🎉 First 100 users offer: Get 35% off any plan — use code WEL35 at checkout. Sign up now →
Model Context Protocol

SocialEnrich MCP Server
Enrichment becomes a tool call.

Let Claude, OpenAI GPT, Cursor, and any AI agent query 950M+ profiles directly — social, behavioral, contact — with a single natural language command. Set up in 30 seconds.

Claude · MCP Native
OpenAI GPT · Function Calling
Cursor · MCP Plugin
What is MCP?

Model Context Protocol — an open standard for AI agents to access external context.

MCP (Model Context Protocol) is an open standard that allows AI models — Claude, GPT, Cursor, and other agents — to call external tools and retrieve data directly during reasoning.

Instead of users copy-pasting data into prompts, the AI agent automatically calls SocialEnrich MCP Server to fetch social profiles, behavioral signals, and verified contacts — then uses that context to complete the task.

SocialEnrich is the first enrichment platform to provide a native MCP server — turning 950M+ profiles into ready-made context for any AI agent.

AI Agent
Claude / GPT / Cursor
"Enrich jane@stripe.com before the call"
MCP Layer
SocialEnrich MCP Server
Tool call: enrich_contact(email)
Data Infrastructure
950M+ Profiles
Social · Behavioral · B2B · B2C
Response
Complete Human Profile
Contact + social + intent + insights
Integration Guide

Two ecosystems. One data layer.

SocialEnrich supports both Anthropic Claude (MCP native) and OpenAI GPT (function calling) — choose the protocol that fits your stack.

Anthropic Claude

MCP Native

Claude supports MCP protocol natively — SocialEnrich MCP Server registers as a tool and Claude can call it directly in conversation. Supports Claude Desktop, Claude API, and Claude in Cursor.

1

Install MCP Server

npm install -g @socialenrich/mcp-server
2

Configure Claude Desktop

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "socialenrich": {
      "command": "socialenrich-mcp",
      "env": {
        "SE_API_KEY": "se_live_..."
      }
    }
  }
}
3

Start using

Ask Claude: "Enrich jane@stripe.com and write a personalized email for her"

OpenAI GPT

Function Calling

OpenAI GPT-4o and GPT-4.1 support function calling — SocialEnrich registers as a function tool. Works with Chat Completions API, Assistants API, and custom GPT Actions.

1

Install SDK

pip install socialenrich openai
2

Register SocialEnrich tools

tools = [{
  "type": "function",
  "function": {
    "name": "enrich_contact",
    "description": "Enrich a contact...",
    "parameters": { ... }
  }
}]
3

GPT automatically calls SocialEnrich

GPT receives tool_call → calls SocialEnrich API → gets profile → continues reasoning with full context.

MCP Tools Available

6 tool calls. The entire 950M+ profiles.

MCP Server exposes 6 tools to AI agents — each tool maps to a core SocialEnrich capability.

enrich_by_email

Full contact enrichment from email address — returns social, behavioral, contact, insights.

enrich_by_email("jane@stripe.com")

enrich_by_phone

Enrich from phone number — supports international formats, auto-normalization.

enrich_by_phone("+84-xxx-xxx")

enrich_by_social_url

Enrich from LinkedIn URL, X/Twitter handle, or any social profile URL.

enrich_by_social_url("linkedin.com/in/...")

search_contacts

Search contacts by keyword, domain, title, or industry — returns a list of matches.

search_contacts("VP Sales fintech")

get_behavioral_signals

Retrieve behavioral data — intent signals, buying stage, cohorts — for a known contact.

get_behavioral_signals("jane@stripe.com")

check_credits

Check current credit balance — so agents know when to notify users about usage.

check_credits()
Real-World Example

Agent auto-researches a prospect before the call.

Here's a real workflow: A sales rep asks Claude to enrich a prospect, write a personalized email based on social insights and behavioral signals — all in 1 conversation turn.

Claude calls SocialEnrich MCP → receives complete profile → uses personal insights to craft an outreach message. Time: 5 seconds instead of 30 minutes of manual research.

See more examples →
Claude MCP
OpenAI Functions
// User prompt in Claude Desktop:
// "Enrich jane@stripe.com and write
//  a personalized outbound email"

// Claude automatically calls MCP tool:
Tool call: enrich_by_email
Input:  { "email": "jane@stripe.com" }

// SocialEnrich returns:
{
  "contact": {
    "name": "Jane Doe",
    "title": "VP of Sales",
    "company": "Stripe"
  },
  "insights": {
    "interests": ["AI sales tools"],
    "communities": ["Pavilion"],
    "podcast": "Revenue Architects"
  },
  "behavioral": {
    "intent": "evaluating_crm",
    "buying_stage": "evaluation"
  }
}

// → Claude writes email using above insights
// → Mention podcast, Pavilion community
// → Address CRM evaluation intent
MCP Use Cases

AI agent + SocialEnrich = GTM superpowers.

How revenue teams are using MCP Server in practice.

AI SDR Agent

Auto research + personalize outbound

Agent receives a list of prospects → calls SocialEnrich for each contact → writes personalized emails based on social insights, interests, and intent signals. Reply rate increases 3–5x compared to generic templates.

ClaudeSocialEnrich MCPOutreach
Pre-Meeting Briefing

Auto briefing 60 seconds before meeting

Agent runs before every meeting: enriches all attendees → compiles social profiles, mutual connections, behavioral signals → outputs a 1-page briefing for the AE.

GPT-4oSocialEnrichGoogle Calendar
Intent Monitoring Agent

Monitor intent signals and alert in real-time

Agent runs daily: checks behavioral signals for target account list → when an intent signal fires ("evaluating CRM", "hiring SDRs") → alerts SDR via Slack with full context.

n8nSocialEnrich APISlack
ABM Multi-Threading

Map the entire buying committee automatically

Agent receives target account → search_contacts finds all decision makers → enriches each person → identifies warm intro paths via relationship mapping → suggests multi-threading strategy.

ClaudeSocialEnrich MCPSalesforce
Claude vs OpenAI — Which to Choose?

Two protocols, same data layer.

Both access 950M+ profiles. They differ in integration approach — choose based on your current stack.

Criteria Claude (MCP) OpenAI GPT (Functions)
ProtocolMCP (Model Context Protocol)Function Calling / Tool Use
Setupnpm install + config JSONRegister function schema in API call
Setup time~30 seconds~5 minutes
Desktop App✓ Claude Desktop native✗ Needs custom app
IDE Integration✓ Cursor nativeVia extension
Conversation memory✓ Auto context window✓ Via messages history
Custom GPT / ActionsN/A✓ GPT Actions support
Assistants APIN/A✓ Native tool
Data access950M+ profiles950M+ profiles
Behavioral signals✓ Full✓ Full
CreditsShared poolShared pool
Best forClaude power users, Cursor devs, MCP ecosystemGPT ecosystem, custom agents, Assistants API

Conclusion: Use Claude MCP if you're in the Claude/Cursor ecosystem. Use OpenAI functions if you build on the GPT API. Both access the same data layer.

Compatible

Every agent stack. One data source.

Claude Desktop
MCP native
OpenAI GPT-4o
Function calling
Cursor
MCP plugin
Windsurf
MCP support
Clay
Native integration
n8n
HTTP node / MCP
Make
HTTP module
LangChain
Custom tool
CrewAI
Custom tool
AutoGen
Function tool
Custom GPTs
GPT Actions
Custom Agents
REST API
FAQ

Frequently asked questions about MCP.

Is MCP Server free?
MCP Server is completely free to install and use. You only pay credits for each successful enrichment — exactly like using the API directly. 1 profile with data = 1 credit.
Does MCP Server use separate credits or shared with API?
Shared credit pool. No separate fee for MCP. API, UI, and MCP all deduct from the same balance.
Do I need a separate API key for MCP?
No. Use the same API key from the SocialEnrich dashboard. One key for everything — API, MCP, SDK.
Does MCP support batch enrichment?
MCP Server currently supports single enrichment per tool call. For batch, use the API directly (POST /v1/enrich/batch, up to 50 records) or run an agent loop.
Is the data returned via MCP different from API?
Exactly the same. MCP Server calls the same API endpoints underneath. Response format, data depth, and coverage are all identical.
Can I use both Claude MCP and OpenAI functions at the same time?
Yes. Same API key, same credit pool. You can run Claude Desktop with MCP for daily work, and OpenAI Assistants API for automated workflows — simultaneously.
Is MCP secure? Does data go through third parties?
MCP Server runs locally on your machine and calls the SocialEnrich API directly (HTTPS, TLS 1.3). Data does not pass through any third party outside SocialEnrich infrastructure.

Don't just enrich contacts.
Start understanding people.

950M+ profiles. One API. First-party data, no middlemen.

No credit card required · 100 free enrichments · Cancel anytime