AI Agent Integration (MCP)

Axiom supports the Model Context Protocol (MCP), allowing external logic-driven AI agents (like Claude Desktop) to securely interface with your decision matrix. By connecting an agent, you can delegate heavy contextual reasoning to an LLM, allowing it to autonomously evaluate options, suggest criteria modifications, and extract summary reports.

System Capabilities

Our MCP server hosts secured tools that allow an agent to:

  • Read Project State: Rapidly ingest your elimination criteria definitions, scoring structures, and current option pools.
  • Evaluate Exclusions: Autonomously check documents or URLs connected to an option and eliminate it if it falls afoul of deal-breaker constraints.
  • Score Synthetically: Synthesize qualitative data and reliably post numerical score values back into Axiom via the official API.

Connecting Claude Desktop

1. Provisioning an API Key

To grant an agent network authority, you need an API key bounded to your Organization.

  1. Navigate to Organization Settings.
  2. Drill into the API Keys sub-section.
  3. Mint a new key and securely store it.

2. Client Payload Configuration

To inject the MCP server into your local client, append the following JSON payload to your client's core integration file (e.g., claude_desktop_config.json).

Replace YOUR_API_KEY_HERE with your minted key.

{
  "mcpServers": {
    "axiom": {
      "command": "npx",
      "args": ["-y", "axiom-agent-mcp@latest"],
      "env": {
        "AXIOM_API_KEY": "YOUR_API_KEY_HERE"
      }
    }
  }
}

3. Prompting your Agent

Once booted, the MCP layer establishes the semantic bridge. You can now engage directly.

Example Invocations:

  • "Pull my 'Choosing a CRM' project in Axiom. Review their SOC2 docs and eliminate anyone without a certified audit."
  • "Evaluate the non-eliminated options against my 'Ease of Use' heuristic and provide a rationale score for each. Update Axiom."
PreviousStakeholder Sign-offs & Reaching Decisions