Aare MCP
Enables formal verification of LLM outputs against compliance ontologies using Z3 SMT solver. Validates that AI-generated content adheres to regulatory requirements like HIPAA or mortgage compliance rules.
README
aare-mcp
MCP (Model Context Protocol) server for aare-core Z3 SMT verification.
This server exposes aare-core's formal verification capabilities to LLM applications like Claude Desktop and Claude Code.
Installation
pip install aare-mcp
Or install from source:
cd aare-mcp
pip install -e .
Configuration
Claude Desktop
Add to your Claude Desktop configuration (~/Library/Application Support/Claude/claude_desktop_config.json on macOS):
{
"mcpServers": {
"aare-verify": {
"command": "aare-mcp"
}
}
}
Claude Code
Add to your Claude Code MCP configuration:
{
"mcpServers": {
"aare-verify": {
"command": "aare-mcp"
}
}
}
Available Tools
verify
Verify LLM output against a compliance ontology using Z3 SMT solver.
Parameters:
llm_output(string, required): The LLM-generated text to verifyontology(string, required): Name of the ontology to verify against
Example:
verify(
llm_output="Based on your income of $75,000 and the property value of $400,000, I recommend a loan amount of $320,000 with an APR of 6.5%.",
ontology="mortgage-compliance-v1"
)
Response:
{
"verified": true,
"ontology": "mortgage-compliance-v1",
"violations": [],
"parsed_data": {
"income": 75000,
"property_value": 400000,
"loan_amount": 320000,
"apr": 6.5
},
"proof": {
"method": "Z3 SMT Solver",
"version": "4.12.1",
"results": []
},
"execution_time_ms": 12
}
list_ontologies
List all available compliance ontologies.
Parameters: None
Response:
{
"ontologies": [
"example",
"hipaa-v1",
"mortgage-compliance-v1"
],
"count": 3
}
parse_claims
Extract structured data from LLM output using ontology-defined extractors. Useful for debugging.
Parameters:
llm_output(string, required): The LLM-generated text to parseontology(string, required): Name of the ontology containing extractor definitions
Response:
{
"ontology": "mortgage-compliance-v1",
"parsed_data": {
"income": 75000,
"loan_amount": 320000
},
"extraction_details": {
"income": {
"value": 75000,
"confidence": 0.95,
"source": "75,000",
"extractor_type": "money"
}
}
}
Custom Ontologies
Place custom ontology JSON files in the ontologies/ directory or set the ONTOLOGY_DIR environment variable:
export ONTOLOGY_DIR=/path/to/your/ontologies
aare-mcp
Development
# Install dev dependencies
pip install -e ".[dev]"
# Run tests
pytest
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.