agent-deploy-dashbaord
Unified deployment dashboard MCP server for AI agents. 9 tools to manage services across Vercel, Render, Railway, and Fly.io ā deploy status, logs, service listing, environment variables, rollback, and health checks from one endpoint. Free tier: 50 requests/IP/day.
README
Agent Deploy Dashboard MCP Server
Unified deployment management for AI agents ā manage Vercel, Render, Railway, and Fly.io services from a single MCP + REST API.
Features
š Multi-Platform Support ā Manage Vercel, Render, Railway, and Fly.io from one interface
š Deployment Status ā Check deploy status and health across all platforms
š Unified Logging ā Tail logs and view build logs
āļø Environment Management ā List, update, and manage env vars
š Redeploy Operations ā Trigger redeployments and rollbacks
š° x402 Micropayments ā Built-in payment middleware for API monetization
š Rate Limiting ā 50 free requests/IP/day with paid tier support
Quick Start
MCP Configuration
Add to your MCP settings file (cline_mcp_settings.json or similar):
{
"mcpServers": {
"agent-deploy-dashboard": {
"url": "https://agent-deploy-dashboard-mcp.onrender.com/mcp"
}
}
}
REST API
Base URL: https://agent-deploy-dashboard-mcp.onrender.com
List All Services
curl -X GET https://agent-deploy-dashboard-mcp.onrender.com/api/v1/list_all_services
Response:
{
"success": true,
"services": [
{
"id": "prj_abc123",
"name": "my-app",
"platform": "vercel",
"url": "https://my-app.vercel.app",
"framework": "nextjs"
},
{
"id": "srv_xyz789",
"name": "api-service",
"platform": "render",
"type": "web_service",
"region": "oregon"
}
],
"count": 2
}
Get Deploy Status
curl -X POST https://agent-deploy-dashboard-mcp.onrender.com/api/v1/get_deploy_status \
-H "Content-Type: application/json" \
-d '{
"platform": "vercel",
"service_id": "prj_abc123"
}'
Response:
{
"success": true,
"platform": "vercel",
"service_id": "prj_abc123",
"deployment_id": "dpl_xyz",
"status": "READY",
"url": "https://my-app.vercel.app",
"created_at": 1709823600000
}
Tail Logs
curl -X POST https://agent-deploy-dashboard-mcp.onrender.com/api/v1/tail_logs \
-H "Content-Type: application/json" \
-d '{
"platform": "render",
"service_id": "srv_xyz789",
"lines": 50
}'
Get Environment Variables
curl -X POST https://agent-deploy-dashboard-mcp.onrender.com/api/v1/get_env_vars \
-H "Content-Type: application/json" \
-d '{
"platform": "vercel",
"service_id": "prj_abc123"
}'
Response:
{
"success": true,
"platform": "vercel",
"service_id": "prj_abc123",
"env_vars": {
"DATABASE_URL": {
"value": "[ENCRYPTED]",
"target": ["production"],
"type": "encrypted"
},
"API_KEY": {
"value": "abc123",
"target": ["production", "preview"],
"type": "plain"
}
},
"count": 2
}
Set Environment Variable
curl -X POST https://agent-deploy-dashboard-mcp.onrender.com/api/v1/set_env_var \
-H "Content-Type: application/json" \
-d '{
"platform": "render",
"service_id": "srv_xyz789",
"key": "NEW_FEATURE_FLAG",
"value": "true"
}'
Trigger Redeploy
curl -X POST https://agent-deploy-dashboard-mcp.onrender.com/api/v1/trigger_redeploy \
-H "Content-Type: application/json" \
-d '{
"platform": "vercel",
"service_id": "prj_abc123"
}'
Get Build Logs
curl -X POST https://agent-deploy-dashboard-mcp.onrender.com/api/v1/get_build_logs \
-H "Content-Type: application/json" \
-d '{
"platform": "vercel",
"deploy_id": "dpl_xyz"
}'
Check Health
curl -X POST https://agent-deploy-dashboard-mcp.onrender.com/api/v1/check_health \
-H "Content-Type: application/json" \
-d '{
"url": "https://my-app.vercel.app/health"
}'
Response:
{
"success": true,
"url": "https://my-app.vercel.app/health",
"status_code": 200,
"healthy": true,
"response_time_ms": 142,
"headers": {
"content-type": "application/json",
"x-vercel-id": "sfo1::abc123"
}
}
Pricing
Free Tier
- 50 requests per IP per day
- All tools included
- All platforms supported
- No credit card required
Paid Tier (HTTP 402 Payment)
After free tier exhausted:
- $0.01 per request
- Payment via HTTP 402 with crypto wallet
- Wallet address:
0x8E844a7De89d7CfBFe9B4453E65935A22F146aBB - Include
X-Paymentheader with payment proof
Platform Support
| Platform | List Services | Deploy Status | Logs | Env Vars | Redeploy | Build Logs |
|---|---|---|---|---|---|---|
| Vercel | ā Full | ā Full | ā ļø Build only | ā Full | ā Full | ā Full |
| Render | ā Full | ā Full | ā Full | ā Full | ā Full | ā Full |
| Railway | ā Basic | ā³ Planned | ā³ Planned | ā³ Planned | ā³ Planned | ā³ Planned |
| Fly.io | ā Basic | ā³ Planned | ā³ Planned | ā³ Planned | ā³ Planned | ā³ Planned |
ā
= Fully implemented
ā ļø = Partial implementation
ā³ = Planned/stub implementation
Tools Reference
1. list_all_services()
List all services across all platforms.
Parameters: None
Returns:
{
"success": true,
"services": [...],
"count": 10,
"errors": null
}
2. get_deploy_status(platform, service_id)
Check deployment status for a specific service.
Parameters:
platform(string): Platform name āvercel,render,railway, orflyservice_id(string): Service/project ID
Returns:
{
"success": true,
"platform": "vercel",
"service_id": "prj_abc",
"deployment_id": "dpl_xyz",
"status": "READY",
"url": "https://...",
"created_at": 1709823600000
}
3. tail_logs(platform, service_id, lines=100)
Stream recent logs from a service.
Parameters:
platform(string): Platform nameservice_id(string): Service/project IDlines(integer, optional): Number of log lines (default: 100)
Returns:
{
"success": true,
"platform": "render",
"service_id": "srv_xyz",
"logs": [...],
"count": 100
}
4. get_env_vars(platform, service_id)
List environment variables for a service.
Parameters:
platform(string): Platform nameservice_id(string): Service/project ID
Returns:
{
"success": true,
"platform": "vercel",
"env_vars": {"KEY": "value"},
"count": 5
}
5. set_env_var(platform, service_id, key, value)
Update an environment variable.
Parameters:
platform(string): Platform nameservice_id(string): Service/project IDkey(string): Environment variable namevalue(string): Environment variable value
Returns:
{
"success": true,
"message": "Environment variable set successfully"
}
6. trigger_redeploy(platform, service_id)
Force redeploy a service.
Parameters:
platform(string): Platform nameservice_id(string): Service/project ID
Returns:
{
"success": true,
"deployment_id": "dpl_new",
"message": "Redeploy triggered successfully"
}
7. get_build_logs(platform, deploy_id)
Fetch build logs for a deployment.
Parameters:
platform(string): Platform namedeploy_id(string): Deployment ID
Returns:
{
"success": true,
"logs": [...],
"count": 50
}
8. check_health(url)
Ping a health endpoint.
Parameters:
url(string): URL to check
Returns:
{
"success": true,
"status_code": 200,
"healthy": true,
"response_time_ms": 142
}
9. rollback_deploy(platform, service_id, version)
Rollback to a previous deployment version.
Parameters:
platform(string): Platform nameservice_id(string): Service/project IDversion(string): Version/deployment ID to rollback to
Returns:
{
"success": false,
"error": "Rollback not yet implemented for this platform"
}
Environment Variables
Configure platform API access via environment variables:
# Vercel
VERCEL_TOKEN=your_vercel_token
# Render
RENDER_API_KEY=your_render_api_key
# Railway
RAILWAY_TOKEN=your_railway_token
# Fly.io
FLY_API_TOKEN=your_fly_api_token
# Payment (optional)
X402_WALLET_ADDRESS=0x8E844a7De89d7CfBFe9B4453E65935A22F146aBB
Get your API tokens:
- Vercel: https://vercel.com/account/tokens
- Render: https://dashboard.render.com/u/settings#api-keys
- Railway: https://railway.app/account/tokens
- Fly.io: Run
flyctl auth token
Development
Local Setup
# Clone repo
git clone https://github.com/aparajithn/agent-deploy-dashboard-mcp.git
cd agent-deploy-dashboard-mcp
# Create virtual environment
python3 -m venv venv
source venv/bin/activate # On Windows: venv\Scripts\activate
# Install dependencies
pip install -e ".[dev]"
# Set environment variables
export VERCEL_TOKEN=your_token
export RENDER_API_KEY=your_key
# Run server
uvicorn src.main:app --reload --port 8080
Test Endpoints
# Health check
curl http://localhost:8080/health
# List services (requires platform tokens)
curl http://localhost:8080/api/v1/list_all_services
# Test MCP protocol
curl -X POST http://localhost:8080/mcp \
-H "Content-Type: application/json" \
-d '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2024-11-05","capabilities":{},"clientInfo":{"name":"test","version":"1.0.0"}}}'
# List MCP tools
curl -X POST http://localhost:8080/mcp \
-H "Content-Type: application/json" \
-d '{"jsonrpc":"2.0","id":2,"method":"tools/list","params":{}}'
Docker
# Build
docker build -t agent-deploy-dashboard-mcp .
# Run
docker run -p 8080:8080 \
-e VERCEL_TOKEN=your_token \
-e RENDER_API_KEY=your_key \
-e PUBLIC_HOST=localhost \
agent-deploy-dashboard-mcp
Deployment on Render
Via Web UI
- Fork this repo to your GitHub account
- Go to Render Dashboard
- Click New ā Web Service
- Connect your GitHub repo:
aparajithn/agent-deploy-dashboard-mcp - Configure:
- Name:
agent-deploy-dashboard-mcp - Runtime: Docker
- Region: Oregon (or closest)
- Instance Type: Free
- Name:
- Add environment variables:
VERCEL_TOKENRENDER_API_KEYRAILWAY_TOKEN(optional)FLY_API_TOKEN(optional)X402_WALLET_ADDRESS(optional)PUBLIC_HOST=agent-deploy-dashboard-mcp.onrender.com
- Click Create Web Service
Via Render API
curl -X POST https://api.render.com/v1/services \
-H "Authorization: Bearer $RENDER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"type": "web_service",
"name": "agent-deploy-dashboard-mcp",
"repo": "https://github.com/aparajithn/agent-deploy-dashboard-mcp",
"branch": "main",
"runtime": "docker",
"plan": "free",
"region": "oregon",
"envVars": [
{"key": "VERCEL_TOKEN", "value": "your_token"},
{"key": "RENDER_API_KEY", "value": "your_key"},
{"key": "PUBLIC_HOST", "value": "agent-deploy-dashboard-mcp.onrender.com"}
]
}'
Architecture
agent-deploy-dashboard-mcp/
āāā src/
ā āāā main.py # FastMCP server + REST API
ā āāā tools/
ā ā āāā platforms.py # Platform API clients (Vercel, Render, etc)
ā ā āāā deploy_tools.py # Tool implementations
ā āāā middleware/
ā āāā rate_limit.py # Rate limiting
ā āāā x402.py # Payment middleware
āāā Dockerfile
āāā pyproject.toml
āāā README.md
Tech Stack
- Python 3.11 ā Modern async/await
- FastAPI ā REST API framework
- FastMCP ā MCP protocol implementation (Streamable HTTP)
- httpx ā Fast async HTTP client
- Pydantic ā Data validation
API Reference Docs
Once deployed, view interactive API docs at:
- Swagger UI:
https://agent-deploy-dashboard-mcp.onrender.com/docs - OpenAPI JSON:
https://agent-deploy-dashboard-mcp.onrender.com/openapi.json
License
MIT License ā see LICENSE for details.
Support
- Issues: GitHub Issues
- Email: aparajith@dabaracoffee.com
Built for AI agents by Forge (Aparajith's coding agent) š¤
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.