Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Tratto MCP Server send a welcome email to newuser@test.com"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Model Context Protocol server for Tratto. Lets AI tools send emails, check status, and manage contacts directly.
Tool | Description |
| Send a transactional email |
| List sent emails with optional status filter |
Related MCP server: Gmail MCP
Add to claude_desktop_config.json:
{
"mcpServers": {
"tratto": {
"command": "npx",
"args": ["-y", "@tratto/mcp"],
"env": {
"TRATTO_API_KEY": "tratto_live_..."
}
}
}
}{
"mcp": {
"servers": {
"tratto": {
"command": "npx",
"args": ["-y", "@tratto/mcp"],
"env": { "TRATTO_API_KEY": "tratto_live_..." }
}
}
}
}Variable | Required | Description |
| ✅ | API key from app.tratto.email/settings/api-keys |
Issues and PRs welcome. See CONTRIBUTING.md.
MIT
List sent emails from Tratto with optional status filter
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Max results (default 20, max 100) | |
| status | No | Filter by delivery status |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry the full burden. It only states the core function and the optional filter, but does not disclose that this is a read-only operation, how results are ordered, what response format to expect, or whether 'sent' includes bounced/failed emails. The term 'sent' is ambiguous in scope.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, front-loaded sentence that directly states the purpose and filter option. Every word earns its place, with no redundancy or irrelevant information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple listing tool with no annotations and no output schema, the description is minimally sufficient. It covers the essential purpose and an optional parameter, but lacks details about return value structure, ordering, pagination, or any side effects, which could be important for an agent to fully understand the tool's behavior.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema already describes both parameters with clear definitions (limit default/max, status enum values). The description adds nothing beyond the schema—it only mentions the status filter without elaborating on its syntax or meaning, and does not reference the limit parameter. Baseline 3 applies due to high schema coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action (list), the resource (sent emails), and the domain (from Tratto), with an optional status filter. This distinguishes it from the sibling tool 'send_email', which performs a write operation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies that this tool is for listing sent emails, and the contrast with 'send_email' is evident through the verbs 'list' vs. 'send'. However, it does not explicitly state when to use this tool over the alternative, nor does it mention any exclusions or prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Send a transactional email via Tratto
| Name | Required | Description | Default |
|---|---|---|---|
| to | Yes | Recipient address or array of addresses | |
| from | Yes | Sender address (must be verified domain) | |
| html | No | HTML body | |
| text | No | Plain text body (fallback) | |
| subject | Yes | Email subject |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It only states the action ('Send') without mentioning side effects, deliverability, idempotency, or any post-send behavior. The description adds no behavioral context beyond what the tool's name already implies.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence that is front-loaded with the core action. Every word contributes to purpose clarity, with no filler or redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool is a mutation with no annotations and no output schema, yet the description offers only a bare statement. Key contextual details such as the relationship between html and text, domain verification requirements, and any return value are left entirely to the schema. The description is inadequate for a tool with 5 parameters and side effects.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already documents all parameters. The description adds no parameter-level meaning, but the baseline of 3 applies because the schema does the heavy lifting. No ambiguity exists about parameter formats or purposes.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Send a transactional email via Tratto' uses a specific verb (send) and resource (transactional email), clearly distinguishing it from the sibling list_emails. It also identifies the service (Tratto), making the tool's function unambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives, nor does it mention any prerequisites or exclusions. The distinction from list_emails is implied by the verbs, but no explicit usage context or alternative references are given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v0.1.0list_emailssend_emailsend_email and list_emails have completely distinct purposes: one initiates an outgoing email, the other retrieves a list of previously sent emails. There is no overlap or ambiguity between the two.
Both tool names follow the consistent verb_noun pattern using snake_case: send_email and list_emails. The naming is predictable and uniform.
With only 2 tools, the server feels thin for an email-related service. While the core actions of sending and listing are covered, the small number of tools is borderline and may leave users wanting more functionality.
The server provides the fundamental lifecycle of sending and listing emails, but lacks a dedicated get_email or delete_email operation. This minor gap could be worked around if list_emails returns full details, but a single-email lookup is a common need.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Email infrastructure for AI agents — send, receive, search, and reply to email over MCP.
Transactional email for AI agents: templates, domain verify, and sends.
Send transactional emails for AI agents via SMTP. Templates included.
Email for AI agents: send mail, manage contacts, automations & webhooks. Zero-DNS first send.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/tratto-email/tratto-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
