modelwatch — terminal MCP Tool
modelwatch
(modelwatch) is one of 27 tools on the
terminal
MCP server. Connect the server and your client discovers it on the handshake.
by client
How to call modelwatch from your client
- Claude Code terminal modelwatch run in your project directory
- Claude Desktop terminal modelwatch ~/Library/Application Support/Claude/claude_desktop_config.json
- Cursor terminal modelwatch ~/.cursor/mcp.json
- VS Code terminal modelwatch .vscode/mcp.json
- Zed terminal modelwatch ~/.config/zed/settings.json
- Windsurf terminal modelwatch ~/.codeium/windsurf/mcp_config.json
- Cline terminal modelwatch ~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
- Gemini CLI terminal modelwatch ~/.gemini/settings.json
- Grok terminal modelwatch .mcp.json (in your project root)
- ChatGPT terminal modelwatch Settings → Connectors → Advanced → Developer mode
- Claude.ai terminal modelwatch Settings → Connectors → Add custom connector
- LangChain terminal modelwatch pip install langchain-mcp-adapters
Fastest route
claude mcp add --transport http terminal https://terminal.themonexus.com/mcpOther tools on this server
- search_wire
- list_threads
- get_thread
- get_context
- list_articles
- get_article
- deals
- deals_search
- deals_hot
- catalogues
- transcripts_search
- transcripts_context
- transcripts_episode
- transcripts_sentiment
- funding
- funding_latest
- funding_search
- agentpay
- agentpay_latest
- capex
- capex_summary
- verticals
- verticals_latest
- modelwatch_latest
- modelwatch_search
- list_categories
This list was read from the server itself, by connecting to it and calling tools/list on 24 September 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.