1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Lathe shape my resume for a senior backend role" 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.

Lathe

by itonskie

Overview Schema Related Servers Score Discussions

Local

Lathe

Local MCP server that shapes tailored resume PDFs with a live browser preview.

Lathe is a small Model Context Protocol server you run on your own machine. You talk to Claude about your background, your target job, and the kind of resume you want; Claude shapes the content; Lathe renders it in a real browser window that updates as you iterate. When you're happy, Lathe exports a print-ready PDF.

Nothing about you leaves your laptop.

Why this exists

A lot of resume MCPs ship your data to a third-party API to render the PDF. The most popular one (resumake-mcp) depends on an upstream service that's been shut down, and pins a vulnerable version of the MCP SDK. Lathe takes the opposite approach: render everything locally with headless Chromium, no external services, no accounts.

Related MCP server: md2pdf-mcp

Features

Live preview — A Chromium window opens on first use and stays put. Every edit Claude pushes refreshes the page in place, so you watch the resume change as you give feedback.
HTML/CSS templates — Three starter templates (modern, classic, minimal). Hand-write your own, or describe one in chat and let Claude generate it.
Print-ready PDF — letter paper, real CSS, real fonts. Exported on demand.
Local-first — No third-party APIs. No accounts. Your data stays on your machine.
Strict TypeScript — strict: true, noUncheckedIndexedAccess: true.
Zero secrets — no env vars, no keys, no auth.

How it works

You ────▶ Claude ────▶ Lathe MCP ──▶ Handlebars render ──▶ work/current.html
                                                              │
                                                              ▼
                                                      Puppeteer Chromium
                                                       (visible window)
                                                              │
                                       ────▶ page.reload() ◀──┘
                                       │
                                       ▼
                                  You see it change
                                       │
                                       ▼
                                  "Export it"
                                       │
                                       ▼
                                 output/*.pdf

Install

git clone https://github.com/itonskie/lathe.git
cd lathe
npm install        # also downloads a Chromium for Puppeteer (~170 MB on first install)
npm run build

Then add Lathe to your Claude Desktop config:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json Windows: %APPDATA%\Claude\claude_desktop_config.json Linux: ~/.config/Claude/claude_desktop_config.json

Recommended (works with nvm / fnm / system node):

{
  "mcpServers": {
    "lathe": {
      "command": "/absolute/path/to/lathe/bin/lathe.sh",
      "args": []
    }
  }
}

The wrapper script in bin/lathe.sh sources nvm if it's installed, so it survives nvm install upgrades.

System-node alternative (no wrapper):

{
  "mcpServers": {
    "lathe": {
      "command": "node",
      "args": ["/absolute/path/to/lathe/dist/server.js"]
    }
  }
}

Only works if node is on Claude Desktop's PATH — i.e., installed via Homebrew or system package manager, not nvm. (Claude Desktop spawns subprocesses with a minimal PATH that doesn't see ~/.nvm/.)

Fully quit Claude Desktop (⌘Q on macOS — closing the window isn't enough) and reopen. Lathe shows up in the tools list.

Usage

Talk to Claude naturally:

"Here's my background [paste]. I'm applying for this Senior Backend Engineer role at Stripe [paste JD]. Use the modern template, open the preview, and let's iterate."

Claude will:

Call lathe_templates to confirm what's available.
Extract a structured resume from your inputs.
Call lathe_preview — a Chromium window opens with your resume.
You give feedback in chat ("make the first Acme bullet stronger", "drop the GPA").
Claude calls lathe_shape after each round — the window auto-refreshes.
When it looks right, ask for the PDF — Claude calls lathe_finish.

Tools

Tool	What it does
`lathe_templates`	List templates in `templates/`
`lathe_preview(data, template)`	Render + open the live browser window
`lathe_shape(data, template?)`	Push updates; browser auto-refreshes
`lathe_finish(filename?, folderPath?)`	Export the current preview as PDF
`lathe_add_template(name, html)`	Save a new template

Templates

Templates are plain HTML files in templates/, with Handlebars placeholders:

<h1>{{basics.name}}</h1>
{{#each work}}
  <div>
    <strong>{{position}}</strong> at {{company}}
    <ul>{{#each highlights}}<li>{{this}}</li>{{/each}}</ul>
  </div>
{{/each}}

One custom helper is registered: {{join keywords ", "}} — joins an array with a separator.

Templates assume this data shape, but any field is optional:

{
  basics:   { name, headline, email, phone, location, website, summary }
  work:     [{ company, position, location, startDate, endDate, highlights[] }]
  education:[{ institution, area, studyType, location, startDate, endDate, gpa }]
  skills:   [{ name, keywords[] }]
  projects: [{ name, description, url, keywords[], highlights[] }]
}

To add a template, drop an HTML file into templates/, or have Claude generate one and save it via lathe_add_template.

Development

npm run dev        # tsx watch — restart on save
npm run typecheck  # strict tsc check
npm test           # smoke test: render all templates + export PDFs (no visible browser)
npm run build      # compile to dist/

Project layout

lathe/
├── src/
│   ├── server.ts      # MCP wiring (tool registration, transport)
│   └── lathe.ts       # Core: render + Puppeteer + PDF
├── templates/         # HTML templates (Handlebars)
├── test/smoke.ts      # End-to-end render + PDF test
├── work/              # Rendered HTML lives here (gitignored)
├── output/            # Exported PDFs (gitignored)
└── dist/              # Compiled JS (gitignored)

License

Available Tools

5 tools

lathe_add_templateA

Save a new HTML template into the templates folder. The HTML can use Handlebars placeholders like {{basics.name}} or {{#each work}}…{{/each}}.

ParametersJSON Schema

Name	Required	Description	Default
`html`	Yes	Full HTML document with Handlebars placeholders
`name`	Yes	Template name (filename-safe, no extension)

TDQS

A3.8/5.0

Behavior3/5

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

No annotations are provided, so the description carries the full burden of disclosure. It reveals the action (save), destination (templates folder), and content style (Handlebars), but does not mention overwrite behavior, validation, permissions, or return values.

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 two sentences, front-loaded with the primary purpose, and includes a relevant example. Every word earns its place with no redundancy.

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?

For a simple 2-parameter tool with complete schema documentation, the description is adequate. It covers the core action and content expectations. Missing details like overwrite behavior are not critical given the schema's completeness and the absence of an output schema.

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 both parameters fully described. The description adds Handlebars examples but does not introduce additional semantic meaning beyond what the schema already provides.

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?

Uses a specific verb 'Save' and a clear resource 'HTML template into the templates folder'. The description clearly distinguishes the tool from siblings like lathe_templates (which likely lists templates) and lathe_preview (which likely previews them).

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 usage for saving new templates but does not explicitly mention when not to use it or point to alternatives like lathe_templates for listing. Usage context is clear but exclusions are absent.

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

lathe_finishA

Export the current preview as a PDF. Defaults to the output/ folder; pass folderPath to organize into subfolders.

ParametersJSON Schema

Name	Required	Description	Default
`filename`	No	Base filename without extension. A date is appended.
`folderPath`	No	Optional subfolder within output/ (e.g. 'google/2026-q3')

TDQS

A3.7/5.0

Behavior2/5

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

No annotations are provided, so the description carries full responsibility for disclosing behavior. It mentions the default output folder and subfolder option, but does not disclose potential overwriting behavior, the need for an existing preview, or file naming details beyond the schema. This leaves significant behavioral gaps for a tool that writes files.

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, well-structured sentence that front-loads the primary action ('Export the current preview as a PDF') and then adds a brief, relevant detail about default destination and folderPath. No unnecessary words.

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

Completeness3/5

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

The tool is simple, with two optional parameters fully described in the schema and no output schema required. However, the description omits important context like what happens if no preview exists, whether files are overwritten, and the exact filename format (though the schema covers the date suffix). These gaps make it only partially complete.

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

Parameters4/5

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

The schema provides 100% parameter descriptions: 'filename' (base name with date appended) and 'folderPath' (optional subfolder). The main description reinforces folderPath usage, adding contextual value beyond the schema. This exceeds the baseline for high schema coverage.

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 tool's function: 'Export the current preview as a PDF.' This is a specific verb ('export') and resource ('current preview'), and it distinguishes itself from siblings like lathe_preview, which presumably creates the preview, by focusing on finalizing/exporting it.

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 usage context by referencing 'the current preview' and the output folder, but does not explicitly state when to use this tool versus alternatives or provide any when-not-to-use guidance. The folderPath parameter is explained, but there is no mention of alternative tools for similar tasks.

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

lathe_previewA

Open a live browser window showing a rendered resume. Pass the structured resume data and the template name (from lathe_templates). The window stays open so subsequent lathe_shape calls refresh it in place.

ParametersJSON Schema

Name	Required	Description	Default
`data`	Yes	Resume data object (the shape your template expects)
`template`	Yes	Template name from lathe_templates

TDQS

A4.5/5.0

Behavior4/5

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

With no annotations, the description carries the disclosure burden. It goes beyond basic expectations by revealing that the tool opens a persistent live browser window and that the window refreshes on subsequent lathe_shape calls. This gives the agent useful behavioral context without contradicting any annotation (none provided).

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 exactly two sentences, front-loaded with the core purpose. Every phrase earns its place, with no filler or repetition of the tool name.

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

Completeness5/5

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

For a relatively simple preview tool with no output schema, the description covers purpose, inputs, and behavioral nuance (refresh behavior). The inclusion of sibling tool context via the template source is sufficient for an agent to invoke it correctly.

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

Parameters4/5

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

Schema coverage is 100%, but the description adds relational meaning: the 'template' parameter is explicitly tied to lathe_templates, and 'data' is described as 'the shape your template expects'. This enriches understanding beyond the schema's bare descriptions.

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 tool's action ('Open a live browser window showing a rendered resume') with a specific verb and resource. It distinguishes itself from siblings by explicitly mentioning 'live browser window' and how subsequent lathe_shape calls refresh it, which sets it apart from lathe_templates or lathe_finish.

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?

The description tells the user what to pass ('structured resume data' and 'template name from lathe_templates'), and explains the interaction with lathe_shape for refresh behavior. This provides clear context for when to use it, though it does not explicitly state when not to use alternatives.

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

lathe_shapeA

Push updated resume data (and optionally a different template) into the live preview. The browser window auto-refreshes so the user sees the change immediately. Use this after every feedback iteration.

ParametersJSON Schema

Name	Required	Description	Default
`data`	Yes	Updated resume data object
`template`	No	Optional: switch to a different template. Defaults to the current one.

TDQS

A4/5.0

Behavior3/5

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

Discloses a key behavioral trait: 'The browser window auto-refreshes so the user sees the change immediately.' However, with no annotations provided, the description carries the full burden and omits other side effects like persistence or error behavior, limiting transparency to moderate depth.

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: the first states the main purpose, the second covers behavior and usage. Every sentence earns its place with no redundancy or filler.

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?

Given its simplicity (two parameters, no output schema), the description adequately covers purpose, usage, and a key behavior. It could mention error handling or return behavior, but such details are not essential for a basic push/update tool.

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 description coverage is 100% for both parameters, so the description adds limited additional meaning. It mentions 'optionally a different template,' which aligns with the template parameter but doesn't go beyond the schema's own descriptions.

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: 'Push updated resume data (and optionally a different template) into the live preview.' The verb 'push' plus the specific resource 'live preview' distinguishes it from sibling tools like lathe_templates or lathe_preview.

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 instructs 'Use this after every feedback iteration,' which tells the agent when to invoke the tool. It doesn't mention when not to use it or describe alternatives, but the given guidance is direct and actionable.

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

lathe_templatesA

List the resume templates currently available in the Lathe templates folder.

ParametersJSON Schema

Name	Required	Description	Default
No parameters

TDQS

A3.8/5.0

Behavior3/5

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

There are no annotations, so the description carries the responsibility of disclosing behavior. It indicates a read-only operation ('List') and specifies the source folder, but does not mention potential side effects, permissions, return format, or edge cases. The disclosure is adequate for a simple list operation but not rich.

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, concise sentence that immediately states the action and target. It is front-loaded and contains no filler or unnecessary details, earning every word's place.

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?

Given the simplicity of the tool (no params, no annotations, no output schema), the description is mostly complete. It explains the basic purpose but could optionally mention what the returned list contains (e.g., names, paths, metadata) to fully cover expected output. However, for a straightforward listing tool, the current description is sufficient.

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

Parameters4/5

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

The tool has zero parameters, and the schema coverage is trivially 100%. The description adds no parameter information because none is needed. Per the rubric, a baseline of 4 is appropriate when there are no parameters to explain.

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 tool's function: listing resume templates available in the Lathe templates folder. It uses a specific verb ('List') and identifies the exact resource and location, distinguishing it from siblings like lathe_add_template or lathe_preview.

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

Usage Guidelines2/5

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 its siblings, nor any alternatives or exclusions. The usage context is only implied by the verb 'List' and the resource name, but no explicit direction is given.

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.

5 tool updatesv0.1.0Aug 2, 2026
- First observedlathe_add_template
- First observedlathe_finish
- First observedlathe_preview
- First observedlathe_shape
- First observedlathe_templates

Install Server

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A4.2/5.0

Disambiguation5/5

Each tool has a distinct purpose: listing templates, creating a live preview, updating the preview, exporting to PDF, and adding new templates. There is no overlap or ambiguity between them.

Naming Consistency4/5

All tools share the 'lathe_' prefix and use snake_case, but the first tool 'lathe_templates' uses a noun instead of a verb, while others use verbs like 'preview', 'shape', 'finish', and 'add_template'. This minor inconsistency is easy to overlook.

Tool Count5/5

Five tools cover the complete workflow of template management, previewing, iterative updates, and PDF export. The count is well-scoped and each tool contributes a necessary function.

Completeness5/5

The tool set covers the full lifecycle: discover templates, preview, edit data, export, and add custom templates. There are no obvious missing operations for the intended resume rendering use case.

Maintenance

ActivityStale

ResponsivenessSyncing

Resources

GitHub Repository

Need Help?

Related Servers

Unclaimed servers have limited discoverability.

Looking for Admin?

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

Related MCP Connectors

Vitex — AI Resume GeneratorOAuth
io.github.ChanMeng666
Generate tailored, ATS-optimized resume PDFs and cover letters from a job description, over MCP.
AI & Machine Learning Workplace & Productivity
2
Pdfrender A
dev.pdfrender
HTML-to-PDF MCP server — render pixel-faithful PDFs from HTML.
Workplace & Productivity
11
Reactive ResumeOAuth
io.github.amruthpillai
Free open-source resume builder with remote MCP tools for resumes and job applications.
Workplace & Productivity Developer Tools
239,632
CloudresumeOAuth
io.cloudresume
Resume builder with native MCP — create and edit resumes from your AI assistant.
Developer Tools Workplace & Productivity App Automation
2

Related MCP Servers

resume-onepage-autofit-mcp
Developer Tools App Automation Workplace & Productivity
seriserendipia
F
license
Not graded
quality
D
maintenance
From markdown resume to formatted PDF, a MCP server that generates single-page PDF resumes with smart overflow detection and layered content reduction strategies
Updated 3 months ago (2026-06-06 00:41 UTC)
-
md2pdf-mcp
Workplace & Productivity Developer Tools
chunliu
A
license
Not graded
quality
D
maintenance
MCP Server for Markdown to PDF conversion.
Updated a year ago (2025-10-13 06:13 UTC)
MIT
resume-mcp-server
Documentation Access Research & Data Search
mnoomnoo
A
license
A
quality
A
maintenance
MCP server for browsing and searching your local resume and job application documents
Updated a month ago (2026-07-31 02:19 UTC)
19
1
GPL 3.0
resume-processor-mcp
AI & Machine Learning File Systems Workplace & Productivity
OpenSystemsLab
A
license
Not graded
quality
D
maintenance
MCP server for processing Markdown resumes into multiple formats (PDF, LinkedIn templates) with AI analysis and Claude integration.
Updated a year ago (2025-08-25 20:24 UTC)
MIT

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

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/itonskie/lathe'

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