"ChatBot" matching MCP servers:

Enables querying internal documents indexed in Glean through a natural-language chat interface, returning answers with cited sources.

A serverless backend that enables natural language querying of a Postgres database, converting user questions into SQL and returning structured, UI-friendly responses.

A production-grade AI chatbot that enables real-time information retrieval and retrieval-augmented generation for website content. It integrates MCP tools to fetch live data while providing a responsive chat interface with strict guardrails against misinformation.

Enables AI chatbots to securely answer natural-language questions against Oracle databases by discovering metadata, generating and validating read-only SQL, executing with limits, masking sensitive data, and logging all activity.

Exposes a local RAG document index as MCP tools (ask, search, rebuild_index, status) for MCP clients like Claude Desktop and Claude Code to query your documents over stdio.

MCP server that exposes an Italian textbook's OCR content, structured exercises, and progress tracking, enabling chatbot agents to interact with the book for language learning.

An AI-powered chatbot that researches and tracks LLM inference pricing across providers, stores structured pricing data locally, and answers pricing questions via natural language.

An MCP server that integrates the Glean API to provide search results and chatbot interaction.

A multi-functional AI agent with an Arabic legal chatbot, Google search capability, and a VAE model that generates handwritten digit images.

MCP server + RAG chatbot that makes your MDX documentation searchable by AI assistants. Built on BM25 + metadata filtering.

Enables read-only interaction with NetBox network documentation and infrastructure data through LLMs. Allows querying devices, sites, IP addresses, and viewing change history via natural language.

Enables employees to ask natural-language questions about a client's dbt semantic layer through the chatbot they already use, asking for clarification when needed, refusing when data can't answer, and logging every interaction so the semantic layer improves over time.

Provides a curated technical glossary with search, lookup, and category listing tools, enabling AI assistants to answer tech concept questions via MCP.