bm25-budget-research — AgentDiet AI Token Diet & Context Window Distiller MCP Prompt
bm25-budget-research
is one of 2 prompts on the
AgentDiet AI Token Diet & Context Window Distiller
MCP server. Connect the server and it appears in your client, ready to invoke.
by client
How to invoke bm25-budget-research from your client
- Claude Code AgentDiet AI Token Diet & Context Window Distiller Prompt/bm25-budget-research run in your project directory
- Claude Desktop AgentDiet AI Token Diet & Context Window Distiller Prompt/bm25-budget-research ~/Library/Application Support/Claude/claude_desktop_config.json
- Cursor AgentDiet AI Token Diet & Context Window Distiller Prompt/bm25-budget-research ~/.cursor/mcp.json
- VS Code AgentDiet AI Token Diet & Context Window Distiller Prompt/bm25-budget-research .vscode/mcp.json
- Zed AgentDiet AI Token Diet & Context Window Distiller Prompt/bm25-budget-research ~/.config/zed/settings.json
- Windsurf AgentDiet AI Token Diet & Context Window Distiller Prompt/bm25-budget-research ~/.codeium/windsurf/mcp_config.json
- Cline AgentDiet AI Token Diet & Context Window Distiller Prompt/bm25-budget-research ~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
- Gemini CLI AgentDiet AI Token Diet & Context Window Distiller Prompt/bm25-budget-research ~/.gemini/settings.json
- Grok AgentDiet AI Token Diet & Context Window Distiller Prompt/bm25-budget-research .mcp.json (in your project root)
- ChatGPT AgentDiet AI Token Diet & Context Window Distiller Prompt/bm25-budget-research Settings → Connectors → Advanced → Developer mode
- Claude.ai AgentDiet AI Token Diet & Context Window Distiller Prompt/bm25-budget-research Settings → Connectors → Add custom connector
- LangChain AgentDiet AI Token Diet & Context Window Distiller Prompt/bm25-budget-research pip install langchain-mcp-adapters
Other prompts on this server
AgentDiet AI Token Diet & Context Window Distiller also offers 10 resources — data you attach as context, where a prompt is something you run.
Read from the server itself, by connecting to it and calling prompts/list on 19 October 2026.
A listing does not declare its prompts, so asking is the only way to know them, and this
is what the server actually offers rather than what its listing claims. Names only are
stored; connect the server for each prompt's arguments.