Unspam MCP

Unspam MCP Server.

Give your AI assistant secure, plain-language access to Unspam: spam checks, inbox placement, client previews across 50+ real email clients, heatmaps, DMARC reports and recurring autopilot tests. Connected over OAuth, with no API keys to copy.

One server. Every Unspam tool.

Your assistant gets the whole Unspam workflow as callable tools, grouped into five areas. Ask in plain language and it chains the right calls for you.

Account status

Read the subscription and remaining monthly limits before kicking off a run.

• get_account_status

Spam checks

Start a check, list past checks, and pull the score, screenshots, client previews in 50+ real clients, and heatmap.

• start_spam_check
• get_spam_check_result
• get_spam_check_screenshots
• get_spam_check_client_previews
• list_client_preview_devices
• get_spam_check_heatmap

Inbox placement

Run seed-list placement tests across mailboxes and read per-folder results.

• list_mailboxes
• start_inbox_placement_test
• get_inbox_placement_result

Autopilot

Schedule recurring tests, manage as many SMTP senders as you send from, and review every run.

• create_scheduled_test
• set_scheduled_test_status
• list_scheduled_test_runs

DMARC reports

Register a domain, publish the TXT record, then read the aggregate reports and the per-source rows behind them.

• create_dmarc_domain
• get_dmarc_dns_instructions
• verify_dmarc_domain
• list_dmarc_domains
• get_dmarc_domain
• list_dmarc_reports
• get_dmarc_report
• get_dmarc_report_records

Why teams connect Unspam over MCP.

Remote MCP over OAuth, no keys to manage.

The server speaks JSON-RPC 2.0 over HTTP and authenticates with OAuth 2.1 + PKCE. Your assistant opens a browser, you sign in once, and the client caches the token. Nothing to paste, nothing to rotate by hand.

The whole Unspam workflow as tools.

The tool set covers spam checks, inbox placement, autopilot (scheduled tests), screenshots, heatmaps, client previews of your email in 50+ real clients and devices, DMARC report collection, and account status. Your assistant reads the catalog and picks the right call for each request.

Works with the clients teams already use.

Claude Desktop (custom connector or the mcp-remote bridge), Claude Code, Cursor, ChatGPT Developer Mode (Plus, Pro, Business), Windsurf, and any MCP client that supports remote streamable-HTTP servers.

One connection, revoke anytime.

The link shows up under Connected apps in your Unspam account, so you can revoke it whenever you want. MCP access is available on paid plans only, gated to your subscription quota.

What the connection looks like end to end.

Approve one OAuth screen, hand your assistant the full Unspam tool set, then ask for tests in plain language.

Approve one OAuth screen, no keys to copy.

Your client registers itself with Dynamic Client Registration, then runs the Authorization Code grant with PKCE (S256). You sign in through the browser and approve a single consent screen scoped to mcp.

After that, the client caches the token and renews it for you. A missing or invalid token returns 401, the wrong scope returns 403, so the failure modes are explicit.

The full tool catalog, ready for the assistant.

Once connected, your assistant sees every Unspam tool: start_spam_check, get_spam_check_result, get_spam_check_screenshots, get_spam_check_client_previews, get_spam_check_heatmap, the inbox-placement set, the scheduled-test (autopilot) set, the DMARC set from create_dmarc_domain through get_dmarc_report_records, and get_account_status for limits.

No separate SDK to wire up. The client reads the catalog over MCP and exposes each tool to the model directly.

Ask in plain language, the assistant chains the calls.

Say "Run a spam check and tell me when it is done" or "Start an inbox placement test across all mailboxes" and the assistant sequences the tool calls, polls for the result, and reports back.

Set up recurring coverage the same way: "Schedule a weekly automatic test and email me if anything hits spam." The autopilot tools create the sender, the schedule, and the notification for you.

How to connect in four steps.

MCP needs a paid plan with API access. Add the server URL to your client, approve the OAuth screen, then talk to your assistant in plain language.

1. 01

   Pick a paid plan

   MCP needs API access, which is included on all paid plans. Free accounts cannot connect. Check your subscription and monthly limits anytime with get_account_status.

2. 02

   Add the server URL in your client

   Claude Code: claude mcp add --transport http unspam https://api.unspam.email/mcp. Cursor: add {"url":"https://api.unspam.email/mcp"} to ~/.cursor/mcp.json. Claude Desktop and ChatGPT: paste the same URL as a custom connector.

3. 03

   Approve the OAuth consent screen

   Your client opens a browser, you sign in to Unspam, and you approve access scoped to mcp. The token is cached, so you only do this once per client.

4. 04

   Ask your assistant to run a test

   Try "Run a spam check and tell me when it is done." The assistant calls start_spam_check, polls get_spam_check_result, and reports the score back in the chat.

Frequently asked questions about the MCP server.

Supported clients, pricing, authentication, rate limits, and how to revoke access.

Which clients are supported?

Any MCP client that supports remote streamable-HTTP servers. That includes Claude Desktop (custom connector or the mcp-remote bridge), Claude Code, Cursor, ChatGPT in Developer Mode (Plus, Pro, Business), and Windsurf. The setup is always the same server URL: https://api.unspam.email/mcp.

Is it free?

No. MCP access is available on paid plans only and is included with API usage. Free accounts cannot connect. Run get_account_status from your assistant to see your subscription and remaining monthly limits.

How does authentication work?

OAuth 2.1 with Dynamic Client Registration and the Authorization Code grant with PKCE (S256), scoped to mcp. You sign in through a browser once and the client caches the token. There are no API keys to copy or rotate by hand, and you can revoke the connection anytime.

What can the assistant actually do?

Five areas: account status, spam checks (start, list, results, screenshots, client previews across 50+ real clients, heatmaps), inbox placement (mailboxes, tests, results), autopilot (scheduled tests, SMTP senders, and run history), and DMARC reports (register a domain, verify the record, then read aggregate reports and their per-source rows). Ask in plain language, for example "Render this campaign and flag anything broken in Outlook dark mode," and the assistant chains the right calls.

What are the rate limits?

Usage is gated per account by your subscription quota. Check it anytime with get_account_status. If you exceed your limit, the server returns 429. A missing or invalid token returns 401 and the wrong scope returns 403.

How do I revoke access?

The connection appears under Connected apps in your Unspam account, where you can revoke it at any time. Full setup details for each client are in the MCP server documentation.

Connect your AI assistant to Unspam.

MCP access is included on all paid plans.

See pricing