Connect
Optimize
Secure
Live 76 Actions
Postmark MCP Server
for AI Agents
Connect your AI agent to StackOne's Postmark MCP server and give it 76 MCP tools out of the box. Auth, tool execution, and security all managed.
Postmark MCP Server
Built by 
StackOne
StackOne 
Coverage
76 Agent Actions
Create, read, update, and delete across Postmark — and extend your agent's capabilities with custom actions.
Authentication
Agent Tool Authentication
Per-user OAuth in one call. Your Postmark MCP server gets session-scoped tokens with zero credentials stored on your infra.
Agent Auth →
Security
Agent Protection
Every Postmark tool response scanned for prompt injection in milliseconds — 88.7% accuracy, all running on CPU.
Prompt Injection Defense →
Performance
Max Agent Context. Min Cost.
Free up to 96% of your agent's context window to enhance reasoning and reduce cost, on every Postmark call.
Tools Discovery →What is the Postmark MCP Server?
A Postmark MCP server lets AI agents read and write Postmark data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Postmark MCP server ships with 76 pre-built actions, fully extensible via the Connector Builder — plus managed authentication, prompt injection defense, observability, and agent execution runtime. Connect it from MCP clients like Claude Desktop, Claude Code, Cursor, Goose, and VS Code, or from agent frameworks like OpenAI Agents SDK, LangChain, and Vercel AI SDK.
All Postmark MCP Tools
Every action from Postmark's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.
Emails
- Send Email
Send a single email through Postmark
- Send Batch Emails
Send a batch of up to 500 emails in a single API call
A Templates
- Create A Template
Create a new email template
- Get A Template
Retrieve a specific template by ID or alias
- Delete A Template
Delete a template by ID or alias
Bounces
- Get Bounces
Search bounces with filters
- Get Bounce
Get details for a single bounce
A Webhooks
- Create A Webhook
Create a new webhook
- Get A Webhook
Get a specific webhook configuration
- Delete A Webhook
Delete a webhook
Message Streams
- Create Message Stream
Create a new message stream
- List Message Streams
List all message streams for the server
- Get Message Stream
Get a specific message stream
A Suppressions
- Create A Suppression
Create email address suppressions
- Delete A Suppression
Delete email address suppressions
Inbound Rules
- Create Inbound Rule
Create an inbound rule to block emails matching a pattern
- List Inbound Rules
List inbound rules
- Delete Inbound Rule
Delete an inbound rule
A Servers
- Create A Server
Create a new server
- Get A Server
Get server details by server ID
- Delete A Server
Delete a server
Sender Signatures
- List Sender Signatures
List all sender signatures in the account
- Get Sender Signature
Get a sender signature’s details
A Signatures
- Create A Signature
Create a new sender signature
- Delete A Signature
Delete a sender signature
Domains
- List Domains
List all domains in the account
- Get Domain
Get domain details
A Domains
- Create A Domain
Register a new domain
- Delete A Domain
Delete a domain
Other (47)
- Send Email With Template
Send an email using a pre-defined template
- Send Batch Emails With Templates
Send a batch of template-based emails in a single API call
- List Templates
List all templates for the server
- Get Delivery Stats
Get delivery statistics overview
- Get Bounce Dump
Get the raw bounce message content
- Get Outbound Overview
Get outbound overview statistics
- Get Sent Counts
Get sent email counts by day
- Get Bounce Counts
Get bounce counts by type and day
- Get Spam Complaints
Get spam complaint counts by day
- Get Tracked Email Counts
Get tracked email counts by day
- Get Email Open Counts
Get email open counts by day
- Get Email Platform Usage
Get email platform usage
- Get Email Client Usage
Get email client usage
- Get Click Counts
Get click counts by day
- Get Browser Usage
Get browser usage
- Get Browser Platform Usage
Get browser platform usage
- Get Click Location
Get click counts by email body location
- List Webhooks
List all webhooks for the server
- Get The Server
Get the current server configuration
- List Servers
List all servers in the account
- Edit A Template
Edit an existing template
- Validate A Template
Validate template syntax and rendering
- Outbound Message Search
Search outbound messages with optional filters
- Outbound Message Details
Get full details of a sent message
- Outbound Message Dump
Get raw SMTP source content of a sent message
- Inbound Message Search
Search inbound messages with optional filters
- Inbound Message Details
Get full details of a received inbound message
- Bypass Rules For A Blocked Inbound Message
Bypass inbound rules for a blocked inbound message
- Retry A Failed Inbound Message For Processing
Retry a failed inbound message webhook delivery
- Message Opens
Search all message open events
- Opens For A Single Message
Get open events for a specific message
- Message Clicks
Search all message click events
- Clicks For A Single Message
Get click events for a specific message
- Activate Bounce
Reactivate a bounced email address
- Edit A Webhook
Edit an existing webhook
- Edit A Message Stream
Edit a message stream
- Archive A Message Stream
Archive a message stream
- Unarchive A Message Stream
Unarchive a previously archived message stream
- Suppression Dump
Suppression dump for a message stream
- Edit The Server
Edit server configuration
- Edit A Server
Edit a server's configuration by server ID
- Edit A Signature
Edit a sender signature
- Resend A Confirmation
Resend the confirmation email for a sender signature
- Edit A Domain
Edit a domain's Return-Path configuration
- Verify Domain DKIM
Verify DKIM DNS records for a domain
- Verify Domain Return-Path
Verify Return-Path DNS records for a domain
- Rotate Domain DKIM
Rotate DKIM keys for a domain
Set Up Your Postmark MCP Server in Minutes
One endpoint. Any framework. Your agent is talking to Postmark in under 10 lines of code.
Agent Frameworks
JSON{
"mcpServers": {
"stackone": {
"command": "npx",
"args": [
"-y",
"mcp-remote@latest",
"https://api.stackone.com/mcp?x-account-id=<account_id>",
"--header",
"Authorization: Basic <YOUR_BASE64_TOKEN>"
]
}
}
}Platform Resources
MCP Code Mode: Keeping Tool Responses Out of Agent Context
Anthropic's code_execution processes data already in context. Custom MCP code mode keeps raw tool responses in a sandbox. 14K tokens vs 500.
11 min
Comparing BM25, TF-IDF, and Hybrid Search for MCP Tool Discovery
Benchmarking BM25, TF-IDF, and hybrid search for MCP tool discovery across 916 tools. The 80/20 TF-IDF/BM25 hybrid hits 21% Top-1 accuracy in under 1ms.
10 min
Indirect Prompt Injection Defense for MCP Tools: A Technical Guide
MCP tools that read emails, CRM records, and tickets are indirect prompt injection vectors. Here's how we built a two-tier defense that scans tool results in ~11ms.
12 min
Postmark MCP Server FAQ
Does StackOne have a Postmark MCP server?
Yes. StackOne offers a hosted Postmark MCP server with 76 pre-built actions, and every action is tested and QA'd by StackOne. Connect it to Claude, Cursor, and any other MCP client, or to any agent framework through the AI Action SDK. It ships with managed agent authentication, prompt injection defense, and tool discovery with server-side execution that preserve your agent's context window and keep reasoning performance.
Postmark MCP server vs direct API integration — what's the difference?
A Postmark MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software — backend code calling Postmark. A Postmark MCP server is for AI agents — MCP clients like Claude and Cursor, plus framework agents built with OpenAI, LangChain, or Vercel AI — discovering and calling Postmark at runtime. StackOne provides both.
How does Postmark authentication work for AI agents?
Postmark authentication for AI agents works through a StackOne Connect Session. Create one via the dashboard or the SDK — you get an auth link and ready-to-paste config for Claude Desktop, Cursor, and other MCP clients. Your user authenticates their own Postmark account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via
origin_owner_id.Are Postmark MCP tools vulnerable to prompt injection?
Yes — Postmark MCP tools can be vulnerable to indirect prompt injection. Any tool that reads user-written content — documents, messages, tickets, records, or free-text fields — is a potential vector. StackOne Defender scans every tool response before it enters the agent's context — regex patterns in ~1ms, then a MiniLM classifier in ~4ms. 88.7% accuracy, CPU-only.
What is the context bloat of a Postmark agent and how do I avoid it?
Context bloat happens when Postmark tool schemas and API responses eat your Postmark agent's memory, preventing it from reasoning effectively. A single Postmark query can return a massive JSON response, and connecting multiple tools compounds the problem. Tools Discovery and Code Mode reduce context bloat — loading only relevant tools per query and keeping raw responses out of the agent's context.
Can I limit which actions my Postmark agent can access?
Yes — you can limit which actions your Postmark agent can access directly from the StackOne dashboard. Toggle actions on or off, or restrict them to specific accounts, with no code changes to your agent. Session tokens can be scoped to exact actions so if one leaks, exposure stays contained.
Can I create custom agent actions for my Postmark MCP server?
Yes — you can create custom agent actions for your Postmark MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research Postmark's API, generate production-ready connector YAML, test against the live API, and validate before you ship.
When should I NOT use a Postmark MCP server?
Skip a Postmark MCP server if your integration is purely software-to-software — direct Postmark API integration is simpler when no AI agent is involved. For deterministic, compliance-critical operations (financial transactions, regulatory reporting), direct API gives you predictable behavior without agent-driven decision-making. MCP shines when AI agents need to dynamically discover and call Postmark actions at runtime.
What AI frameworks and AI clients does the StackOne Postmark MCP server support?
The StackOne Postmark MCP server supports both. MCP clients (paste-and-go apps): Claude Desktop, Claude Code, Cursor, VS Code, Goose. Agent frameworks (code SDKs you build with): OpenAI Agents SDK, Anthropic, Vercel AI, Google ADK, CrewAI, Pydantic AI, LangChain, LangGraph, Azure AI Foundry.
Put your AI agents to work
All the tools you need to build and scale AI agent integrations, with best-in-class connectivity, execution, and security.