Skip to main content
Glama
markswendsen-code

@striderlabs/mcp-gmail

by markswendsen-code
OverviewSchemaRelated ServersScoreDiscussions
JavaScript
Remote

@striderlabs/mcp-gmail

MCP server that gives AI agents the ability to send, read, and search email via Gmail.

For Agents

Agents use this connector to handle email autonomously on behalf of their human — reading important messages, searching for information, composing thoughtful replies, and sending communications.

Example agent workflows:

  1. Triage emails: Agent reads new messages, summarizes important ones, and flags urgent items for user attention

  2. Answer routine questions: Agent searches email history to find information, composes replies with context from past conversations

  3. Send on behalf: Agent drafts and sends professional emails based on user intent ("Let the team know I'll be late"), then logs a copy to the conversation

Usage example:

User: "Has anyone replied to my email about the Q2 budget proposal?"

Agent:

  1. gmail_search → "to:me subject:budget"

  2. gmail_read → Read each message

  3. Return summary: "Sarah replied yes on Monday. Mark asked for revisions. No word from Finance yet."

Then agent might automatically draft a follow-up to Finance and ask for approval before sending.

Related MCP server: mcp-gmail

Installation

npx @striderlabs/mcp-gmail

Configuration

Add to your MCP client configuration (e.g., Claude Desktop):

{
  "mcpServers": {
    "strider-gmail": {
      "command": "npx",
      "args": ["-y", "@striderlabs/mcp-gmail"],
      "env": {
        "GOOGLE_CLIENT_ID": "your-client-id",
        "GOOGLE_CLIENT_SECRET": "your-client-secret",
        "GOOGLE_REFRESH_TOKEN": "your-refresh-token"
      }
    }
  }
}

Available Tools

gmail_send

Send an email from the user's Gmail account.

Parameters:

  • to (required): Recipient email address

  • subject (required): Email subject line

  • body (required): Email body content

  • cc (optional): CC recipients

  • bcc (optional): BCC recipients

gmail_search

Search emails using Gmail search syntax.

Parameters:

  • query (required): Gmail search query (e.g., "from:example@gmail.com")

  • maxResults (optional): Maximum results (default: 10)

gmail_read

Read the full content of a specific email.

Parameters:

  • messageId (required): The Gmail message ID

gmail_list

List recent emails from the inbox.

Parameters:

  • maxResults (optional): Maximum emails to list (default: 10)

  • label (optional): Filter by label (e.g., "INBOX", "UNREAD")

Getting Google OAuth Credentials

  1. Go to Google Cloud Console

  2. Create a new project or select existing

  3. Enable the Gmail API

  4. Create OAuth 2.0 credentials

  5. Use the OAuth playground or your app to get a refresh token

Response Format

All tools return structured JSON:

{
  "success": true,
  "messageId": "...",
  "message": "Email sent successfully"
}

Part of Strider Labs

Strider Labs builds action execution infrastructure for AI agents.

License

MIT

Available Tools

4 tools
gmail_listB

List recent emails from the inbox. Use this to see what emails the user has received.

ParametersJSON Schema
NameRequiredDescriptionDefault
labelNoFilter by label (e.g., "INBOX", "UNREAD", "STARRED")
maxResultsNoMaximum number of emails to list (default: 10)

TDQS

B3.1/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, and the description lacks behavioral context such as pagination, rate limits, or authentication. It does not explain what 'recent' means or the default limit beyond what the schema states.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences, concise and front-loaded. The only minor issue is the slight inaccuracy about 'from the inbox' that could be clarified.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema and the description does not explain what is returned (e.g., fields of each email). Lacks completeness for a list tool despite having 100% schema coverage for parameters.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so parameters are documented. The description adds no extra meaning beyond the schema, so baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it lists recent emails from the inbox, with a verb and resource. However, it implies only inbox, while the label parameter allows filtering beyond inbox, causing slight ambiguity.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It suggests using the tool to see received emails but does not differentiate from sibling tools like gmail_search or gmail_read. No explicit when-not-to-use or alternatives mentioned.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

gmail_readB

Read the full content of a specific email by its message ID.

ParametersJSON Schema
NameRequiredDescriptionDefault
messageIdYesThe Gmail message ID to read

TDQS

B3.4/5.0
Behavior2/5

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 of disclosing behavioral traits. It only says 'read', implying a non-destructive operation, but it does not confirm whether it modifies anything, what permissions are needed, or any rate limits. This is insufficient.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence of 10 words, directly stating the essential information. No wasted words, and the key action and resource are front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema and no annotations, the description should at least hint at the format of the returned content (e.g., includes body, attachments) or mention error conditions. It fails to provide sufficient context for a complete understanding of the tool's behavior.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% for the single parameter; the description adds no additional semantic value beyond stating 'by its message ID', which is already clear from the schema's parameter description. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action (Read), resource (full content of a specific email), and the identifier (message ID). It distinguishes itself from siblings like gmail_list, gmail_send, and gmail_search by focusing on reading a single email.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies that the user needs a message ID to read, which likely comes from gmail_list or gmail_search, but it does not explicitly state when to use this tool or mention any alternatives or prerequisites. Some guidance is missed.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

gmail_sendA

Send an email from the user's Gmail account. Use this when the user wants to send an email to someone.

ParametersJSON Schema
NameRequiredDescriptionDefault
ccNoCC recipients (comma-separated, optional)
toYesRecipient email address
bccNoBCC recipients (comma-separated, optional)
bodyYesEmail body content (plain text)
subjectYesEmail subject line

TDQS

A3.8/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, so description carries full burden. Only states basic action, no disclosure of mutation, authentication needs, success/error behavior, or rate limits.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with purpose, zero wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Adequate for a simple send tool with well-documented parameters. No output schema needed. Could mention sending as authenticated user.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with clear descriptions. Description adds no extra meaning beyond schema. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states verb 'send' and resource 'email from user's Gmail account'. Distinguishes from read-only siblings (gmail_list, gmail_search, gmail_read).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly says when to use: 'when the user wants to send an email'. Implicitly excludes reading/searching tools. No explicit when-not-to or alternatives, but context makes it clear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. 4 tool updatesv0.1.0
    • First observedgmail_list
    • First observedgmail_read
    • First observedgmail_search
    • First observedgmail_send
Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A3.7/5.0
Disambiguation5/5

Each tool has a unique and clearly defined purpose: listing inbox, sending, searching, and reading specific emails. There is no overlap in functionality.

Naming Consistency5/5

All tool names follow a consistent 'gmail_<verb>' pattern (list, send, search, read), making them predictable and easy to distinguish.

Tool Count5/5

With 4 tools, the server is well-scoped for basic Gmail operations. It covers the most common actions without being overly minimal or bloated.

Completeness4/5

The set covers core email workflows (read, send, list, search) but lacks update/delete or draft management, which are common in email systems. Minor gap.

Maintenance

ActivityInactive
ResponsivenessSyncing

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

  • sudo-mcp-gmail

    sahilyadav902
    A
    license
    Not graded
    quality
    D
    maintenance
    An MCP server for Gmail that allows AI assistants to read, search, compose drafts, send emails, and manage labels with attachment support.
    MIT

  • mcp-gmail

    Nandani-Rejoice
    A
    license
    Not graded
    quality
    D
    maintenance
    An MCP server that provides Gmail access for LLMs, enabling email composition, sending, searching, and label management via the Gmail API.
    MIT

  • Gmail MCP Server

    varun00391
    F
    license
    Not graded
    quality
    C
    maintenance
    Production-ready MCP server for Gmail, enabling AI agents to search, read, send, draft, and manage emails, labels, and attachments via the Google Gmail API.
    -

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/markswendsen-code/mcp-gmail'

If you have feedback or need assistance with the MCP directory API, please join our Discord server