"Google Pub/Sub" matching MCP servers:

Local-first, read-only Codex session aggregator that indexes multiple CODEX_HOME directories into a SQLite database and provides MCP tools for cross-project, archival, and sub-agent history queries.

Scoped, low-latency persistent memory layer for AI agents, Cursor, and Claude Code over Model Context Protocol with sub-50ms hybrid search.

Connects AI agents to persistent topological memory on the Volumetric Lattice Network, enabling sub-5ms associative recall and storage of facts, documents, and code.

A cross-AI-agent local task context sharing MCP server that allows clients like Codex, Claude Code, Hermes, and VS Code to read and write the same task state, enabling task tracking and context distillation.

A high-performance MCP server providing long-term memory storage with semantic and keyword search capabilities, using SQLite and fastembed for sub-200ms queries.

Standard coding agents waste 70% of context tokens re-reading raw files with shell grep. Synapse-MCP indexes your codebase into a sub-millisecond local AST graph—giving Claude Code, Cursor, and Windsurf exact caller trees, 60% lower token spend, and zero-hallucination refactoring.

Enables AI coding assistants to recall past lessons, bugs, and conventions from local git history with sub-5ms latency and full privacy.

Enables searching Google Scholar with Scholar operators, year ranges, cited-by and all-versions lookups, and retrieving citations in five styles with BibTeX and EndNote export links as structured JSON.

Enables multiple isolated Claude sessions to read markdown knowledge bases versioned in git and deposit proposals, while only a manager role integrates changes.

A reusable MCP server providing shared, versioned context across AI agents and devices via a private GitHub workspace, with tools to discover projects, bootstrap, query, and close out task state.

Gives your agent a private Kinematic Drive: a deterministic memory engine for sub-millisecond exact recall over code and docs with no hallucination. Also provides self-serve checkout and metered pay-per-call tools for AI agents.

Provides MCP tools to search, browse, and retrieve unified read-only history from CLI agents like Codex, Claude Code, and OpenCode, with connector discovery and project-folder grouping.

Provides a shared, persistent memory layer for AI assistants, letting them read and write to a local Obsidian vault through MCP with validation, secret rejection, and deduplication.

Enables AI agents to store, search, and retrieve long-term memories with BM25 full-text search, auto-tagging, and importance scoring.

Serverless, 100% decentralized P2P storage engine and shared memory mesh for autonomous AI agents via Hyperswarm DHT and Hypercore v10. Zero cloud costs, sub-50ms sync, and OWASP 2026 agentic security hardening.

Self-hosted MCP + REST continuity hub for coding agents. Tracks unfinished work, progress, overlap, reminders, and project context across Cursor, Codex, Claude Code, and other MCP clients.

Exposes bounded MCP tools that let connected coding agents resolve a matter by natural language, search and page through an archived read-only store of Codex and ZCode session history, and write back attributed notes with evidence IDs without auto-merging disagreements.

Enables MCP host agents to maintain a locally persisted dynamic personality and identity across sessions, context compaction, and sub-agents, with emotion- and drive-driven tone adaptation through nine MCP tools.

High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 159 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies.

AI-operable research workspace integrating Zotero, Obsidian, and NotebookLM. Search papers (arXiv/Semantic Scholar/PubMed/CrossRef), ingest into Zotero, sync per-paper notes to Obsidian, verify NotebookLM briefs. All three external tools optional.

Enables users to import, synchronize, index, and search their conversations from Gemini, Search AI Mode, AI Studio, NotebookLM, My Activity, and related services through MCP clients. It also fetches individual chats from pasted URLs for continuation or project creation, storing local Markdown transcripts and providing SQLite FTS5 full-text search.

Enables AI agents to resolve typed routing, loop-stall arbitration, and tool safety checks locally at sub-millisecond latency, avoiding unnecessary frontier LLM calls. It enforces reversible execution checkpoints, token budgets, and decayed episodic memory for safe, privacy-first autonomous operation.

Exposes 7-prime spine, 7 κ-bands, and 6 fold operations as native tools and resources in any MCP client like Claude Code, Cursor, or Cline.

MCP server for foldkit, exposing 7-prime spine, κ-bands, and fold operations as tools and resources, enabling fold operations, κ-band classification, and state probing in any MCP client.

An advanced contextual memory server for agent orchestration providing chronological history, semantic vector search via Redis Stack, and temporary scratchpad storage. It also enables context compression through history rollups and facilitates inter-agent communication using a Redis-based Pub/Sub system.

Persistent decision memory and contradiction detection for AI coding agents. Enforces architectural consistency across sessions — the agent cannot code until it loads prior decisions. Human resolves conflicts on a dashboard or in chat.

Enables analysis of documents far larger than an LLM's context window by letting the model emit constrained Nucleus symbolic commands that are parsed, type-checked, and executed server-side against the document. Results and agent context are kept as compact in-memory handles and memos, cutting token usage dramatically while supporting recursive sub-queries and multi-context loading.

Enables interaction with GLPI (ITSM) through 71 tools covering tickets, assets, problems, changes, knowledge base, projects, users, and more, using SSE or stdio transport.

Privacy-first personal knowledge database for your AI that ingests data exports (Google Takeout first) and exposes them via MCP tools like search and list items. Runs locally with no cloud or telemetry.

Secure MCP server for querying Google NotebookLM notebooks. Enables AI assistants to list notebooks, read sources, and ask the NotebookLM AI questions about your sources.