inferra-mcp

Inferra MCP Server

Use Inferra — deterministic rule-based decisions with RAG-powered explanations — from Claude Code, Claude Desktop, or any MCP client.

The verdict always comes from the Rete rule engine (auditable, reproducible); the LLM only explains why, grounded in your ingested policy documents.

Tools

Tool	What it does
decide	Make a decision in a domain (structured facts and/or free text)
list_rules	Inspect a domain's rules — conditions, verdicts, salience, overlaps
ingest_text	Add policy text to a domain's knowledge base
list_documents	Browse a domain's ingested documents
get_usage	Check your plan and remaining monthly decision quota

Install

No install needed with uv — uvx inferra-mcp fetches and runs the server on demand (see the config snippets below).

Alternatively, install it as a package:

pip install inferra-mcp         # from PyPI
pip install ./mcp-server        # or from source, in this repo

Configure

First create an API key: sign in at ai-rete-rag.com, open Settings → API Keys, and create a key (ik_... — shown once).

Claude Code

claude mcp add inferra -e INFERRA_API_KEY=ik_your-key-here -- uvx inferra-mcp

(If you installed via pip, use -- inferra-mcp instead of -- uvx inferra-mcp.)

Claude Desktop / other clients (JSON)

{
  "mcpServers": {
    "inferra": {
      "command": "uvx",
      "args": ["inferra-mcp"],
      "env": {
        "INFERRA_API_KEY": "ik_your-key-here"
      }
    }
  }
}

(With a pip install, set "command": "inferra-mcp" and drop "args".)

Environment variables:

Variable	Default	Purpose
INFERRA_API_KEY	(none)	Your API key — authenticates calls and ties them to your plan quota
INFERRA_API_URL	https://ai-rete-rag.com	API base URL — point at http://localhost:8000 for local dev

Without a key you can still explore the shared demo domains (loan, fraud, clinical, …) subject to free-tier limits.

Example

"Use inferra to decide whether this loan application should be approved: credit score 645, annual income $52k, requested amount $30k."

Claude calls decide(domain="loan", facts={...}) and returns the rule-derived verdict plus a plain-English explanation citing the underwriting policy.