Key Takeaways
- Add @agent-infra/mcp-server-lead-enrichment to Claude Code for live firmographics, technographics, and intent signals.
- Pay only when confidenceScore > 0.6—zero cost for low-quality matches.
What Changed
A new MCP server, @agent-infra/mcp-server-lead-enrichment, gives Claude Code native access to live B2B lead data. Instead of duct-taping APIs into your workflow, you can now ask Claude Code to verify a company's size, revenue, tech stack, or hiring signals directly—right from your terminal.
The server exposes an enrich_lead tool that returns structured JSON-RPC payloads with:
- Deep Firmographic Data — company size, revenue brackets, HQ location, verified industry
- Technographic Intelligence — real-time detection of cloud providers, CRM, frontend frameworks (e.g., AWS, Salesforce, React, Snowflake)
- Dynamic Intent Signals — hiring status, recent funding rounds
- Confidence Score — a 0–1 score indicating match reliability
What It Means For You
Claude Code users now have a way to ground their AI agents in real-world company data. This is huge for developers building sales tools, market research scripts, or internal dashboards. Instead of hallucinating company details, Claude Code can pull verified data on demand.
The server uses strict Zod annotations on all tool parameters. This forces the LLM to provide valid domain formats, preventing the "garbage in, garbage out" problem common in AI agents. Claude Code won't invent a company's revenue bracket—it must call the tool with valid inputs, and the tool returns ground truth.
Try It Now
Add the server to Claude Code with the claude mcp add command:
claude mcp add b2b-enrichment -- npx -y @agent-infra/mcp-server-lead-enrichment
Then set the required environment variables. In your shell:
export ENRICHMENT_API_KEY="YOUR_FREE_API_KEY_HERE"
export MCP_ENDPOINT="https://lead-enrichment-mcp.agent-infra.workers.dev/mcp"
Or add it to your ~/.claude.json under mcpServers if you prefer persistent config:
{
"mcpServers": {
"b2b-enrichment": {
"command": "npx",
"args": ["-y", "@agent-infra/mcp-server-lead-enrichment"],
"env": {
"ENRICHMENT_API_KEY": "YOUR_FREE_API_KEY_HERE",
"MCP_ENDPOINT": "https://lead-enrichment-mcp.agent-infra.workers.dev/mcp"
}
}
}
}
Once configured, you can prompt Claude Code like:
"Use the enrich_lead tool to check if Acme Corp is a good fit for our enterprise software. Get their industry, tech stack, and hiring status."
Claude Code will call the tool, receive the structured payload, and reason over it—no manual API calls needed.
Risk-Free Billing
One standout feature: Risk-Free Metered Billing. The server only charges for successful enrichments where confidenceScore exceeds 0.6. If the match is low quality or not found, the query costs $0. This is a game-changer for building high-volume SDR swarms or research agents—you won't burn credits on empty results.
Get Your Free API Key
Grab a free API key at lead-enrichment-mcp.agent-infra.workers.dev and start enriching leads natively within Claude Code today.
Source: dev.to
[Updated 10 Aug via devto_mcp]
The MCP server also supports autonomous SDR swarm architectures, with a sample JSON-RPC response showing a confidenceScore of 0.94 and an "attribution" field marked "Verified" [per dev.to]. This attribution layer may help teams audit lead quality at scale. The guide also demonstrates integration with Claude Desktop and Cursor via claude_desktop_config.json, using an environment variable named LEAD_ENRICHMENT_API_KEY rather than the ENRICHMENT_API_KEY shown in the original setup, so double-check your config naming.
