MCP

Customer intelligence for AI agents

Customer intelligence exposed as structured tools for any MCP-compatible client.

Every agent you build for GTM needs customer context. Today you are wiring that up yourself. Connectors to Gong, chunking, reranking, prompt engineering, citation tracking, error handling. Amdahl ships it as an MCP server. Your agent calls one tool, gets a cited answer grounded in real buyer conversations, and moves on. That is the entire pitch.

Three lines of config in your Claude Desktop, Cursor, or custom agent. Your first tool call in under two minutes.

Claude Desktop config

json
{
  "mcpServers": {
    "amdahl": {
      "url": "https://app.amdahl.co/mcp",
      "headers": {
        "Authorization": "Bearer amdhl_YOUR_API_KEY_HERE"
      }
    }
  }
}

Connect from

Claude Desktop, Claude Code, and Cursor all speak the same MCP protocol. Generate an API key at app.amdahl.co, then paste the snippet below into the client of your choice. Windsurf, custom Anthropic SDK agents, and custom OpenAI function-calling work the same way.

Claude Desktop

Add to your Claude Desktop config and restart.

json
{
  "mcpServers": {
    "amdahl": {
      "url": "https://app.amdahl.co/mcp",
      "headers": {
        "Authorization": "Bearer amdhl_YOUR_API_KEY_HERE"
      }
    }
  }
}

Claude Code

One command from the CLI:

bash
claude mcp add amdahl https://app.amdahl.co/mcp \
  --header "Authorization: Bearer amdhl_YOUR_API_KEY_HERE"

Cursor

Add to Cursor settings under MCP servers.

json
{
  "mcp": {
    "servers": {
      "amdahl": {
        "url": "https://app.amdahl.co/mcp",
        "auth": { "type": "bearer", "token": "amdhl_YOUR_API_KEY_HERE" }
      }
    }
  }
}

Security and compliance

The Amdahl MCP was built for a CTO review on day one. Every connection is authenticated, every call is logged, every customer’s data sits in its own isolated tenancy.

SOC 2 Type 2 certified
Audited controls across security, availability, and confidentiality. Per-customer data isolation enforced at the database layer.
Encryption in transit and at rest
TLS 1.2 or higher on every connection. AES-256 at rest. Zero-retention agreements with every LLM provider Amdahl queries on your behalf.
Scoped, revocable API keys
Generate a key per agent, scope it to the tools that agent should reach, revoke it the moment a teammate leaves. Read-only by default.
No training on customer data, ever
Your conversations never enter a model training corpus. The MCP returns answers grounded in your data; the data stays yours.
MCP semantics, plain English
Tool responses are sent to the agent runtime you chose: your Claude, your Cursor, your custom client. Amdahl does not send your data anywhere else. Rate limits, audit logs, and observability ship out of the box.

What agents are doing with this

Four shapes of workflow that builders are wiring up against the Amdahl MCP today. Each one is a real production pattern, not a demo script.

01

AI SDR grounded in verbatim buyer quotes

Every outbound email cites a real customer quote pulled through the data tool. The model never invents a persona.

amdahl.data({ action: "search", query: "ICP pain point: data pipelines", source_type: "transcripts" })
02

Content agent on a daily cron

A scheduled job calls the assets tool to draft a grounded LinkedIn post every morning. Every claim links to the source call.

amdahl.assets({ action: "generate", query: "today's POV on AI GTM", channel: "linkedin" })
03

RevOps retention agent

Pulls churn risk signal from the context tool, then drafts personalized retention outreach in the account owner's voice.

amdahl.context({ action: "query_substrate", intent: "answer_question", query: "churn signals this month" })
04

Battle card drafting from inside Cursor

An engineer working in Cursor asks for a competitor battle card. The MCP returns clustered objection language and verbatim wins, all cited.

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

Frequently asked

Connect Amdahl to your agent stack in three lines of config.