cv-rest-mcp-server

cv-rest-mcp-server

Enables retrieval of CV data as JSON, listing available themes, and generating themed CV PDFs via MCP tools and REST endpoints.

Category
Visit Server

README

CV REST/MCP Server

FastAPI + FastMCP service that renders a CV as JSON or themed PDFs.

Run

just setup && just dev

Server: http://localhost:8080 · MCP: /mcp (JSON-RPC, not a browser page)

REST API

Method Path Description
GET / Landing page
GET /health Health check
GET /cv CV as JSON
GET /cv/html?theme=<name> Rendered CV as HTML
GET /cv/preview?theme=<name> Preview page with toolbar
GET /cv/pdf?theme=<name> CV as PDF (attachment)

Interactive OpenAPI docs (Swagger UI): /docs

MCP

Mounted at /mcp via Streamable HTTP transport.

Tools

Tool Parameters Returns
get_cv — JSON object with full CV data
get_available_themes — list[str] of theme names
generate_cv_pdf theme: str Base64-encoded PDF bytes

Connect from an MCP client

Any MCP-compatible client (Claude Desktop, Cursor, VS Code with Kilo, Windsurf) can use this server. Add to your client's MCP config:

{
  "mcpServers": {
    "cv-rest-mcp-server": {
      "url": "http://localhost:8080/mcp"
    }
  }
}

For a deployed instance, replace the URL with your public endpoint.

Themes

classic · minimal · modern · original — defined in app/themes/<name>.py as CSS strings.

Content & Customization

Edit data/cv.json (validated against CVData in app/cv_data.py). Restart after changes.

Set CV_DATA_PATH to point to a different JSON file. See data/cv.example.json for the full schema.

Rate Limiting

Per-IP, in-memory. localhost exempt.

Endpoint Limit
/ 30/min
/health 60/min
/cv* 30/min
/cv/pdf 5/15min

Docker

just build && just run

GCP Deploy

Pushes to main run CI and, after both quality and test jobs pass, deploy to Cloud Run automatically. Add [skip deploy] to a commit message to run CI without deploying. GitHub-native [skip ci], [ci skip], [no ci], [skip actions], and [actions skip] skip the workflow entirely, which can leave required checks pending.

The one-time operator setup uses the deploy script (idempotent; SVC_NAME in .env names the service, image, and derived service accounts):

just deploy bootstrap                                  # first full run
just deploy upload-cv                                   # publish personal CV data
just deploy wif                                        # one-time GitHub OIDC wiring

For a normal code release, push a green change to main; do not run the build/deploy/verify stages manually. The CD verify job prints the deployed URL. It is also visible in Google Cloud Console under Cloud Run, the service, then URL. The CLI lookup uses the current SVC_NAME and GCP_REGION; service account IDs do not form part of the URL.

Stack

FastAPI · FastMCP v3 · WeasyPrint · Jinja2 · Cloud Run-compatible (stateless, $PORT-aware)

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured