email-on-acid-mcp

email-on-acid-mcp

An MCP server exposing every documented Email on Acid API v5 request as a tool — 24 tools across authentication, email client lists, email rendering testing, and spam testing.

Category
Visit Server

README

Email on Acid MCP Server

An MCP server exposing every documented Email on Acid API v5 request as a tool — 24 tools across authentication, email client lists, email (rendering) testing, and spam testing.

Setup

Create a virtual environment and install dependencies (Python 3.12):

python3.12 -m venv .venv
.venv/bin/pip install -r requirements.txt

Credentials

The server authenticates with HTTP Basic auth (API key as username, account password as password) and resolves credentials from EOA_API_KEY / EOA_ACCOUNT_PASSWORD environment variables — including values from a .env file in this directory, which is loaded automatically at startup. Copy .env.example to .env and fill in your key:

cp .env.example .env
# then edit .env:
# EOA_API_KEY=your_api_key
# EOA_ACCOUNT_PASSWORD=your_account_password   (omit if your account has none)

Register with Claude Code

claude mcp add email-on-acid \
  -- /absolute/path/to/email-on-acid-mcp/.venv/bin/python \
     /absolute/path/to/email-on-acid-mcp/server.py

Register with Claude Desktop

Add to ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "email-on-acid": {
      "command": "/absolute/path/to/email-on-acid-mcp/.venv/bin/python",
      "args": ["/absolute/path/to/email-on-acid-mcp/server.py"]
    }
  }
}

Tools

Authentication

Tool API request
verify_auth GET /auth

Email client lists

Tool API request
get_available_email_clients GET /email/clients
get_default_email_clients GET /email/clients/default
set_default_email_clients PUT /email/clients/default

Email testing

Tool API request
create_email_test POST /email/tests
get_email_tests GET /email/tests
search_email_tests GET /email/tests?<query>
get_email_test_info GET /email/tests/{test_id}
delete_email_test DELETE /email/tests/{test_id}
get_email_test_results GET /email/tests/{test_id}/results[/{client_id}]
reprocess_email_test_screenshots PUT /email/tests/{test_id}/results/reprocess
get_email_test_content GET /email/tests/{test_id}/content
get_email_test_content_inline_css GET /email/tests/{test_id}/content/inlinecss
get_email_test_content_text_only GET /email/tests/{test_id}/content/textonly
get_email_test_spam_results GET /email/tests/{test_id}/spam/results
get_email_test_spam_seedlist GET /email/tests/{test_id}/spam/seedlist

Spam testing

Tool API request
get_spam_clients GET /spam/clients
create_spam_test POST /spam/tests
get_spam_tests GET /spam/tests
search_spam_tests GET /spam/tests?<query>
get_spam_test_results GET /spam/tests/{test_id}
delete_spam_test DELETE /spam/tests/{test_id}
get_spam_test_seedlist GET /spam/tests/{test_id}/seedlist
reserve_spam_seedlist GET /spam/seedlist

Testing

.venv/bin/python test_mcp_server.py

The test suite spawns the server over stdio (no separate server start needed) and offers three modes: read-only, write-only, or full. Test IDs are auto-discovered from the account or created during the run — no saved configuration is needed. Write tests default to sandbox mode (no test credits consumed) and prefix subjects with MCPTEST_; anything that costs a credit or quota (real email test with spam component, real spam test, screenshot reprocessing) asks for confirmation first, and created tests are deleted in a confirmed cleanup step at the end. Answering yes to all prompts in full mode exercises all 24 tools.

Notes

  • API errors are returned as {"http_status": ..., "error": {...}} rather than raised, so the calling agent can see the failure details.
  • Test results are retained by Email on Acid for 90 days.
  • search_email_tests / search_spam_tests use from_date / to_date parameter names (mapped to the API's from / to) because from is reserved in Python.
  • Enterprise-only parameters (reference_id, customer_id, headers x-headers) are included but will be ignored or rejected on non-enterprise plans.

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured