Allows sending email notifications via Gmail SMTP, supporting customizable recipients, subjects, and body content.
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., "@CV Email MCP Server Send an email to hiring@company.com with my CV summary"
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.
A Model Context Protocol (MCP) server that provides CV parsing and email notification capabilities.
CV Parsing: Parse PDF resumes and answer questions about your career history
Email Notifications: Send emails with customizable recipients, subjects, and body content
Related MCP server: MCP Resume & Email Assistant
Install dependencies:
npm installBuild the project:
npm run buildSet up environment variables:
cp .env.example .env
# Edit .env with your configurationCreate a .env file with the following variables:
CV_PDF_PATH: Path to your resume PDF file (default: resume.pdf)
SMTP_HOST: SMTP server hostname (default: smtp.gmail.com)
SMTP_PORT: SMTP server port (default: 587)
EMAIL_USER: Your email address
EMAIL_PASSWORD: Your email password or app-specific password
npm startparse_cv: Parse your resume PDF
Optional parameter: pdf_path (uses default if not provided)
ask_cv: Ask intelligent questions about your CV
Required parameter: question
Basic Info: "What is my name?", "What's my contact information?"
Experience: "What role did I have at my last position?", "How many years of experience do I have?"
Technical Skills: "What programming languages do I know?", "What frameworks do I work with?"
Education: "Where did I study?", "What's my degree?", "What's my GPA?"
Projects: "What projects have I worked on?", "What are my achievements?"
Advanced: "What are my strengths?", "What industry do I work in?"
send_email: Send email notifications
Required parameters: recipient, subject, body
Add this server to your MCP configuration:
{
"mcpServers": {
"cv-email": {
"command": "node",
"args": ["path/to/cv-email-mcp-server/dist/index.js"],
"env": {
"CV_PDF_PATH": "path/to/your/resume.pdf",
"EMAIL_USER": "your-email@gmail.com",
"EMAIL_PASSWORD": "your-app-password"
}
}
}
}npm run build
node demo.js./start-full-demo.shThen open http://localhost:3000
For Gmail: Enable 2FA and generate an app-specific password for EMAIL_PASSWORD.
Ask questions about your CV content
| Name | Required | Description | Default |
|---|---|---|---|
| question | Yes | Question about your CV/resume |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full behavioral disclosure burden, but it only states 'Ask questions about your CV content.' It does not disclose what happens under the hood (e.g., whether it references a previously parsed CV, whether it has side effects, or what the response format is). This is minimal and leaves key behavior unspecified.
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 concise sentence, front-loaded with the core purpose. It has no redundancy or wasted words, but it is so brief that it misses essential context, slightly reducing the conciseness score.
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 tool with siblings and no annotations or output schema, the description is too incomplete. It does not explain how to use it in conjunction with parse_cv, what kind of answers it returns, or any prerequisites. The provided context signals (1 param, no output schema) indicate a simple tool, but the description still lacks necessary operational details.
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 schema covers 100% of the parameter descriptions (the 'question' param is described). The description adds little beyond the schema, so the baseline of 3 applies for 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 tool's function: 'Ask questions about your CV content' with a specific verb ('ask') and resource ('CV content'). It distinguishes itself from siblings parse_cv (parsing) and send_email (sending) by focusing on interactive Q&A.
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?
No guidance is provided on when to use this tool vs alternatives. It does not mention whether a CV must be parsed first, what types of questions are appropriate, or how it relates to parse_cv and send_email. The usage context is entirely implied.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Parse and load CV content from PDF file
| Name | Required | Description | Default |
|---|---|---|---|
| pdf_path | No | Path to the PDF file (optional, uses default if not provided) |
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, but it only offers a high-level action. It does not explain what 'load' means in practice, whether any state changes occur, error handling, supported PDF formats, or the return behavior. This is a significant gap for a tool that likely has side effects.
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 concise sentence, front-loaded with the verb and resource. There is no redundant information or fluff, making it efficiently structured for a tool description.
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?
Given that there is no output schema and no annotations, the description should clarify what the tool returns or accomplishes. It only says 'Parse and load CV content' without explaining the outcome, the relationship to sibling tools, or any caveats. This leaves the agent under-informed about the tool's behavior and integration context.
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 schema already provides a complete description for the sole parameter (pdf_path: 'Path to the PDF file (optional, uses default if not provided)'), so the schema coverage is 100%. The tool description adds no extra semantic detail about the parameter beyond what the schema has, so a baseline score of 3 is appropriate.
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 ('Parse and load') and the resource ('CV content from PDF file'), which distinguishes it from the sibling ask_cv tool. However, 'load' is somewhat vague—it does not specify whether the content is stored, returned, or made available for subsequent queries.
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?
No explicit usage guidance or alternatives are mentioned. The intended use is implied by the name 'parse_cv' (ingestion) versus sibling 'ask_cv' (querying), but the description does not state when to use this tool instead of the siblings or any prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Send an email notification
| Name | Required | Description | Default |
|---|---|---|---|
| body | Yes | Email body content | |
| subject | Yes | Email subject line | |
| recipient | Yes | Email address of the recipient |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must carry full behavioral disclosure. It states the primary action (send email) but does not disclose whether it actually sends or simulates, authentication requirements, rate limits, or any side effects.
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 short sentence, which is concise, but it is also sparse and close to a tautology of the tool name. It doesn't add enough value to be considered well-structured, though it is not verbose.
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 side-effectful tool like sending email, the description is incomplete. It lacks any behavioral context, output expectations, or error handling information. The schema covers parameters but not usage context, and there is no output schema.
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%, with each parameter having a clear description. The tool description adds no extra meaning beyond the schema, so the baseline of 3 applies.
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 an email notification' clearly states the action (send) and the resource (email). It is unambiguous and implicitly distinguishes from sibling tools (parse_cv, ask_cv) which deal with CV processing, but lacks specific scope like recipient or purpose.
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?
No guidance is given on when to use this tool versus alternatives. The sibling tools are clearly different, but the description does not mention any context, exclusions, or alternative tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Each tool has a clearly distinct purpose: parse_cv loads CV data, ask_cv queries it, and send_email sends a notification. There is no functional overlap between the three.
All tool names follow a consistent verb_noun pattern (parse_cv, ask_cv, send_email), using snake_case throughout. The naming is uniform and predictable.
With only 3 tools, the server is tightly scoped to its stated purpose of CV parsing, querying, and email notification. This is well within the ideal range and each tool earns its place.
The tools cover the core workflow of parsing a CV, asking about its content, and sending an email. Minor gaps exist, such as no direct ability to update the parsed CV or manage email templates, but these are likely outside the server's narrow scope.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
AI resume triage for recruiters. Query your candidate pool from Claude or ChatGPT.
Auto-apply to jobs: matches your CV, tailors a fresh CV per posting, and applies for you.
Lint, match, and tailor resumes against real job postings, and save them to your Zelume account.
ATS resume scoring, job analysis, interview prep, and auto-apply that verifies each submission.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/anmolvarshney77/MCP-Server-Resume-Parser'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
