agent_open — Marsell MCP Tool
agent_open
(agent open) is one of 126 tools on the
Marsell
MCP server. Connect the server and your client discovers it on the handshake.
by client
How to call agent_open from your client
- Claude Code Marsell agent_open run in your project directory
- Claude Desktop Marsell agent_open ~/Library/Application Support/Claude/claude_desktop_config.json
- Cursor Marsell agent_open ~/.cursor/mcp.json
- VS Code Marsell agent_open .vscode/mcp.json
- Zed Marsell agent_open ~/.config/zed/settings.json
- Windsurf Marsell agent_open ~/.codeium/windsurf/mcp_config.json
- Cline Marsell agent_open ~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
- Gemini CLI Marsell agent_open ~/.gemini/settings.json
- Grok Marsell agent_open .mcp.json (in your project root)
- ChatGPT Marsell agent_open Settings → Connectors → Advanced → Developer mode
- Claude.ai Marsell agent_open Settings → Connectors → Add custom connector
- LangChain Marsell agent_open pip install langchain-mcp-adapters
Fastest route
claude mcp add --transport http marsell https://getmarsell.com/mcpOther tools on this server
- list_projects
- get_overview
- list_decisions
- answer_decision
- get_brand
- update_brand
- get_market
- list_people
- get_tokens
- make_pictures
- ask_marsell
- card_read
- inbox_read
- site_draft_read
- get_app
- get_analytics
- get_setup
- fill_setup
- set_offer
- add_products
- add_pictures
- add_characters
- add_places
- add_logo
- add_font
- set_look
- add_socials
- add_rivals
- add_guide
- answer_question
- remove_from_setup
- add_brand_file
- get_upload_link
- add_notes
- set_preferences
- finish_setup
- voices_read
- voice_library_search
- voice_keep
- voice_clone
- voice_remove
- series_read
- series_quote
- series_create
- series_start
- homework_list
- homework_get
- homework_take
- homework_done
- homework_schedule
- homework_stuck
- missions_next
- mission_done
- mission_skipped
- mission_stuck
- mission_inbox
- scheduled_posts_read
- scheduled_posts_sync
- scheduled_posts_remove
- journal_read
- work_list
- work_get
- outcomes_summary
- timeline_query
- crm_segments
- crm_search
- crm_timeline
- experiments_list
- memory_search
- metrics_series
- discovery_read
- web_research
- work_plan
- slot_add
- slot_move
- slot_drop
- work_cancel
- work_reschedule
- stream_set
- stream_stop
- experiment_start
- learning_write
- journal_note
- agent_run_early
- situation_read
- place_open
- waiting_read
- agents_read
- agent_mode_set
- canvas_film
- code_film
- picture_price
- ad_results_read
- post_options
- ad_offer
- ad_card
- ad_answer
- business_context_read
- business_context_change
- offerings_read
- offering_remove
- offering_restore
- set_aside
- set_goal
- owner_facts_read
- owner_fact_set
- freezer_read
- freezer_take_out
- set_type
- series_video_types_read
- series_video_type_set
- series_end_card_read
- series_end_card
- listings_read
- listings_mark
- pages_read
- page_again
- page_change
- business_read_quote
- business_read_start
- screen_read
- attachment_read
- attachment_keep
- attachment_watch
- conversations_read
This list was read from the server itself, by connecting to it and calling tools/list on 11 November 2026. It is what
the server actually exposes, not what its listing claims.
Mutating and Read-only are read off each tool's name, not its schema — a hint, not a guarantee. The registry stores tool names only; connect the server for its live schemas.