"Information on MCP-Codex-Keeper" matching MCP servers:

Enables Codex to rank available tools and skills, rerank code and documentation search results, and triage saved output artifacts using Jev-based relevance scoring while leaving final decisions to Codex.

Your coding agent remembers how it solved past tasks and reuses it next time: trigger, steps, outcome, lessons. Hooks recall the right skill before a task; skills strengthen with confirmed use and unused ones decay. Local SQLite, no API key, nothing leaves your machine. 9 MCP tools, works with Claude Code, Codex and Cursor. Agent-written memory stays untrusted until you approve it.

Enables developers and AI agents to compress context, plan token budgets, rerank results, patch code, analyze ASTs and dependencies, isolate stack traces, compile polyglot types, solve deterministic math, schedule constraints, judge A/B tests, and diff agent memory checkpoints through 12 specialized tools.

A local MCP server that provides semantic code search for Python codebases using tree-sitter for chunking and LanceDB for vector storage. It enables natural language queries to find relevant code snippets based on meaning rather than just text matching.

Memory vaults on your own machine, one per life domain, retrieved with a local BM25 index fused with vector search, where the human decides which vaults a model may answer from. Requires the Mnemosyne OS desktop app running locally; it also reports what other coding agents on the same machine are doing.

DevsContext is an MCP server that provides AI coding agents with synthesized engineering context—requirements, decisions, architecture, and standards—from tools like Jira and Slack. It fetches and synthesizes relevant information on demand to help agents work on tasks correctly.

Provides MCP tools for Friday AI, enabling code indexing, Graph RAG, coding plans, and PR/MR operations via AI coding assistants like Cursor, Claude Code, and Codex.

Provides persistent, searchable memory for AI agents, enabling them to retain, recall, and reflect on information across conversations.

A remote MCP server providing a tool for searching and querying ATprotocol documentation, helping developers easily access information while building on the protocol.

An MCP server that provides semantic memory on top of Qdrant vector search, with tools to store and retrieve information using embeddings.

Enables storing and retrieving text passages based on semantic meaning using local embeddings (Ollama) and vector storage (ChromaDB), allowing conversational memorization and retrieval of information.

Enables web search capabilities through the Tavily API. Allows users to search the web for information using natural language queries via the MCP protocol.

Provides a durable memory layer for coding agents like Claude Code and Codex by indexing codebases and enabling RAG queries, reducing rediscovery tokens and providing senior-engineer orientation.

A Model Context Protocol server that runs on Cloudflare Workers with OAuth login, allowing clients like Claude Desktop to connect to it for tool-augmented AI interactions.

MCP server providing context usage estimation, conversation compaction, and durable semantic memory via local embeddings and SQLite.

A Model Context Protocol server that enables web search capabilities using the Tavily API, allowing AI models to retrieve current information from the internet through natural language commands.

This read-only MCP Server allows you to connect to Act-On data from Claude Desktop through CData JDBC Drivers. Free (beta) read/write servers available at https://www.cdata.com/solutions/mcp

Utilizes Gemini API and Google Search to generate answers based on the latest information for user queries.

MCP server providing durable Substrate organizational memory tools, including search, read, query, ingest, remember, and sync. It integrates with Codex to automatically capture completed turns and session boundaries for persistent memory.

Enables Codex to list and read saved Claude Code conversations, retrieve incremental context updates before replies, and optionally ask Claude text-only follow-up questions within a selected session without disrupting the workflow.