"Oh Dear" matching MCP servers:

MCP server for Yu-Gi-Oh! card data, providing cards, prices, banlists, rules, rulings, relations, and deck tools via a local SQLite database with semantic search.

Provides MCP tools to search, retrieve, and answer questions from the public Open Finance Brasil Confluence documentation using BM25-based local indexing.

Enables LLM agents to query and analyze hh.ru job vacancies via full-text and semantic search, with tools for vacancy lookup, skill statistics, market overview, and candidate profile comparison.

Provides tools for searching Agent8 game development code examples and system prompts to assist in Agent8 SDK development.

Give your AI agents access to 8,500+ community curated awesome lists with over 1 million curated resources.

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.

Enables coding agents to query a team knowledge base via MCP, performing semantic search and asking questions that return grounded, citation-backed answers from ingested documents.

Provides retrieval-grounded, citation-verified access to Philippine law and compliance, including statutes, jurisprudence, and government issuances across 15 compliance domains.

Enables code agents to persist and recall durable project knowledge — rules, decisions, procedures, learnings and secrets — across sessions at low context cost, with accent-insensitive PT-BR search, scoped per repository/workspace, and secrets that stay out of the model's context.

MCP server that converts .eml email exports (Gmail, Outlook, and other archives) into clean Markdown with YAML front matter — splitting reply threads, stripping signatures and quoted history, extracting attachments, and parsing calendar invites. Built for feeding archived email into RAG and LLM pipelines.

MCP server for Google's Gemini File Search (RAG). Manage file search stores, upload documents, and query with RAG through 12 tools.

Enables AI assistants to securely connect to Snowflake data warehouses and execute SQL queries through natural language interactions. Supports multiple authentication methods and provides formatted query results with built-in security controls.

Provides OpenCode with adaptive long-term memory by storing preferences, lessons, and usage history locally in SQLite, enabling AI to remember and adapt to users through context-based learning.

Enables AI coding agents to intelligently index and search codebases with sub-20ms retrieval, 8x memory compression, and cross-encoder reranking via MCP stdio.

Turns a plain-Markdown Obsidian vault into a second brain that any MCP-speaking coding agent can search, read, extend, and maintain, using swappable SQLite, Qdrant, or markdown memory backends with automatic re-indexing and wiki-link graph navigation. Exposes read, write, and index tools plus an operator CLI for health, linting, and graph export.

Shrimp Task Manager is a task tool built for AI Agents, emphasizing chain-of-thought, reflection, and style consistency. It converts natural language into structured dev tasks with dependency tracking and iterative refinement, enabling agent-like developer behavior in reasoning AI systems.

Enhances large language models with competitive programming knowledge by leveraging OI-Wiki content through vector search, allowing models to retrieve relevant algorithms and techniques.

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.

Enables academic literature management through PDF import, hybrid search, knowledge graph construction, and automated literature review generation. Combines full-text search with semantic vector search for comprehensive paper analysis.

An MCP server that uses Groq's API to expose raw chain-of-thought tokens from Qwen's qwq model, enabling LLMs to think step-by-step before responding.