DreamAgent MCP Server
Click on "Install 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., "@DreamAgent MCP ServerCreate a Telegram bot called WeatherBot that replies with the weather."
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.
DreamAgent MCP Server
Standalone MCP server that lets ChatGPT operate your DreamAgent account: create projects (Telegram bots, Discord bots, websites, schedulers), watch them build, and edit them conversationally through DreamAgent's AI agent.
It talks only to the existing DreamAgent REST API — no backend changes, and all server-side ownership checks apply unchanged.
Tools
Tool | What it does |
| List your projects (id, type, status, domain) |
| Create a telegrambot / discordbot / website / scheduler (async) |
| Poll a project until |
| Send a build/edit/debug instruction to the project's AI agent (async, consumes credits) |
| Poll the agent run; streams new output + |
| Cancel a running edit |
Long operations are submit-then-poll: create → poll status; chat → poll chat status. The tool descriptions tell ChatGPT to do this.
Related MCP server: chatgpt-codex-tools-mcp
Setup
cd mcp-server
pip install -r requirements.txt
cp .env.example .env # fill in your DreamAgent email + passwordThe account is connected by logging into the existing POST /auth/login
endpoint; the session token is cached in memory and refreshed on expiry.
Run
# stdio (local clients: Claude Desktop, Claude Code, etc.)
python server.py
# HTTP (remote MCP — for ChatGPT apps)
python server.py --http --port 8800
# then expose https://your-host:8800/mcp via your reverse proxyConnect to ChatGPT (developer apps / MCP)
Run the server with
--httpbehind HTTPS (e.g.https://mcp.dreamagent.cloud/mcp).In your ChatGPT app config (or any MCP client that supports remote servers), point the MCP endpoint at that URL.
Per-user credentials: set
DREAMAGENT_EMAIL/DREAMAGENT_PASSWORDfor the account the server should act as. (For a multi-user deployment, run one instance per user or wait for the OAuth phase.)
Try it locally (smoke test)
python - <<'PY'
from server import mcp
tools = mcp._tool_manager.list_tools() if hasattr(mcp, "_tool_manager") else []
print([t.name for t in tools])
PY
# or simply:
fastmcp dev server.pyExample ChatGPT conversations
"Show my DreamAgent projects"
"Create a Telegram bot called WeatherBot, token 123456:ABC — it should reply with the weather when I send a city name" → create → poll until ready
"Add a /price command to my Discord bot" → dreamagent_chat → poll until done
"Is my website finished building?"
"Cancel the edit running on my crypto bot"
Security notes
Credentials live only in the
.envyou control; the session token is transient and refreshed via the existing login endpoint.Every API call carries the user's own token — DreamAgent's per-user authorization and rate limits apply exactly as in the dashboard.
Bot tokens passed to
dreamagent_create_projectare sent to DreamAgent over HTTPS and stored in the project's.env, the same as creating via the dashboard.
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- Alicense-qualityBmaintenanceEmpower any MCP-compatible AI Agent(MCP Client) with engineering-grade capabilities to understand, modify, run, and deliver real-world code repositories.749Apache 2.0
- Alicense-qualityAmaintenanceEnables ChatGPT to inspect and edit local projects through a secure MCP interface, offering workspace management, file operations, git integration, and safe command execution.4MIT
- Flicense-qualityCmaintenanceEnables AI agents to read and modify Mendix application models through MCP tools for creating modules, entities, pages, microflows, deploying, and querying runtime data.1
- Flicense-qualityBmaintenanceEnables a ChatGPT Web conversation to act as a coding agent on a VPS, with project-bound chats, Git worktree isolation, live activity streaming, structured questions, and file/image exchange via MCP.
Related MCP Connectors
Connect any AI agent to 11+ social platforms: schedule, publish & track posts via hosted MCP.
OCR, transcription, file extraction, and image generation for AI agents via MCP.
Free public MCP for AI agents — 193 tools, 44 workflows. No API key.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/nivethaug/dreamagent-mcp-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server