          mcp.id,
          client,
          options.providedSecrets || {},
          options.skipExisting !== false
        );
    
        results.push(result);
    
        switch (result.status) {
          case 'success':
            installed++;
            break;
          case 'already_installed':
            skipped++;
            break;
          case 'secrets_required':
            secretsRequired++;
            break;
          case 'error':
            failed++;
            break;
        }
      }
    
      return {
        total: mcps.length,
        installed,
        skipped,
        failed,
        secrets_required: secretsRequired,
        results
      };
    }
  • src/index.ts:176-178 (registration)
    Registration of the tools list (including install_all) for the ListToolsRequest handler.
    server.setRequestHandler(ListToolsRequestSchema, async () => ({
      tools
    }));
Behavior3/5

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

With no annotations, the description carries full burden. It discloses key behavioral traits: it can install all or essential MCPs, skips MCPs needing secrets unless provided, and implies batch operation. However, it doesn't cover important aspects like whether installation is destructive to existing configurations, authentication requirements beyond secrets, error handling, or rate limits.

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 and includes all essential qualifications. Every word earns its place with no redundancy or unnecessary elaboration.

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?

For a tool with 4 parameters, no annotations, and no output schema, the description is adequate but has clear gaps. It explains the what and some behavioral constraints, but doesn't cover return values, error conditions, or detailed operational context that would be helpful for an agent.

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 100%, so the schema fully documents all 4 parameters. The description adds no specific parameter information beyond what's in the schema, but doesn't need to compensate for gaps. The baseline 3 is appropriate when schema does the heavy lifting.

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 ('Install all MCPs'), specifies the target ('to a client'), and distinguishes from siblings by mentioning the optional scope ('or just essential ones') and secret-handling behavior. It's more comprehensive than the sibling 'install_mcp' which presumably installs individual MCPs.

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 implies when to use this tool (bulk installation with optional filtering) versus alternatives like 'install_mcp' (single MCP installation), but doesn't explicitly name alternatives or state when not to use it. It provides context about secret handling but lacks explicit exclusions.

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/danielrosehill/My-MCP-Installer'

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