Halden Solutions logoHalden Solutions wordmark

Tool Calling & Agent Protocols

MCP Config Generator

Create Model Context Protocol (MCP) server configuration files to securely connect AI coding assistants to external tools, databases, APIs, and cloud resources.

Output: mcp.jsonOpen Standard100% Client-Side

Start with a conversation

Talk to us

Use Halden AI as a sales assistant to explore services, understand offerings, and choose the right next step before booking a meeting.

Book a Meeting
Back to all toolsMCP Config Generator
Interactive Generator

Configure & Build your mcp.json

The Model Context Protocol (MCP) is an open standard that allows AI models and IDEs to securely interact with external tools, local filesystems, cloud databases, GitHub repositories, and custom APIs. Generate clean, spec-compliant configurations in seconds.

1. Target Client & Configuration Scope

Select your AI client or editor to automatically format the output file path and JSON schema.

2. Pre-Configured MCP Server Library

Click any integration to toggle it in your configuration.

2 Server(s) Active

3. Active Servers Configuration & Custom Tools

Fine-tune command arguments, allowed paths, and environment variable references.

filesystem
npx
github
npx
Environment Variables & Secrets Placeholders
GITHUB_PERSONAL_ACCESS_TOKEN:${GITHUB_TOKEN}

Add Custom MCP Server

.cursor/mcp.jsonSpec Valid JSON

Save to your project root or editor settings directory.

{
  "mcpServers": {
    "filesystem": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-filesystem",
        "./src"
      ]
    },
    "github": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-github"
      ],
      "env": {
        "GITHUB_PERSONAL_ACCESS_TOKEN": "${GITHUB_TOKEN}"
      }
    }
  }
}

Security Tip: Avoid committing hardcoded secrets into git. Always use environment variable tokens like "${GITHUB_TOKEN}" and populate them through a gitignored .env.local file.

Integration

Where to place your mcp.json

Save project-scoped configs in your repository under .cursor/mcp.json or .vscode/mcp.json. For global access across all projects in Claude Desktop, save to the application support directory.

Repository File Structure
Project Scope (Cursor / VS Code):
.cursor/mcp.json
.vscode/mcp.json

Global Scope (Claude Desktop):
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json

Key Capabilities & Features

  • Multi-client support: Cursor (.cursor/mcp.json), Claude Desktop, VS Code (.vscode/mcp.json), Windsurf, and Generic
  • Target scope switching between project-specific and global configurations
  • Curated catalog of top MCP servers (Filesystem, GitHub, Postgres, Supabase, Slack, Linear, Sentry, Brave Search, Puppeteer, Memory)
  • Custom MCP server builder for stdio, command execution, and remote SSE transports
  • Safe environment variable management with secret placeholders
  • Instant JSON validation, clipboard copy, and file download

Related Tags

Model Context ProtocolTool CallingAgent InfrastructureAPI IntegrationsCursorClaude Desktop

FAQ

Frequently Asked Questions

Everything you need to know about mcp.json and AI agent tooling.

What is the Model Context Protocol (MCP)?

Model Context Protocol (MCP) is an open standard created by Anthropic that enables AI assistants to securely connect to external data sources, developer tools, and operational environments through standardized clients and servers.

How do I pass secrets like API tokens securely?

Never commit real secret keys into public repositories. Use environment variables (e.g., "${GITHUB_PERSONAL_ACCESS_TOKEN}") or set them in a local, git-ignored .env file.

Can I add our own internal custom MCP servers?

Yes. Use the "Add Custom Server" button in the generator to configure any custom command, script, or container endpoint.

Explore

More Developer & AI Tools

Explore other open configuration generators from Halden Solutions.

AGENTS.mdAgent Orchestration & Context

AGENTS.md Generator

Generate a universal AGENTS.md configuration file that provides unified repo context, guidelines, and execution boundaries to any AI coding agent.

Launch Tool
DESIGN.mdDesign Systems & AI Rules

DESIGN.md Generator

Build a tokenized design system specification that AI coding agents can read, understand, and apply consistently across your codebase.

Launch Tool
llms.txtAI SEO & Discoverability

llms.txt Generator

Create structured llms.txt and llms-full.txt files to guide AI search engines, LLMs, and agent web crawlers to your highest-value documentation.

Launch Tool
Enterprise Engineering

Need help building production AI platforms and multi-agent systems?

Halden Solutions helps teams design, build, and scale autonomous AI systems, secure agent guardrails, and enterprise cloud infrastructure.

Explore Data & AIGet in Touch