"Searching for an MCP server with persistent memory for tool usage" matching MCP servers:

Enables Claude Code to leverage OpenAI models for expert code review, deep architecture analysis, and security audits, with automatic markdown report generation.

Translates natural language commands into structured geometric operations for a simulated CAD engine using LLMs. It enables users to create shapes, modify dimensions, and perform 3D operations like extrusion through the Model Context Protocol.

MCP server for querying OpenAI usage and cost data, including spend summaries, daily breakdowns, month-over-month comparisons, and token usage by model.

Provides vision capabilities to Reasonix, enabling analysis of images/videos, OCR, and comparisons via OpenAI-compatible vision models.

Bridges DeepSeek (text-only) with vision models via MCP, enabling image description and compression using any OpenAI-compatible visual API.

Semantic navigator for MCP tools that finds relevant tools by natural language intent, reducing token usage by 95%.

Enables local-first tracking of AI token usage and costs from Claude Code and OpenCode, answering queries about tokens, models, sessions, and cost through MCP tools and a CLI, with no network calls.

MCP server that reads local OpenClaw session files to provide token usage and cost data without any network calls or authentication.

Enables retrieving real Claude subscription usage statistics, including the 5-hour session window, weekly limit, and per-model limits, from the same endpoint Claude Code uses.

A local-first, multi-provider cost meter for LLM usage, exposed as MCP tools. Captures every call into a local SQLite ledger and lets any coding agent query spend, compare providers, and get recommendations — no cloud, no account. First-class support for Chinese providers (Qwen, DeepSeek) alongside Anthropic and OpenAI.

MCP server that routes natural language requests to structured tool calls using a LoRA-tuned small language model, with built-in validation, retry, and fallback recovery.

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.

The MCP server provides tools for entity extraction, query refinement, and relevance checking to enhance RAG applications by integrating with OpenAI and Gemini.

Provides a no-op 'think' tool that enables Claude to decompose complex problems and enhance reasoning by pausing to organize thoughts.

Two-layer memory for AI agents. Episodes compress into identity. The only MCP memory server with an immune system. Patterns earn permanence through evidence, false knowledge gets caught and demoted, and stale information fades — so your agent's memory gets smarter over time, not just bigger. Zero dependencies. 5 tools. Works with any MCP client.

Provides persistent memory for AI assistants via MCP, enabling them to store and recall facts, preferences, and tasks across conversations using either local file storage or a cloud backend with semantic search.

Cognitive memory engine for AI agents with 5,100+ knowledge modules, circadian rhythm awareness, emotional state tracking (PAD model), and hybrid semantic search. Supports persistent per-user memory, project-scoped contexts, and multi-protocol access.

Persistent memory MCP server for AI agents, using SQLite with hybrid keyword and semantic search for long-term memory storage.

MCP server for Kaggle API integration that allows creating, running, and managing Kaggle notebooks programmatically.

A fully local persistent memory layer for LLM coding agents (Claude Code, Codex, Gemini CLI, OpenCode). A shell wrapper intercepts tool invocations, fires hooks on every tool call, then runs a 3-layer pipeline (extract → compress to ≤500-token digest → merge into project memory doc) at session end. The next session gets prior context injected automatically.