Compatible with every major AI agent and IDE
What is the Coder (Remote Dev) MCP Server?
Connect your Coder deployment to any AI agent to orchestrate remote development infrastructure and monitor workspace health through natural language.
What you can do
- Deployment Monitoring — Retrieve build info, deployment statistics, and check for available updates to keep your infrastructure current.
- AI Bridge Management — List connected AI clients, available models, and active sessions to understand how AI is being utilized in your workspaces.
- Agent Operations — Stream logs from specific workspace agents and manage application statuses to troubleshoot remote environments instantly.
- Infrastructure Config — Access SSH configurations and deployment settings to ensure seamless connectivity for your engineering team.
- Session Insights — Fetch threads and interceptions from AI sessions to audit and optimize AI-assisted development workflows.
How it works
- Subscribe to this server
- Enter your Coder URL and Session Token
- Start managing your remote dev clusters from Claude, Cursor, or any MCP-compatible client
Who is this for?
- DevOps Engineers — monitor deployment health and configuration without leaving the terminal or chat interface.
- Platform Teams — manage AI Bridge sessions and model availability across the organization's remote workspaces.
- Software Developers — quickly retrieve SSH configs and agent logs to debug environment issues without context switching.
Built-in capabilities (84)
Add an enterprise license
Authenticate agent using cloud provider identity
Cancel a pending or running build
Check if user has permission to perform actions
Start a new AI chat session
Send a message to a chat session
Create a group in an organization
Create an organization
Create a user
Create a user secret
Create a long-running AI task for a user
Create a user token
Create a workspace
Create a port share for a workspace
Delete an enterprise license
Delete a user
Download a file by ID
Get DERP and connection details for an agent
List running containers and devcontainers
Get the last 10MiB of agent logs (local agent API)
Get Tailscale magicsock debug info (local agent API)
Get the startup manifest from the server (local agent API)
Get external authentication tokens for the agent
Stream logs from a specific agent
Get threads for an AI session
Get basic API information
Redirect to a URI with an encrypted API key
Get the base host for applications
Get dashboard branding and banners
Get a paginated list of audit logs
Get Coder build info
Get messages for a chat session
Get deployment configuration
Get deployment statistics
Initiate device-based OAuth
Get Daily Active User stats
Get usage data for templates
Get activity duration per user
List user notifications
Get global notification settings
List available notification templates
Get prebuild settings
Get SSH configuration
Check for Coder updates
Get user profile
Get workspace metadata
Get workspace ACLs
Get details of a specific build
Get logs for a specific build
List parameters used for the build
List connected AI Bridge clients
List AI interceptions
List available AI models
List active AI Bridge sessions
List user chat sessions
List linked external accounts (e.g., GitHub)
List groups
List enterprise licenses
List members of an organization
List active provisioner daemons
List jobs for the organization provisioners
List assignable roles in an organization
List organizations
Manage long-running AI tasks
List starter template examples
List versions for a template
List all templates
List user secrets
List user tokens
List users
List port shares for a workspace
g., owner:me). List workspaces
Authenticate a user with email and password
Register a new log source
Send logs to the server
Update status of an application running on the agent
Update dashboard branding and banners
Update an organization
Update prebuild settings
Update user profile
Update workspace ACLs
Update workspace autostart schedule
Update workspace autoupdates schedule
Upload a file (tar or zip)
Why Claude Code?
Claude Code registers Coder (Remote Dev) as an MCP server in a single terminal command. Once connected, Claude Code discovers all 84 tools at runtime and can call them headlessly. ideal for CI/CD pipelines, cron jobs, and automated workflows where Coder (Remote Dev) data drives decisions without human intervention.
- —
Single-command setup:
claude mcp addregisters the server instantly. no config files to edit or applications to restart - —
Terminal-native workflow means MCP tools integrate seamlessly into shell scripts, CI/CD pipelines, and automated DevOps tasks
- —
Claude Code runs headlessly, enabling unattended batch processing using Coder (Remote Dev) tools in cron jobs or deployment scripts
- —
Built by the same team that created the MCP protocol, ensuring first-class compatibility and the fastest adoption of new protocol features
Coder (Remote Dev) in Claude Code
Coder (Remote Dev) and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect Coder (Remote Dev) to Claude Code through Vinkius don't need to source, host, or maintain individual MCP servers. Every tool call runs inside a hardened runtime with credential isolation, DLP, and a signed audit chain.
Raw MCP | Vinkius | |
|---|---|---|
| Server catalog | Find and host yourself | 4,000+ managed |
| Infrastructure | Self-hosted | Sandboxed V8 isolates |
| Credential handling | Plaintext in config | Vault + runtime injection |
| Data loss prevention | None | Configurable DLP policies |
| Kill switch | None | Global instant shutdown |
| Financial circuit breakers | None | Per-server limits + alerts |
| Audit trail | None | Ed25519 signed logs |
| SIEM log streaming | None | Splunk, Datadog, Webhook |
| Honeytokens | None | Canary alerts on leak |
| Custom domains | Not applicable | DNS challenge verified |
| GDPR compliance | Manual effort | Automated purge + export |
Why teams choose Vinkius for Coder (Remote Dev) in Claude Code
The Coder (Remote Dev) MCP Server runs on Vinkius-managed infrastructure inside AWS — a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts. All 84 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in Claude Code only access the data you authorize, with DLP that blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade infrastructure, zero maintenance.

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
How Vinkius secures
Coder (Remote Dev) for Claude Code
Every tool call from Claude Code to the Coder (Remote Dev) MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
Can I check the health and usage of my Coder deployment?
Yes. Use the get_deployment_stats tool to retrieve workspace and session statistics, providing a clear overview of your infrastructure's current state.
How do I see which AI models are available in my Coder instance?
Simply run the list_ai_models tool. It will return a list of all AI models currently configured and available through the Coder AI Bridge.
Can I view logs for a specific workspace agent to debug issues?
Yes! Use the get_agent_logs tool with the target agent_id. This allows you to stream and inspect logs directly from the remote environment.
How do I add an MCP server to Claude Code?
Run claude mcp add <name> --transport http "<url>" in your terminal. Claude Code registers the server and discovers all tools immediately.
Can Claude Code run MCP tools in headless mode?
Yes. Claude Code supports non-interactive execution, making it ideal for scripts, cron jobs, and CI/CD pipelines that need MCP tool access.
How do I list all connected MCP servers?
Run claude mcp in your terminal to see all registered servers and their status, or type /mcp inside an active Claude Code session.
Command not found: claude
Ensure Claude Code is installed globally: npm install -g @anthropic-ai/claude-code
Connection timeout
Check your internet connection and verify the Edge URL is reachable
Explore More MCP Servers
View all →
GitBook
8 toolsManage technical documentation via GitBook — list organizations and spaces, handle document pages, search content, and audit collections directly from any AI agent.

Documint
10 toolsEquip your AI agent to automate document generation, manage templates, and track output files via the Documint API.

Aliyun OSS / 阿里云对象存储
10 toolsChina's leading object storage service — manage files, buckets, and metadata via AI.

Gem
12 toolsManage recruitment CRM pipelines, track candidates, and oversee outreach via AI agents with Gem.
