Local-first developer utility

One MCP config.
Every AI client.

Translate between incompatible MCP configuration formats, catch mistakes, and keep credentials out of your files. Nothing leaves your browser.

8clients supported
0uploads or sign-ups
100%runs on-device
01 / CONVERT

Translate your configuration

Private by design
claude_desktop_config.json
Waiting for input
config.toml
Ready to convert
02 / VALIDATE

More than a syntax check.

Every conversion includes practical diagnostics for the failures and security mistakes that cost developers time.

{ }

Structure

Valid JSON or TOML, expected wrapper keys, and correct value types.

Waiting for input
↔

Transport

Detects stdio, HTTP and legacy SSE, including ambiguous definitions.

Waiting for input
⌁

Secrets

Flags tokens and API keys that should be referenced through environment variables.

Waiting for input
!

Portability

Warns when a client-specific field cannot safely cross formats.

Waiting for input
03 / HOW IT WORKS

From pasted config to working client.

  1. 1

    Choose the source

    Select where the config works today and paste the complete file.

  2. 2

    Convert & inspect

    We normalize transports, fields and format-specific conventions locally.

  3. 3

    Copy to the right path

    Use the generated filename and path guidance for your target client.

04 / GUIDES

Popular MCP conversions

05 / FAQ

Useful details, plainly answered.

Is my MCP configuration uploaded anywhere?+

No. Parsing, conversion, validation and secret detection all run inside your browser. The tool has no account system and makes no network request with your configuration.

Which MCP clients are supported?+

Claude Desktop, Claude Code, Cursor, OpenAI Codex, Gemini CLI, VS Code, Windsurf and Cline. Common stdio and remote HTTP servers are supported.

Why does Codex use TOML instead of JSON?+

Codex stores MCP server definitions in config.toml tables such as [mcp_servers.example]. The converter maps the common JSON shape to those tables and changes field naming where required.

Does conversion preserve credentials?+

Environment variable references are preserved. If a value looks like a real token or secret, the validator warns you before you copy or commit it.

PURPOSE & METHODOLOGY

A focused tool, with the context to use it well

MCP Config Lab was created to help developers convert, validate, and understand MCP client configuration files. It is intended for developers configuring Model Context Protocol servers for Claude, Cursor, VS Code, Codex, and Gemini. The tool is free, requires no account, and is paired with original explanations so you can understand the result rather than copy an unexplained output.

How to use the result

Start with a sample or a non-sensitive copy of your data, run the check, and review every finding before changing a production project. Every converter and guide is tested against representative configuration examples. Explanations identify client-specific differences instead of hiding them behind a generic conversion button. Specifications and software evolve, so confirm high-impact decisions against the linked primary documentation.

Privacy and limitations

MCP configuration text is processed in your browser wherever the tool page states that local processing is used. Avoid entering passwords, access tokens, personal data, or confidential material. Automated output may be incomplete because it cannot know your entire deployment, threat model, or organizational policy.

Independent and transparent

This is an independent developer resource, not an official certification service. Source code and issue tracking are available on GitHub. Read more about the project, review the privacy policy, or report an error.