ranger-rag-mcp
Provides integration with Apache Ranger to enforce authorization policies on RAG knowledge base queries, checking user permissions before forwarding requests to the RAG system.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@ranger-rag-mcp As user 'alice', query the 'Finance KB' knowledge base: What was Q3 revenue?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Ranger RAG MCP Server
MCP server that integrates Apache Ranger authorization with RAG (Retrieval Augmented Generation). When a user queries a knowledge base, the server first checks Ranger policies to verify the user has permission — if denied, the query is rejected before reaching the RAG system.
Architecture
User (AI Agent) ──→ MCP Server ──→ Ranger Policy Check ──→ RAG Studio
│
DENY → "Access Denied"
ALLOW → Forward query, return resultsRelated MCP server: ToolBridge
Features
Per-knowledge-base authorization — Ranger policies control which users can access which knowledge bases
Transparent enforcement — denied queries never reach the RAG system
Policy-based access control — uses existing Ranger infrastructure (policies, users, groups)
Automatic retries — exponential backoff on transient errors
Fallback evaluation — if Ranger's evaluateOnce API isn't available, evaluates policies locally
MCP Tools
Tool | Description |
| Query a KB with Ranger auth check |
| List KBs the user can access |
| Pre-flight permission check |
| Show all RAG Ranger policies (admin) |
Setup
1. Create a Ranger Service for RAG
In Ranger Admin, create a new service (or use an existing custom service type) with:
Service Name:
ragResource:
knowledge_base(string, supports wildcards)Access Types:
read,write
2. Create Ranger Policies
Example policies:
Policy Name | Resource | Users | Access |
Finance KB - Analysts |
| alice, bob | read |
HR KB - HR Team |
| charlie | read |
All KBs - Admin |
| admin | read, write |
3. Install and Configure
git clone <repo-url>
cd ranger-rag-mcp
python3 -m venv .venv
source .venv/bin/activate
pip install -e .Copy .env.example to .env and fill in your values:
cp .env.example .env
# Edit .env with your Ranger and RAG Studio credentials4. Configure MCP Client
Claude Desktop (~/Library/Application Support/Claude/claude_desktop_config.json):
{
"mcpServers": {
"ranger-rag-mcp-server": {
"command": "/FULL/PATH/TO/ranger-rag-mcp/.venv/bin/python",
"args": ["-m", "ranger_rag_mcp_server.server"],
"env": {
"RANGER_GATEWAY_URL": "https://<gateway>/<topology>/cdp-proxy-api/ranger/",
"RANGER_USER": "<workload_username>",
"RANGER_PASS": "<workload_password>",
"RANGER_SERVICE_NAME": "rag",
"RAG_STUDIO_URL": "https://<rag-studio-url>",
"RAG_STUDIO_API_KEY": "<api_key>"
}
}
}
}Agent Studio / Kiro:
{
"mcpServers": {
"ranger-rag-mcp-server": {
"command": "uvx",
"args": [
"--from",
"git+https://github.com/<your-org>/ranger-rag-mcp@main",
"run-server"
],
"env": {
"RANGER_GATEWAY_URL": "https://<gateway>/<topology>/cdp-proxy-api/ranger/",
"RANGER_USER": "<workload_username>",
"RANGER_PASS": "<workload_password>",
"RANGER_SERVICE_NAME": "rag",
"RAG_STUDIO_URL": "https://<rag-studio-url>",
"RAG_STUDIO_API_KEY": "<api_key>"
}
}
}
}Configuration
Ranger
Variable | Required | Description |
| Yes | Ranger Admin REST API URL via Knox |
| Yes | Workload username for Ranger API auth |
| Yes | Workload password for Ranger API auth |
| No | Ranger service name (default: |
RAG Studio
Variable | Required | Description |
| Yes | RAG Studio base URL |
| Yes | RAG Studio API key |
| No | Project ID (default: 1) |
| No | Number of chunks to retrieve (default: 5) |
| No | LLM model for response generation |
TLS/HTTP
Variable | Default | Description |
|
| Set |
| — | Path to CA certificate bundle |
|
| Request timeout in seconds |
Example Usage
Once configured, ask the AI:
# User with access → gets results
"As user 'alice', query the 'Finance KB' knowledge base: What was Q3 revenue?"
# User without access → gets denied
"As user 'bob', query the 'HR Policies' knowledge base: What is the PTO policy?"
# Check what a user can access
"List all knowledge bases that user 'alice' can access"
# Admin: see all policies
"Show me all the RAG access policies"How It Works
User calls
query_knowledge_base(user="alice", knowledge_base="Finance KB", query="...")MCP server calls Ranger:
POST /service/plugins/policies/evaluateOnce— "Can alice read Finance KB?"Ranger evaluates policies:
Checks all enabled policies for the
ragserviceLooks for policies where resource
knowledge_basematches "Finance KB"Checks if user "alice" or any of her groups appear in
policyItemswithreadaccess
If ALLOWED: Forward query to RAG Studio, return answer
If DENIED: Return
ACCESS_DENIEDwith reason — RAG Studio is never contacted
Ranger Policy Structure
The server expects Ranger policies with this structure:
{
"service": "rag",
"name": "Finance KB Access",
"isEnabled": true,
"resources": {
"knowledge_base": {
"values": ["Finance KB"],
"isRecursive": false
}
},
"policyItems": [
{
"users": ["alice", "bob"],
"groups": ["finance-team"],
"accesses": [
{"type": "read", "isAllowed": true}
]
}
]
}License
Apache License 2.0
Available Tools
4 toolscheck_accessA
Check if a user has access to a specific knowledge base without querying it.
Useful for pre-flight permission checks before attempting a query.
Args: user: Username to check permissions for. knowledge_base: Name of the knowledge base. access_type: Type of access to check ('read' or 'write'). Default: 'read'.
Returns: Access decision with policy details.
Inputs: user (required), knowledge_base (required), access_type. Returns: result
list_knowledge_basesA
List all knowledge bases the user has access to.
Checks Ranger authorization for each knowledge base and returns only those the user is permitted to query.
Args: user: Username to check permissions for.
Returns: List of accessible knowledge bases with their details.
Inputs: user (required). Returns: result
list_policiesA
List all Ranger policies for the RAG service.
Shows which users/groups have access to which knowledge bases. Useful for administrators to understand the current access control setup.
Returns: List of policies with their resource definitions and access rules.
Inputs: no named parameters. Returns: result
query_knowledge_baseA
Query a RAG knowledge base with Ranger authorization check.
First checks Apache Ranger to verify the user has 'read' access to the specified knowledge base. If allowed, forwards the query to RAG Studio and returns the answer. If denied, returns an access denied message.
Args: user: Username to check permissions for (e.g., 'alice', 'bob'). knowledge_base: Name of the knowledge base to query (e.g., 'Finance KB', 'HR Policies'). query: The question to ask the knowledge base.
Returns: If authorized: The RAG response with answer and sources. If denied: An access denied message with the reason.
Inputs: user (required), query (required), knowledge_base (required). Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 4 tools
Each tool has a clearly distinct purpose: querying a KB, listing accessible KBs, checking access pre-flight, and listing all policies. There is no meaningful overlap that would cause confusion, as even the access check in query is incidental to its primary function.
All tool names follow a consistent verb_noun snake_case pattern (query_knowledge_base, list_knowledge_bases, check_access, list_policies). The two 'list' verbs are used consistently with different objects, and there are no mixed conventions.
Four tools is a well-scoped count for a RAG query service with authorization checks. Each tool covers a necessary function without redundancy, fitting the typical 3-15 range comfortably.
The core workflows of querying, listing accessible bases, pre-flight access checks, and viewing policies are covered. Minor gaps exist such as no policy management or write operations, but these are likely out of scope for a read-oriented query server.
Related MCP Connectors
MCP server unifying ERPs, CRMs, APIs and knowledge base for Claude, ChatGPT and Gemini.
MCP gateway with runtime security policy, tool-call-level control, and audit of agent actions.
AI governance MCP server for EU AI Act compliance and jurisdiction verification
The CustomGPT.ai MCP server is a fully managed, RAG-powered endpoint that connects large language models with private knowledge bases and external data sources. It provides tools for retrieval-augmented generation queries (send_message), data ingestion (upload_file), and source listing, enabling AI agents to query private documents like PDFs with high accuracy and real-time citations.
Related MCP Servers
- AlicenseBqualityBmaintenanceA production-grade MCP server for integrating RAG into AI agents, supporting multiple vector databases with enterprise security and dynamic tool selection.716MIT
- FlicenseNot gradedqualityDmaintenanceA governed MCP server for integrating AI agents with customer data, featuring role-based access control, field redaction, and human-in-the-loop approval for secure support operations.1-
- AlicenseNot gradedqualityDmaintenanceAn MCP server that enforces runtime governance on AI agent actions — file access, command execution, delegation chains, and permission escalation.MIT
- FlicenseNot gradedqualityCmaintenanceMCP server for a modular RAG system that enables natural language question answering over enterprise documents with intent-aware routing, adaptive retrieval, and citation-backed responses.-