Featured

Deploy OpenClaw in 60 seconds — 20% off logoDeploy OpenClaw in 60 seconds — 20% off

Launch OpenClaw on Hostinger in about 60 seconds and keep your agent live 24/7. Our referral link gives you 20% off, no coupon code needed.

Launch on Hostinger
Run your Hermes agent on Hostinger, fully managed logoRun your Hermes agent on Hostinger, fully managed

Launch Hermes on Hostinger in one click, fully managed, no VPS knowledge needed. Use code ZACAARON10 for 10% off.

Launch on Hostinger
Crawl and scrape any site into clean data, 10% off logoCrawl and scrape any site into clean data, 10% off

Firecrawl crawls and scrapes any site into clean markdown for your agent. Get 1,000 free credits, and new users get 10% off their first purchase.

Try Firecrawl free
6,000+ web scrapers for your AI agent, start free logo6,000+ web scrapers for your AI agent, start free

Apify gives your agent live web data: 6,000+ prebuilt scrapers and actors, MCP-ready. Sign up free with $5 in usage credits.

Try Apify free
One API to scrape, enrich, and extract the internet. logoOne API to scrape, enrich, and extract the internet.

Context.dev gives your agents a single API to scrape, enrich, and extract live web data — no proxies, no parsers, no maintenance.

Start building free
SetupClaw: done-for-you OpenClaw for founders & exec teams logoSetupClaw: done-for-you OpenClaw for founders & exec teams

White-glove OpenClaw for founders and exec teams (4–50+ employees): we install, harden, integrate your tools, and maintain it — secured from day one.

Get it set up for you
SEO data APIs for your agent, $1 free credit logoSEO data APIs for your agent, $1 free credit

DataForSEO gives your agent live access to SERP results, keyword data, backlinks, and on-page SEO data through one API. New accounts get a $1 credit, good for up to 20,000 keyword or backlink lookups.

Try DataForSEO free
Reach 48,000+ AI builders

A flat monthly placement in front of developers actively installing AI tools. No lock-in, cancel anytime.

Advertise here

Works with

Claude CodeClaude DesktopCursorVS CodeClineCodex CLIOpenClaw+ any MCP client

Install to Claude Code

This server doesn't publish a one-line install command. Follow the setup in the source repository.

Summary

Resume tailoring, cover letters, PDF export, and job search via the Laddro Career API

README.md

@laddro/career-mcp

![smithery badge](https://smithery.ai/servers/laddro/career)

MCP server for the Laddro Career API. Gives AI agents access to resume tailoring, cover letter generation, PDF export, and template browsing.

Setup

Claude Desktop

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "laddro-career": {
      "command": "npx",
      "args": ["@laddro/career-mcp"],
      "env": {
        "LADDRO_API_KEY": "laddro_live_..."
      }
    }
  }
}

Claude Code

claude mcp add laddro-career -- npx @laddro/career-mcp

Set the environment variable LADDRO_API_KEY before running.

Remote HTTP

Use the hosted Streamable HTTP endpoint:

https://mcp.laddro.com/mcp

Send your Laddro API key on the MCP initialize request:

Authorization: Bearer laddro_live_...

or:

x-api-key: laddro_live_...

Available tools

| Tool | Description | |---|---| | laddro.templates.list | Browse all 22 resume templates | | laddro.templates.get | Get template colors and fonts | | laddro.fonts.list | All available font families | | laddro.languages.list | All 14 supported locales | | laddro.models.list | AI providers for BYOK | | laddro.resumes.list | User's resumes | | laddro.resumes.get | Resume metadata | | laddro.resumes.render | Re-render with new template settings | | laddro.resumes.tailor | AI-tailor resume for a job | | laddro.resumes.export | Export as PDF | | laddro.coverLetters.list | User's cover letters | | laddro.coverLetters.get | Cover letter metadata | | laddro.coverLetters.create | Create manually | | laddro.coverLetters.generate | AI-generate from resume + job | | laddro.coverLetters.render | Render with template settings | | laddro.settings.get | Current AI provider config | | laddro.settings.updateModel | Set BYOK provider | | laddro.settings.deleteModel | Remove BYOK config |

Connector (OAuth) mode

Behind the MCP_CONNECTOR_ENABLED flag (default off). When enabled and a request carries Authorization: Bearer lad_at_* (a Laddro OAuth access token), the server runs an OAuth connector session that forwards the token to laddro-backend (service.laddro.com) instead of career-api. It also serves GET /.well-known/oauth-protected-resource (RFC 9728) and answers unauthenticated /mcp calls with 401 + WWW-Authenticate: Bearer resource_metadata=... so OAuth clients can discover the authorization server. With the flag off, behaviour is unchanged (no discovery route, no 401 enforcement, all 18 tools via career-api).

Connector tools (OAuth sessions only): "You write the content. Laddro stores it and renders the PDF."

| Tool | Scope | Description | |---|---|---| | laddro.resume.schema | — | JSON Schema for resume content | | laddro.resume.create | resumes:write | Create a resume, returns { resumeId } | | laddro.resume.update | resumes:write | Full-replace a resume, returns { resumeId, updatedAt } | | laddro.coverLetter.schema | — | JSON Schema for cover-letter content |

Environment variables

| Variable | Required | Description | |---|---|---| | LADDRO_API_KEY | Yes for stdio; optional fallback for HTTP | Your Laddro API key | | LADDRO_BASE_URL | No | Override API URL (default: https://api.laddro.com) | | MCP_CONNECTOR_ENABLED | No | true enables OAuth connector mode (default off) | | LADDRO_BACKEND_URL | No | Backend base URL for connector tools (default: https://service.laddro.com) | | MCP_PUBLIC_URL | No | This server's public URL for OAuth metadata (else derived from forwarded headers) |

Development

npm ci
npm test

npm test builds the TypeScript package and runs MCP contract tests for auth handling, tool metadata, and handler routing.

Releases

This package uses Changesets and SemVer.

  • Patch: bug fixes, docs, tests, internal hardening.
  • Minor: new backwards-compatible MCP tools or capabilities.
  • Major: breaking tool names, schemas, auth, or transport behavior.

Every PR that changes the published package should include a changeset:

npm run changeset

After the PR merges to main, GitHub Actions opens a release PR with the version bump and changelog. Merging that release PR publishes the package to npm and creates the GitHub release. The Cloud Run deploy workflow also runs on main, so hosted MCP updates automatically after release merges.

MCP registry

This server is listed in the official MCP registry as com.laddro/career. server.json is the registry manifest; scripts/sync-version-metadata.mjs keeps its version in sync with the npm package on every release.

Publishing is automated: .github/workflows/publish-registry.yml runs whenever a release changes server.json on main and pushes the new version to the registry. Auth is DNS-based — the Ed25519 public key lives in the laddro.com TXT record, and the matching private key (hex) is stored as the MCP_PUBLISHER_ED25519_KEY repo secret.

To publish (or catch up) manually:

MCP_PUBLISHER_ED25519_KEY=<hex-private-key> ./scripts/publish-registry.sh

Links

License

MIT

See related servers & alternatives →

Related MCP servers

Browse all →

Related guides

Hand-picked reading to help you choose and use Search servers.