Ragora
This is a hosted MCP server that connects your AI assistant to Ragora's knowledge base platform via streamable HTTP. You point your client at their cloud endpoint with a Bearer token, no local setup required. It exposes three core tools: discover_collections to see what knowledge bases you have access to, search to query across all of them at once, and search_collection to narrow down by name with optional tag and metadata filters. Ragora also generates dedicated tools per collection like search_employee_handbook or get_topic_product_docs. Under the hood it runs hybrid search combining dense vectors and BM25. Reach for this when you want RAG over your own document collections without running infrastructure yourself.
- tools
- 4
- transport
- HTTP
- last updated
- Mar 5, 2026
Tools
4 toolsPublic tool metadata for what this MCP can expose to an agent.
discover_collectionsDiscover all knowledge bases you have access to. Returns collection names, descriptions, content types, stats, available operations, and usage examples for each collection. Call this first to understand what data is available before searching.
Discover all knowledge bases you have access to. Returns collection names, descriptions, content types, stats, available operations, and usage examples for each collection. Call this first to understand what data is available before searching.
No parameter schema in public metadata yet.
searchSearch across ALL your knowledge bases at once. Use this when you want broad results or aren't sure which collection has the answer. For targeted search in a specific collection, use search_collection() instead. Args: query: Natural language search query. top_k: Maximum number...2 params
Search across ALL your knowledge bases at once. Use this when you want broad results or aren't sure which collection has the answer. For targeted search in a specific collection, use search_collection() instead. Args: query: Natural language search query. top_k: Maximum number...
querystringtop_kintegersearch_collectionSearch a specific knowledge base by name. Use discover_collections() first to find available collection names. Args: collection_name: Human-readable collection name or slug (e.g. "employee_handbook"). query: Natural language search query. top_k: Maximum number of results to re...5 params
Search a specific knowledge base by name. Use discover_collections() first to find available collection names. Args: collection_name: Human-readable collection name or slug (e.g. "employee_handbook"). query: Natural language search query. top_k: Maximum number of results to re...
collection_namestringcustom_tagsvaluefiltersvaluequerystringtop_kintegercheck_balanceCheck your current credit balance. Returns your remaining balance and estimated USD value.
Check your current credit balance. Returns your remaining balance and estimated USD value.
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageReadme
Ragora MCP Server
Search your knowledge bases from any AI assistant using the Model Context Protocol.
Ragora's MCP server is a hosted cloud service — no local installation required. Just configure your AI tool with the server URL and your API key.
Server URL: https://mcp.ragora.app/mcp
Quick Start
1. Get an API Key
Sign up at ragora.app and create an API key at Settings > API Keys.
2. Connect Your AI Tool
Claude Desktop
Option 1: CLI (recommended)
claude mcp add --transport http ragora https://mcp.ragora.app/mcp \
--header "Authorization: Bearer sk_live_your_key_here"
Option 2: Config file
Add to ~/Library/Application Support/Claude/claude_desktop_config.json (Mac) or %APPDATA%\Claude\claude_desktop_config.json (Windows):
Details
- Repository
- github.com/velarynai/ragora-mcp
- Website
- ragora.app
- Categories
- AI & LLM Tools, Documents & Knowledge, Search & Web Crawling
- Transport
- HTTP
- Registry
- MCP registry, active
Related AI & LLM Tools MCP servers
View all
Future Video Studioariadne-coil/fvs-mcpCreate and manage cinematic AI video renders through the Future Video Studio Agent API.0stars
Voidfeed Mcpvoidfeedai-ops/voidfeed-mcpKnowledge API for AI agents — content, agent directory, model benchmarks, semantic search.0stars
RegexForgewalkojas-boop/regexforgeDeterministic regex synthesis from labeled examples. Zero LLM, proof matrix, backtracking audit.0stars
Withvibe Voterwithvibe/withvibe-voterVote-gated change control for WithVibe — the agent proposes a change via MCP; team approves first.0stars
Wish Gameworld.3keys/wish-gameWish game — every agent wish permanently reshapes a shared world. Free, no key needed.0stars
Context First Mcpxjtlumedia/context-first-mcp37-tool MCP server: context health, memory, reasoning, truthfulness & research pipeline.0stars