Replit MCP Server
Enables AI assistants to interact with Replit workspaces, providing tools for repl management (create, fork, delete, run, stop), file operations (read, write, create, delete, search), environment variable management, deployment operations, and user management through Replit's GraphQL API.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Replit MCP Server list my recent repls and show me their status"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Replit MCP Server
An MCP (Model Context Protocol) server that enables AI assistants to interact with Replit workspaces directly, without needing an agentic browser or constant user intervention.
Features
User Management: Get current user, lookup users by ID or username
Repl Management: List, create, fork, delete, and get detailed repl information
File Operations: Read, write, create, delete files and directories
Environment Variables: Manage secrets and environment variables
Deployments: Get deployment info and publish repls
Search: Search for content within files
Related MCP server: E2B MCP Server
Installation
From Smithery
smithery install replit-workspace --client claudeManual Installation
Clone this repository
Install dependencies:
npm installBuild:
npm run buildRun:
npm start
Configuration
The server requires a REPLIT_TOKEN environment variable containing your Replit connect.sid cookie token.
Getting Your Token
Log into Replit in your browser
Open Developer Tools (F12)
Go to Application > Cookies > replit.com
Copy the value of
connect.sid
Claude Desktop Configuration
Add to your Claude Desktop config file:
{
"mcpServers": {
"replit": {
"command": "node",
"args": ["/path/to/replit-mcp-server/dist/index.js"],
"env": {
"REPLIT_TOKEN": "your-connect-sid-token"
}
}
}
}Available Tools (24 Total)
User Operations
Tool | Description |
| Get info about the authenticated user |
| Get user info by numeric ID |
| Get user info by username |
Repl Management
Tool | Description |
| List repls owned by the user |
| Get repl info by URL |
| Get detailed repl info (comments, multiplayers, tags, stats) |
| Set the active repl for subsequent operations |
| Create a new repl |
| Fork an existing repl |
| Delete a repl (requires confirmation) |
| Start a repl |
| Stop a running repl |
File Operations
Tool | Description |
| Read file contents |
| Write content to a file |
| List files in a directory |
| Create a new file |
| Delete a file |
| Create a new directory |
| Search for content in files |
Environment Variables
Tool | Description |
| List all environment variables for a repl |
| Set an environment variable |
| Delete an environment variable |
Deployments
Tool | Description |
| Get deployment info for a repl |
| Deploy/publish a repl |
Development
# Install dependencies
npm install
# Run in development mode
npm run dev
# Build
npm run build
# Start production server
npm startDeployment to Smithery
Ensure you have a
Dockerfileandsmithery.jsonin your repoPush to GitHub
Connect your repository via Smithery dashboard
Deploy
API Coverage
This MCP server provides comprehensive coverage of Replit's GraphQL API including:
User queries and lookups
Repl CRUD operations
File system operations
Environment variable management
Deployment management
Search functionality
License
MIT
Available Tools
24 toolscreate_deploymentC
Deploy/publish a repl
Inputs: replId.
create_directoryC
Create a new directory in a Replit workspace
Inputs: path (required), replId.
create_fileC
Create a new file in a Replit workspace
Inputs: path (required), content, replId.
create_replC
Create a new repl
Inputs: title (required), language (required), description, isPrivate.
delete_fileC
Delete a file from a Replit workspace
Inputs: path (required), replId.
delete_replB
Delete a repl by ID (requires confirmation)
Inputs: id (required), confirm (required).
delete_secretC
Delete an environment variable/secret from a repl
Inputs: key (required), replId.
fork_replC
Fork an existing repl by URL
Inputs: url (required).
get_current_userB
Get information about the currently authenticated Replit user
Inputs: no named parameters.
get_deploymentB
Get deployment information for a repl
Inputs: replId.
get_repl_by_urlC
Get information about a repl by its URL
Inputs: url (required).
get_repl_detailsC
Get detailed repl information including comments, multiplayers, tags, run count, like count, and fork count
Inputs: replId, url.
get_secretsC
List all environment variables/secrets for a repl
Inputs: replId.
get_user_by_idC
Fetch user information by their numeric ID
Inputs: id (required).
get_user_by_usernameC
Fetch user information by their username
Inputs: username (required).
list_filesC
List files and directories in a Replit workspace
Inputs: path, replId.
list_replsC
List repls owned by the current user
Inputs: limit.
read_fileC
Read the contents of a file in a Replit workspace
Inputs: path (required), replId.
run_replC
Start/run a Replit workspace
Inputs: replId.
search_filesC
Search for content within files in a Replit workspace
Inputs: query (required), replId.
set_active_replC
Set the active repl ID for subsequent file operations
Inputs: replId (required).
set_secretC
Set an environment variable/secret for a repl
Inputs: key (required), value (required), replId.
stop_replB
Stop a running Replit workspace
Inputs: replId.
write_fileC
Write content to a file in a Replit workspace
Inputs: path (required), content (required), replId.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 24 tools
Each tool has a clearly distinct purpose targeting specific resources and actions, such as create_repl vs. fork_repl for different creation methods, and get_repl_by_url vs. get_repl_details for different information retrieval levels. There is no significant overlap that would cause confusion in tool selection.
All tool names follow a consistent verb_noun pattern with snake_case, such as create_deployment, delete_file, and get_current_user. This uniformity makes the tool set predictable and easy to understand across all 24 tools.
With 24 tools, the count is on the higher side but still within a reasonable range for a comprehensive Replit management server. It covers many operations, though it might feel slightly heavy compared to more focused servers.
The tool set provides complete CRUD and lifecycle coverage for Replit resources, including repls, files, deployments, secrets, and users. There are no obvious gaps, and agents can perform all essential operations without dead ends.
Maintenance
Related MCP Connectors
Connect AI assistants to GitHub - manage repos, issues, PRs, and workflows through natural language.
Persistent cloud workspaces for AI agents: run commands, edit files, use git and a browser.
Connect AI assistants to your approved computer for files, commands, browser and desktop tasks.
- DNS-DATA RemoteDeprecatedcom.dns-data
Connect AI assistants to authorized Windows and macOS devices for files, commands, and management.
Related MCP Servers
- AlicenseAqualityBmaintenanceEnables AI assistants to manage Repliz workspaces via natural language, including listing and replying to comments, scheduling posts, handling DMs, and browsing content and stats.33MIT
- AlicenseAqualityDmaintenanceEnables AI assistants to securely execute Python and JavaScript code in sandboxed environments, with file management and package installation.792 npmMIT
- AlicenseNot gradedqualityCmaintenanceEnables AI assistants to search, update, and manage files, run terminal commands, and automate workflows on a user's computer.721,771 npmMIT
- AlicenseNot gradedqualityCmaintenanceEnables AI assistants to build and update complete applications, including creating, updating, publishing, previewing, and configuring databases, security, permissions, and server-side integrations.Apache 2.0