"Deutsche Bank" matching MCP servers:

Enables agents to query a git-native markdown corpus for the specs governing a file in about two reads, plus supports lexical topic search with expansion. Includes maintenance loops that surface uncovered code and stale governing docs to keep the corpus honest.

A database-backed MCP server that acts as a project memory bank, enabling AI assistants to store, retrieve, and search structured context like decisions, tasks, and architecture using SQLite and vector embeddings.

Enables LLM clients to read, search, create, update, and delete notes in a self-hosted shared memory bank over MCP, using hybrid vector and full-text search with optional summarization.

A local MCP server that helps the Payments team by querying microservice specs, payment flows, triaging CS tickets with GCP analysis, and calling Stark Bank APIs in development/sandbox environments.

An MCP server that adds AI-powered document intelligence to Paperless-ngx, enabling semantic search, automatic classification, receipt data extraction, bank statement matching, and accounting export — all running locally via Ollama.

Enables LLMs to generate and retrieve long-term memories using Vertex AI Memory Bank, with tools for memory initialization, generation, retrieval, creation, deletion, and listing.

A distributed memory bank MCP server that stores AI agent memories in a KùzuDB graph database with repository/branch isolation. Features AI-powered memory optimization, dependency tracking, and comprehensive graph analysis capabilities.

Builds a searchable memory bank from persona-specific PDF content and exposes it as an MCP tool for querying.

Provides a project memory bank and RAG context provider for enhanced code understanding and management through vector embeddings, integrated with RooCode and Cline.

Enables seamless integration with Convolut Context Bank for AI-powered context management, search, consolidation, and export operations. Provides 11 powerful tools for creating, managing, and analyzing contexts with semantic search and automated planning capabilities.

Enables hybrid retrieval over agent memory and documents by fusing BM25 lexical and cosine vector rankings with reciprocal rank fusion, plus knowledge graph expansion, semantic caching, and context reordering for RAG.

Enables agents to retrieve relevant context via a zero-dependency hybrid search engine that blends sparse keyword-based lexical ranking with dense vector similarity scores into one fused result set, then refines it with knowledge graph triplet expansion and lost-in-the-middle context reordering. It also provides episodic memory consolidation, recency decay, and semantic query caching, exposed as a JSON-RPC 2.0 stdio MCP server for clients such as Claude Desktop, Cursor, and Windsurf.

Context Portal (ConPort): A memory bank MCP server building a project-specific knowledge graph to supercharge AI assistants. Enables powerful Retrieval Augmented Generation (RAG) for context-aware development in your IDE.

Provides LLM-free search, fetch, and rerank tools over any reachable SearXNG instance, returning extracted, deduplicated, cross-encoder-reranked results with citation-ready markers and coverage signals. Lets agent hosts such as Open WebUI, Claude, or tool-calling models drive their own iterative research loop while sharing one deterministic retrieval and ranking core.