Skip to main content

Getting Started with Enginy MCP

Problem it solves

Sales reps who already use Claude or another AI tool daily have to constantly switch between their AI workspace and Enginy to run outbound. Every time they research a prospect in Claude, they have to open Enginy separately to build the list, set up the sequence, or check what's running. MCP removes that friction — Enginy works from inside the AI tool they're already in, so the full outbound motion (finding prospects, enriching, sequencing, tracking) happens without leaving the conversation. For teams building AI workflows, MCP makes Enginy a programmable part of their stack — callable from any MCP-compatible client alongside their other tools.

Use cases supported

  1. Build and enrich a prospect list from a plain-language brief. "Find 50 Sales Executives at Barcelona-based SaaS companies with 50-500 employees" → Enginy returns them enriched, ready to drop into a sequence.

  2. Run multi-step outbound plays in one workflow. Enrich, score, build campaign, write personalised messages, review before send — all from one prompt.

  3. Pull campaign performance and identify what's working. "Pull performance across all active campaigns and tell me what's driving replies" → the agent surfaces patterns across sequences, openers, segments, and send times.

  4. Triage the inbox and draft the next move. "Look at today's replies, classify each (interested / objection / out-of-office), and draft responses for my review."

  5. Chain Enginy with other tools in a single conversation. Because MCP clients can hold several connectors at once, Enginy becomes one node in a wider toolchain — e.g. pull a prospect from a meeting notes tool, enrich them in Enginy, add to a campaign, all in one conversation.

How it works

What MCP is (one paragraph — functional, not marketing)

MCP (Model Context Protocol) is an open standard that lets AI tools like Claude communicate with external platforms in real time during a conversation. When Enginy is connected via MCP, the AI tool can call Enginy directly — finding prospects, enriching contacts, building campaigns, reading the inbox — without the user leaving the AI interface.

Supported AI tools

Claude, Codex (OpenAI's developer environment), Gemini, Cursor, and other clients that support remote MCP.

⚠️ The ChatGPT consumer app does NOT support custom MCP connections. Never list it. The OpenAI path is Codex only.

Setup — step by step

  1. Pick your AI tool: Claude, Codex, Gemini, Cursor, and other clients that support remote MCP.

  2. Go to that tool's connector settings

    Claude:

    1. Settings > Connectors (or go directly to claude.ai/settings/connectors)

    2. From there, click the "+" button next to Connectors and select "Add custom connector."

    3. Paste the url: https://openapi.enginy.ai/mcp
      ​

    Codex:

    1. Open a terminal and run this command:

    codex mcp add enginy --url <https://openapi.enginy.ai/mcp>

    1. Run this command to start the authorization flow

    codex mcp login enginy

    Cursor:

    1. Go to Settings → Tools & MCPs and click "New MCP server" to open your mcp.json
      file

    2. Paste this into mcp.json

    { "mcpServers": { "Enginy": { "type": "http", "url": "<https://openapi.enginy.ai/mcp>", "headers": {} } } }

    Other tools:

    1. Open MCP settings

    2. Add the server URL: https://openapi.enginy.ai/mcp

  3. Sign in with your Enginy credentials

  4. Done — the connection is live

Authentication is OAuth 2.0. No API keys required. Setup takes approximately 2 minutes.

What you can do

~150 operations across the full platform: contacts, companies, lists, campaigns, AI Research / AI Message / AI Snippets, AI Finder, inbox, tasks, and analytics.

Known limitations

  • Each user connects individually — there is no admin-level team deployment. Everyone authenticates under their own Enginy permissions.

  • MCP is not available in the ChatGPT consumer app. If you use OpenAI tools, the path is Codex.

  • Some actions still require the Enginy UI: setting team roles and permissions, connecting Identities, and sender warmup.

  • Complex multi-step workflows may require multiple prompts. Specific, detailed prompts return better results than vague ones.

  • Operations triggered via MCP consume the same credits as in the Enginy UI. There is no separate MCP charge.

  • Tool calls are logged with user attribution and timestamps. All paid operations appear in the Activity tab.

Security & permissions

On first connection, you'll be asked to approve the scopes MCP is allowed to perform. After that, MCP is scoped to your own Enginy permissions — if you can't see something in the Enginy UI, the agent can't access it via MCP either.

Tool results are returned to the AI tool you've connected. This means your data passes through your AI provider (Claude, Codex, Gemini, etc.) in the same way it would if you were chatting with them directly. Data retention on the AI provider side is governed by your own agreement with that provider.

To revoke access at any time: go to Enginy Integrations → MCP and disable the connection, or remove Enginy from your AI tool's connector settings. Tokens are invalidated immediately.

Troubleshooting

My AI tool keeps asking me to reconnect, or says a permission is missing.

This usually means the client is re-running the OAuth flow instead of reusing its existing token — it's not a real permission problem. Reconnect once and confirm your session is active. See docs.enginy.ai/mcp/security-troubleshooting.

The agent used the wrong tool, or couldn't find a tool.

Be specific in your prompt. The MCP tool surface is broad and auto-generated, so vague requests can route incorrectly. Describing the action clearly (e.g. "find contacts in Enginy" rather than "find contacts") helps the agent pick the right tool.

Did this answer your question?