"A system for building an autonomous second brain" matching MCP servers:

Enables querying Tom Osborne's voice-cloned AI agent with a 21,000-article marketing knowledge base and his interview corpus to get answers in his voice.

Lets MCP-aware agents consult rival LLMs mid-conversation, sending questions to a specific provider or fanning out to OpenAI, Gemini, Anthropic, and xAI/Grok in parallel for second opinions.

Enables AI coding agents to request a second opinion from a different frontier model via a single tool call, with PII scrubbed before transit, live web search, and support for Claude, ChatGPT, Cursor, and Gemini.

An MCP server that connects AI assistants to YNAB budgets, enabling natural language queries about finances backed by full API coverage and built-in YNAB methodology knowledge.

Enables AI agents to request an independent second opinion from a different frontier model, with PII scrubbing before transit, live web search grounding, caching, and multi-provider failover.

A long-term emotional memory system for Claude, enabling persistent, cross-conversation memory with emotional tagging using Russell's valence/arousal model and natural forgetting curves.

An MCP server that queries a panel of LLMs from different providers via OpenRouter and returns their answers side by side, optionally synthesizing them to highlight disagreements.

Enables MCP clients to generate and edit images through Codex's built-in image generation using a ChatGPT login, returning final files with metadata and optional inline previews.

Enables coding agents to add a bounded semantic-judgment layer for routing, ranking, extraction, verification, and escalation, returning typed signals and review recommendations.

Personal knowledge graph with 16 MCP tools. Auto-links, deduplicates, tracks themes, synthesizes insights.

It enables users to interact with a codebase through hybrid retrieval, code graph navigation, impact analysis, and context preparation for AI coding agents.

Enables self-hosted AI gateway and agent control plane with governed MCP tools, virtual-key budgets, caching, and audit, supporting OpenAI, Anthropic, Gemini, MCP, and A2A protocols. It provides deterministic prompt enhancement and governed execution with a zero-credential first run.

Provides intelligent conversation memory storage using DuckDB, with support for multiple storage backends and automatic memory consolidation.

Enables automatic knowledge capture and injection of guardrails for AI assistants like Claude and Cursor, improving code quality and preventing recurring mistakes.

Enables real-time auditing of LLM long-term memory to detect contradictions, user-introduced falsehoods, staleness, and unsourced fabrications, while providing a safe memory store with tools like recall, review, and restore.

Gives Claude persistent cross-conversation memory by tagging each entry with Russell valence/arousal coordinates, storing them as Obsidian-compatible Markdown files, and letting them naturally decay, surface, and merge over time. Exposes breath, hold, grow, trace, and pulse tools for storing, retrieving, editing, and inspecting these memories through the MCP protocol.

Autonomous, carbon-aware building management system that pairs EnergyPlus digital twins with LLMs via the Model Context Protocol (MCP) for dynamic HVAC optimization and grid carbon reduction.

Enables Claude to keep persistent, cross-conversation emotional memories tagged along Russell's valence/arousal dimensions and stored as Obsidian-compatible Markdown buckets. Memories decay on a modified Ebbinghaus curve and automatically surface when unresolved or emotionally intense, with tools to store, search, edit, and track system status.

Enables Claude to persist long-term emotional memories tagged with valence/arousal coordinates, letting them decay naturally, merge automatically, and surface unresolved or intense moments at the start of new conversations. Memories are stored as Obsidian-compatible Markdown files with YAML metadata that can be browsed, edited, and searched directly in a vault.

Enables Claude to maintain persistent emotional memories across conversations using valence/arousal tagging, Obsidian-compatible Markdown storage, natural decay, and automatic surfacing of unresolved memories via MCP.

Enables Claude to keep persistent, emotionally tagged memories across conversations using valence/arousal coordinates stored as Obsidian-compatible Markdown, with natural forgetting, weighted surfacing of unresolved memories, and automatic compression and tagging via an OpenAI-compatible API with local fallback.

Enables Claude to keep long-term emotional memory across conversations by tagging stored memories with Russell's valence/arousal coordinates, decaying and surfacing them via a forgetting curve, and storing them as Obsidian-compatible Markdown. Provides five tools (breath, hold, grow, trace, pulse) for surfacing, storing, digesting, editing, and inspecting memories.

Enables Claude to keep persistent long-term emotional memory across conversations by storing, tagging, searching, and modifying memories with valence/arousal coordinates, letting unresolved or emotionally intense ones surface automatically as older ones decay. Memories live as Obsidian-compatible Markdown files with a forgetting-curve archive and optional LLM-powered compression and auto-tagging.

Enables Claude to maintain persistent emotional memory across conversations by tagging memories with valence/arousal, storing them as Obsidian-compatible Markdown, and using forgetting and surfacing mechanics through MCP tools for storing, searching, updating, and inspecting memories.

Enables Codex to consult Claude Code for a second opinion through a local stdio MCP server, exposing the ask_claude tool for text-only reviews and recommendations using existing Claude Code authentication. Codex can request findings and tradeoff analysis without allowing Claude to edit files or run commands.

AI agent provenance, trust, and auditability layer. VERITAS multi-gate scoring, Cortex approval gates, S.E.A.L. hash-chain audit ledger, and semantic RAG with cryptographic provenance tracking for every decision an agent makes.

Helps founders and teams review business workflows, identify AI opportunities, assess trust/control risks, and recommend a safe first AI-human workflow.

Enables MCP clients to discover OpenRouter image and video models, generate and edit images, create variations, launch and monitor video jobs, and save resulting media into authorized local project directories with cost controls.

A production-grade MCP server designed for multi-tenant, authenticated, and observable AI agent systems, enabling secure tool execution across heterogeneous data sources.

Enables OpenAI-compatible clients to access external tools, APIs, repositories, and data sources through MCP with allowlisting, approval, and argument validation, deployable as a FastAPI service or Python library.