Gpt2agent
UnclaimedYour codex login → a full ChatGPT Plus/Pro account (every model, deep research, image gen, code exec) inside Claude Code, Codex & any MCP client. One-line install.
Set up this server
01 / Choose your client
02 / Before you connect
Authentication is not specified. Check the project instructions before connecting.
Project instructions03 / Add the configuration
claude mcp add --transport stdio 'gpt2agent' -- 'uvx' 'gpt2agent'04 / Check it in your client
Open your client’s MCP settings and confirm the server connects and lists its tools. A copied configuration does not confirm a working connection.
More in AI & ML
Browse the full directoryUnclaimed listing
Is this your MCP server?
This listing was auto-indexed from the public record. Claim it to edit the page, set compatibility and unlock growth tools. Takes under two minutes.
Claim this serverSecurity profile
Claimed and verified servers get a weekly static scan that shows what the code can reach: external services, environment variables, shell commands, agent configuration folders, plus any dependencies with known advisories. Claim this listing to get one. How the security profile works
25 of 25 tools
Documented tools (25)
From project documentation. A server handshake does not verify each tool’s description or behavior.
account_status
Plan, country, groups, feature count, subscription expiry
agent
Agent Mode — 262K context with autonomous browsing, code execution, tool use
canvas_execute
Execute code via ChatGPT's Canvas feature (live editing environment)
chat
Talk to any model on your account (gpt-5-3 default, override via model=). Pass gpt-5-5-pro, o3-pro, gpt-5-4-thinking, …
code_interpreter
Run Python in ChatGPT's sandbox. Returns output + any generated charts/images
codex_task_create
Kick off a new Codex task (resolves env from repolabel)
custom_instructions_get
Read your current aboutuser / aboutmodel
custom_instructions_set
Update them (read-modify-write, preserves unspecified fields)
deep_research
Web-augmented research with citations (~30–120 s). Auto-confirms by default
deep_research_heavy
Long-form DR via gpt-5-5-pro + connector (5–30 min, monthly quota). Configurable via [models].heavydr
generate_image
Generate images via ChatGPT's built-in DALL-E. Returns download URLs + metadata
get_conversation
Full message history for a specific conversation (multimodal, code, images)
get_file_download_url
Temporary download URL for a ChatGPT file (~1h expiry)
get_file_info
Metadata for any ChatGPT file (images, uploads)
gpt_chat
Talk through one of your private Custom GPTs (g-p-) — experimental
list_apps
Connected apps + connectors
list_codex_envs
Codex environments (label, repos, network policy)
list_codex_tasks
Recent Codex tasks + status
list_conversations
Recent ChatGPT conversations (titles: emails/phones redacted)
list_custom_gpts
Your private g-p- GPTs
list_models
All models on your account (slug, maxtokens, reasoningtype, capabilities, enabledtools)
list_tasks
Scheduled / completed ChatGPT tasks
memory_create_via_chat
Add a memory (model-initiated workaround — POST /memories is 405)
memory_list
List all ChatGPT memory entries (emails/phones redacted)
memory_search
Keyword filter over memories
Tool change history
FAQ
Questions about Gpt2agent MCP Server
- How do I connect Gpt2agent MCP Server to Claude?
- Run `claude mcp add gpt2agent -- uvx gpt2agent` in Claude Code, or add the same command and arguments under mcpServers in Cursor's mcp.json or Claude Desktop's claude_desktop_config.json, then restart the client. The blocks above are ready to paste.
- Is Gpt2agent MCP Server free?
- The listed licence is MIT. Check the upstream terms for permitted use and commercial requirements; a public repository does not by itself mean the software is free or open source. Connected APIs and hosted services may have separate charges.
- What can Gpt2agent MCP Server do?
- Gpt2agent MCP Server documents 25 tools to the agent, including account_status, agent, canvas_execute. The descriptions above come from project documentation. A live handshake does not test individual tool behavior.