Argorant – 614M+ verified B2B contacts
About
Search, count, preview, reveal, export & build saved lists across 614M+ verified B2B contacts — from Claude, ChatGPT, Cursor & any MCP client. Hosted, OAuth, account-scoped.
Details
- Author
- argorant
- Downloads
- 290
- Categories
- Database, Other, AI, Developer Tools
Jump to
- 614M+ verified B2B contact records.
- Emails verified live at reveal/export time.
- Billed only for deliverable contacts.
- Free tools provide masked previews and counts.
- Credit tools reveal raw contact details and exports.
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
Argorant – 614M+ verified B2B contactsCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Connect by adding the remote server URL https://mcp.argorant.com/mcp and authenticating with OAuth. Free tools (search, fetch, argorant_account, argorant_count_people, argorant_preview_people) return aggregate counts and masked previews. Credit-based tools (argorant_reveal_people, argorant_create_export, argorant_export_list, argorant_create_list, argorant_list_status) unlock full contact details and exports.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"argorant \u2013 614m+ verified b2b contacts": {
"argorant": {
"url": "https://mcp.argorant.com/mcp"
}
}
}
}McpServers
{
"argorant": {
"url": "https://mcp.argorant.com/mcp"
}
}Verified B2B contact data for AI agents.Search, count, preview, reveal, export, and build saved lists across600M+ business contacts— directly from Claude, ChatGPT, Cursor, and any MCP client.
- MCP endpoint:https://mcp.argorant.com/mcp
- Transport:Streamable HTTP ·Auth:OAuth 2.1 (Dynamic Client Registration, account-scoped)
- Website:https://argorant.com·Privacy:https://argorant.com/privacy·Terms:https://argorant.com/terms
This is ahosted remote connector— no install, no API key paste. Clients connect to the endpoint and authenticate via OAuth. A standalone CLI also exists (npx argorant) for terminal/script use.
Claude(claude.ai / Desktop): Settings → Connectors →Add custom connector→ URLhttps://mcp.argorant.com/mcp→ complete the OAuth login.
ChatGPT(Developer Mode): Settings → Apps & Connectors → Advanced → enable Developer Mode → Connectors →Create→ URLhttps://mcp.argorant.com/mcp. Thesearch+fetchtools make it usable as a Deep Research connector.
Cursor / other MCP clients:add the remote server frommcp.json:
{ "mcpServers": { "argorant": { "url": "https://mcp.argorant.com/mcp" } } }
Free (no credits, masked/aggregate only):
Consume credits (require OAuth scope + permission; verification is live at this step andonly valid/deliverable contacts are billed):
Tools are annotated with read-only vs. action hints. Reveal/export/list actions only run after OAuth, scope, permission, quota, and plan checks; without credits they are blocked by design.
- OAuth + account-scoped.Unauthenticated requests to/mcpreturn401withWWW-Authenticatepointing at protected-resource metadata.
- Masked by default.search/fetch/previewnever return raw emails, phones, or profile URLs — only aggregate coverage and masked rows. Raw contact details require the scoped reveal/export tools and consume credits.
- Verification is live.Emails are verified at reveal/export time; you are billed only for deliverable contacts. Raw verification status is never exposed as a queryable field.
- Hosts are separated:argorant.com(marketing/docs),app.argorant.com(signed-in app),mcp.argorant.com(remote MCP + OAuth).
https://mcp.argorant.com/.well-known/oauth-protected-resource https://mcp.argorant.com/.well-known/oauth-authorization-server
Dynamic Client Registration is supported at/register(grant types:authorization_code,refresh_token).
- Overview:https://argorant.com/docs/mcp/overview
- Connect guide:https://argorant.com/docs/mcp/connect
- Tool reference:https://argorant.com/docs/mcp/tools
- Claude setup:https://argorant.com/docs/mcp/claude· ChatGPT setup:https://argorant.com/docs/mcp/openai
- Security:https://argorant.com/docs/mcp/security
- CLI:https://argorant.com/docs/cli
- mcp.json— Open Plugins / Cursor remote-server declaration.
- server.json— officialMCP Registryentry (io.github.argorant/argorant-mcp, remote streamable-http).
Chinese writing toolbox for Claude Code: text analysis, outline generation, GB/T 7714 references,character frequency
Biologically-inspired memory for Claude. Hebbian plasticity, dream cycles, and temporal decay for persistent knowledge synthesis.
Access GPT-5, Claude, Gemini and other models through a single MCP connection. Save development time and money on subscriptions.
Universal tool adapter — @tool decorator exports Python functions to OpenAI, Claude, Gemini, MCP, JSON Schema. Audit token costs.
Standing review layer for coding agents: Claude, GPT and Gemini debate each answer and return one recommendation plus the strongest dissent.
Deepseek Thinking & Claude 3.5 Sonnet
Combines DeepSeek's reasoning capabilities with Claude 3.5 Sonnet's response generation through OpenRouter.
The production framework for Predictive and Generative AI. Serve any model as an API in one line, with OpenAI/Anthropic/Ollama-compatible endpoints, a built-in chat UI, and native MCP.
An MCP server that orchestrates Google Gemini and Claude Code models via the OpenRouter API.
Delegate bounded work from Claude to any OpenAI-compatible LLM endpoint (LM Studio, Ollama, OpenRouter), preserving your Claude context and quota.
Stop AI Hallucinations Before They Start Run models from OpenAI, Google, Anthropic, xAI, Perplexity, and OpenRouter in parallel. They check each other's work, debate solutions, and catch errors before you see them.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
