"Arm" matching MCP servers:

An MCP server that protects AI agents and RAG systems from adversarial poisoning attacks like prompt injection, steganography, and data anomalies through multi-layer sanitization, entropy-based detection, and consensus verification.

Enables AI assistants to access and query a verified knowledge base of Chinese whisky, including distillery profiles, flavor notes, product recommendations, regional maps, and content generation support.

A local, offline-first MCP server for searching, grepping, reading, rendering, and comparing long datasheet/TRM PDFs, using hybrid retrieval with BM25, dense embeddings, and visual page indexing.

Facilitates integration of Brave Search functionalities with AI assistants through the Model Context Protocol, enabling web and local searches using the Brave Search API.

MCP server that provides web search functionality using the Tavily API. It runs in stdio transport mode and can be integrated with Cursor or other MCP clients.

Gives MCP clients a small remote Streamable HTTP tool surface for a Brain memory database, letting agents store facts, retrieve current-truth answers with evidence, delete memories, and check their effective identity. Each call is scoped by a customer identifier for per-customer isolation, and the endpoint can optionally be secured as an OAuth 2.1 resource server.

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

This read-only MCP Server allows you to connect to Dynamics CRM data from Claude Desktop through CData JDBC Drivers. For full CRUD support, check out the first managed MCP platform: CData Connect AI (https://www.cdata.com/ai/).

This read-only MCP Server allows you to connect to Zoho CRM data from Claude Desktop through CData JDBC Drivers. For full CRUD support, check out the first managed MCP platform: CData Connect AI (https://www.cdata.com/ai/).

Enables semantic and hybrid search over documents and codebases backed by a Qdrant vector database, with collection management, document CRUD, metadata filtering, and AST-aware code indexing using local or cloud embedding providers. Supports natural language queries, incremental re-indexing of changed files, and custom configurable prompts for guided workflows.

Enables AI assistants to interact with HubSpot CRM data, providing tools for managing contacts and companies, retrieving activity and conversations, and performing semantic search with vector storage and caching for improved performance.

MCP server that provides semantic search, graph query, and keyword search tools for interacting with DocSmith's knowledge graph and documentation.

Persistent memory for Claude Code — a self-evolving knowledge layer that survives across sessions, grows from every conversation, and surfaces relevant context automatically.

A high-performance MCP server that connects tools like Cursor to Elasticsearch clusters using public-key authorization instead of API keys. It provides optimized tools for searching data, listing indices, and inspecting cluster mappings or shards with support for concurrent requests.

Enables automatic memory retrieval and injection for AI conversations to provide continuous learning through semantic search and memory management.

Integrates CRM data with AI agents to manage leads, track pipeline statistics, and search price catalogs via Supabase. It enables automated lead creation, stage updates, and history tracking through natural language commands.

Enables AI assistants to query a person's CV and portfolio content via MCP tools and resources, returning grounded answers from local markdown data instead of relying on resume parsing.

MCP server for indexing source code from repositories into a Neo4j graph database and enabling Graph RAG-based search and traversal of functions via natural language queries.