Skip to content

Skills, MCPs and integrations

What was said about this, newest first. For what exists today, see feature status.

Decisions, plans and what was built

  • 12 Oct 2026: Said to exist · System terminal instances are controlled and monitored via MCP (Model Context Protocol) integration using Cmax.
  • 5 Oct 2026: Said to exist · Speaker 1 uses cmux on macOS as an MCP-driven terminal tool to orchestrate Claude CLI sessions and agent swarms.
  • 28 Sep 2026: Planned · The engineering team must build the harness while Speaker 1 completes the Cessation memory MCP backend.
  • 28 Sep 2026: Said to be in progress · The Cessation memory MCP server is being built to provide Memory as a Service and manage context token bloat across swarms.
  • 21 Sep 2026: Said to exist · An MCP server modeled on the [doctrine term] causal doctrine has been developed to handle memory decay and context cessation.
  • 23 Feb 2026: Planned · Speaker 1 will share resources and links regarding Claude/agent skills and MCP with [name withheld].
  • 23 Feb 2026: Planned · Expose the validated website data via an MCP tool interface so external voice models and LLMs can accurately query and respond on Abhidhamma topics.
  • 9 Feb 2026: Decided · Use Telegram instead of WhatsApp for the bot interface due to official API support and cost efficiency.
  • 19 Jan 2026: Decided · Use Discord server as the primary messaging integration over MS Teams for office communication testing.
  • 12 Jan 2026: Said to exist · Gmail skill configuration is loaded via environment variables and a JSON file specifying credentials.
  • 15 Dec 2025: Planned · Build an end-to-end skill where providing a song automatically posts meaning, dimensions, and links to web, YouTube, and channels.
  • 1 Sep 2025: Said to exist · Web3Forms third-party tool is used with an API key to handle contact form submissions sent to email.
  • 11 Aug 2025: Planned · Speaker 2 must document their step-by-step production process and identify the required inputs, outputs, and tooling for each step.
  • 28 Jul 2025: Planned · Speaker 2 and [name withheld] will use an AI-assisted tool or crawler to fetch songs from SoundCloud and group them by common lyrics and meanings.
Ideas, questions and details (41)
  • 5 Oct 2026: Decided · Speaker 2 tested background poster generation using the Hugging Face API and Flux model.
  • 5 Oct 2026: Open · Third-party WhatsApp integration carries risks of account suspension unless routed through official paid network APIs.
  • 5 Oct 2026: Open · Automated video upload tests using the YouTube API caused Speaker 2's test channel to be suspended due to automated bot detection.
  • 5 Oct 2026: Decided · The Cessation memory MCP service automatically releases stale context content to prevent drift and maintain operational clarity.
  • 28 Sep 2026: Idea · The harness should load on top of OpenRouter to connect flexibly to any required underlying model or API.
  • 21 Sep 2026: Open · Local Sinhala AI language modeling research remains underfunded and underdeveloped, forcing reliance on external multilingual models connected via tools like Whisper.
  • 21 Sep 2026: Idea · Integrate third-party transport networks and local services via APIs into calendar agents to schedule commutes and pick-ups automatically.
  • 2 Mar 2026: Idea · Trained and fine-tuned user skills will earn tokens when utilized by others, establishing a token economy capable of acquiring physical goods.
  • 2 Mar 2026: Idea · Agents are coordinated using skills, hooks (execution triggers based on actions or schedules), and commands (workflow procedures like subtitle injection).
  • 2 Mar 2026: Decided · Inner Realm songs use blended skills and mind blends to present multiple distinct visual stories supporting a single underlying meaning.
  • 2 Mar 2026: Decided · Audio visualization in the system separates rupa (form, characters, visual palette) from nama (underlying concept and meaning) to allow flexible skill transformation.
  • 2 Mar 2026: Decided · The system architecture is a native AI backbone where layer-level orchestration manages different AI functions, omni models, and tool calls.
  • 23 Feb 2026: Open · Whether 3D plane animations and smooth image zoom/diffusion transitions can be achieved using tools like CapCut.
  • 23 Feb 2026: Idea · The audio-to-video pipeline will use containerized execution where an ephemeral container spins up on API trigger, renders the video, and is destroyed.
  • 23 Feb 2026: Idea · The automated agent architecture will combine agent skills and MCP tools to manage audio processing and distribution.
  • 9 Feb 2026: Idea · Use Docker MCP containers or Antigravity MCP tools for standardizing agent tool execution.
  • 9 Feb 2026: Planned · Integrate a Vector Database to store conversation history and context per user.
  • 9 Feb 2026: Planned · Deploy per-user Docker containers with injected API keys, GitHub tokens, and MCP tools to isolate execution environments.
  • 2 Feb 2026: Decided · OpenRouter does not provide video generation models, requiring external API endpoints and tokens for video workflows.
  • 2 Feb 2026: Decided · An intent verification engine will be added to confirm and clarify user requests before executing multi-step tool chains.
  • 2 Feb 2026: Decided · The system will utilize Docker containers running MCP (Model Context Protocol) tooling with mapped file systems and injected secret token bundles.
  • 2 Feb 2026: Idea · The agent system should expose webhook integrations to connect directly with messaging apps like WhatsApp for regular user communication.
  • 2 Feb 2026: Idea · Scheduled cron jobs running every 2 to 10 minutes will autonomously monitor Gmail, filter spam, and alert users only when critical conditions are met.
  • 19 Jan 2026: Idea · Develop a Machine World POC integrating three core business systems (CRM, Financial, HR/Payroll) alongside Discord and Email.
  • 12 Jan 2026: Decided · The Machine World system architecture uses YAML files for skill and context definitions and Python files for executable logic.
  • 12 Jan 2026: Idea · Implement Test-Driven Development (TDD) with automated unit and integration tests across Python and YAML skill definitions.
  • 12 Jan 2026: Decided · Adding new skills into feature branches breaks previously working functionality like reading inbox emails.
  • 12 Jan 2026: Decided · When an API call returns empty data, the LLM hallucinates responses instead of indicating that no data was found.
  • 12 Jan 2026: Decided · Skill collective confidence calculation has an error where multi-step execution adds up scores beyond 100%, reaching 270%.
  • 15 Dec 2025: Open · Collaborator [names withheld] has not responded to requests or video instructions for setting up tools and Git.
  • 15 Dec 2025: Idea · Agent skills will be exposed to other agents using MCP (Model Context Protocol) and Agent-to-Agent (A2A) protocols.
  • 8 Dec 2025: Idea · Set up a centralized API token pool with a $40 monthly budget and shift to tools like Claude Code, DeepSeek, or Qwen models rather than paying for Cursor seats.
  • 8 Dec 2025: Decided · A bug in Playwright MCP currently disrupts the ability to read browser or Drive content via Cursor.
  • 13 Oct 2025: Idea · Expose the Citta-Cetasika website as an MCP server for AI agents to query mental states and enable voice navigation.
  • 22 Sep 2025: Open · Determine how the live counter layout will handle large numbers as view counts grow rapidly.
  • 1 Sep 2025: Idea · Explore running native voice-interactive chat bots using Vercel AI SDK or AWS Bedrock integration.
  • 11 Aug 2025: Idea · For cost efficiency or local execution, open-source models running on local Llama can be integrated into the workflow instead of paid token APIs.
  • 11 Aug 2025: Idea · Use n8n containerized flow models to automate repetitive development tasks across chained AI agents with specific tooling access.
  • 11 Aug 2025: Idea · The website should enable cross-navigation between all seven song versions, showing each version's story, audio narrative, visual music patterns, and creation tools.
  • 28 Jul 2025: Idea · Model Context Protocol (MCP) should be used to provide tools to LLMs for tasks such as web browsing and data scraping.
  • 28 Jul 2025: Idea · Speaker 1 proposes funding AI tool subscriptions for the mentees to facilitate multi-model development.