MCP Configuration

Model Context Protocol (MCP) connects your AI agent to external tools, APIs, and services. The Desktop App (Code Mode), VS Code Extension, and CLI all share a single MCP configuration file, so you only set things up once.

Config File Locations

Level	Path	Scope
User	~/.abacusai/mcp.json	All projects for the current user
Project	./.abacusai/mcp.json	Current project directory only

Project-level config takes precedence when both exist. Servers from both levels are merged, with project-level winning on conflicts.

Format

Each entry under mcpServers is a named server. There are two types:

• Local (stdio) - runs a command on your machine. Uses command, args, and optionally env.
• Remote (HTTP) - connects to a network endpoint. Uses url and optionally headers.

{
  "mcpServers": {
    "github": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-github"],
      "env": {
        "GITHUB_PERSONAL_ACCESS_TOKEN": "<YOUR_TOKEN>"
      }
    },
    "brave-search": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-brave-search"],
      "env": {
        "BRAVE_API_KEY": "<YOUR_KEY>"
      }
    },
    "analytics-api": {
      "url": "https://api.example.com/mcp",
      "headers": {
        "Authorization": "Bearer <YOUR_TOKEN>"
      }
    }
  }
}

Field Reference

Local servers (stdio)

Field	Type	Required	Description
command	string	Yes	Executable to run (npx, python, node, etc.)
args	string[]	Yes	Arguments passed to the command
env	object	No	Environment variables (API keys, tokens)

Remote servers (HTTP)

Field	Type	Required	Description
url	string	Yes	URL of the remote MCP server
headers	object	No	HTTP headers for authentication

Finding MCP Servers

Browse available servers at:

• GitHub - Official MCP Servers
• mcp.so
• Zapier MCP

Best Practices

• Store tokens in env or headers rather than hardcoding them in args.
• Start with one or two servers. Too many tools can overwhelm the model context.
• For team projects, commit .abacusai/mcp.json with project-specific servers but leave secrets out — each developer supplies their own keys via user-level config.
• Verify a server works by asking the agent a simple question that uses it.

Troubleshooting

If a server isn't connecting:

1. Check that the command or url is correct.
2. Make sure required API keys/tokens are filled in (env or headers).
3. For local servers, confirm the command is in your PATH (npx, node, python).
4. Validate the JSON — a missing comma or bracket is the most common issue.

For further help, reach out at support@abacus.ai.