Wire the eval into your agents.

Score every draft against your calls and CRM — over MCP or REST.

Try it for free
claude plugin marketplace add amdahlco/amdahl-cookbook; claude plugin install amdahl-gtm@amdahl-cookbook

Connect in the Claude web app or Claude Desktop

  1. Open Claude and go to Settings → Connectors.
  2. Click Add Add custom connector.
  3. Name it Amdahl and set the URL to https://app.amdahl.co/mcp.
  4. Click Connect, then Configure.
  5. Sign in to Amdahl when prompted, then choose this workspace.

Need a config-file or CLI path instead?

  1. Generate an API key.
  2. Copy and paste the snippet below into the client of your choice:

Add to your Claude Desktop config and restart.

json
{
  "mcpServers": {
    "amdahl": {
      "url": "https://app.amdahl.co/mcp",
      "headers": {
        "X-API-Key": "amdhl_YOUR_API_KEY_HERE"
      }
    }
  }
}

Building a custom agent instead of an MCP client?

Secure by default.

Every connection is authenticated, every call is logged, every customer’s data sits in its own isolated tenancy. Same posture across MCP and REST.

SOC 2 Type 2 certified

Audited for security, availability, and confidentiality. Per-customer isolation at the database layer.

Encryption in transit and at rest

TLS 1.2+ in transit, AES-256 at rest. Zero retention with every LLM provider we query.

Scoped, revocable API keys

One key per agent, scoped to the tools it needs, revoked the moment a teammate leaves. Read-only by default.

No training on customer data

Your conversations never train a model. Answers stay grounded in your data; the data stays yours.

MCP semantics, plain English

Tool responses go to the runtime you chose (your Claude, Cursor, or custom client) and nowhere else. Rate limits, audit logs, and observability ship by default.

Agents that score drafts in production.

Score outbound before it sends

The SDR agent pastes the opener. Amdahl returns a score, gaps, and citations from won and lost deals. Thin evidence never ships.

amdahl.data({ action: "cluster_search", query: "objections in lost SMB deals matching this opener" })

Daily content draft eval

A cron scores the morning LinkedIn draft against recent customer language. Every mark links back to the source call.

amdahl.data({ action: "search", query: "buyer language for today's POV", source_type: "transcripts" })

Retention message scored against churn calls

Pulls churn signal from context, then scores the outreach draft against what at-risk accounts actually said.

amdahl.context({ action: "query_substrate", intent: "answer_question", query: "churn signals this month" })

Battle card claim scored in Cursor

An engineer pastes a competitive claim. The MCP returns a score plus clustered objections and cited wins.

amdahl.data({ action: "cluster_search", query: "competitor: ${competitor}" })

Run the eval from the agents you already use.