Landed MCP Server
OfficialThis server lets an AI agent search Landed's live AI-native job corpus and prepare applications and interview prep.
Search jobs (
search_jobs): ranked, fit-scored shortlists from a structured brief — role, skills, seniority, work mode, physical locations, remote-eligibility countries/regions, comp/currency, industries, company stages, companies to avoid — or a free-textquery, withlimitand aproductUrlto apply in Landed.Get an application form (
get_job_form): fetch a job's form byjobId, grouped into standard (auto-fillable), screening (draftable), and EEO fields — free.Study for interviews (
get_learning_content): free curated interview-prep, portfolio-project, and roadmap resources filtered by role, topic, or category — works with no backend.Guided prompts:
find_jobsandprep_for_roleslash-command workflows that chain tools and present clean shortlists.Access notes: OAuth 2.1 sign-in (or a bearer API token); searches count against daily plan limits (Free 10 / Plus 50 / Pro & Max 200), returning
sign_in_requiredorlimit_reachedstatuses when applicable.
Click on "Deploy 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., "@Landed MCP Server find ai engineer jobs remote"
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.
Search AI-native jobs and study for interviews — from any MCP client. A public Model Context Protocol server giving Claude, Cursor, VS Code, and any MCP-capable agent live access to Landed's ranked, fit-scored job corpus.
Maintained by Landed — daily AI-native job matches, agent help with every application, and mock-interview prep.
What is this?
Landed MCP connects your AI assistant to a curated, continuously-updated corpus of AI-native roles (AI Engineer, ML Engineer, RAG Engineer, AI PM, GTM Engineer, and more). Instead of copy-pasting job boards into a chat, your agent can:
🔎 Search jobs — ranked and fit-scored against a structured brief (role, skills, seniority, remote, compensation, industries…), or from a plain-English description.
📝 Apply in landed — every result links to the job in the landed app, where you apply.
🎓 Study for interviews — fetch free, curated interview-prep, portfolio, and roadmap resources.
It speaks Streamable HTTP and works with any MCP client. Use the hosted server in seconds, or self-host this repo against your own Landed API.
Sign in with landed. Add the server and your AI app opens landed's sign-in; choose Allow and you're connected. Clients without OAuth can still send a landed API token as
Authorization: Bearer <token>.
Related MCP server: CareerPilot
Quick start (hosted)
The hosted server lives at:
https://mcp.landed.jobs/mcpPick your client below. Clients with OAuth (Claude, Claude Code, ChatGPT, Cursor, VS Code) open
"Sign in with landed" the first time: sign in, choose Allow, done. You can disconnect any time in
landed under Settings → API tokens. The --header / headers lines below are only for clients
without OAuth: sign in to landed and create an API token in Settings.
Claude Code
The one-liner (CLI):
claude mcp add --transport http landed-jobs https://mcp.landed.jobs/mcpThen in a session: /mcp, pick landed and sign in, to confirm it's connected, and try the find_jobs prompt.
Claude Desktop
Open Settings → Developer → Edit Config (this opens claude_desktop_config.json), then add:
{
"mcpServers": {
"landed-jobs": {
"command": "npx",
"args": [
"-y", "mcp-remote", "https://mcp.landed.jobs/mcp",
"--header", "Authorization: Bearer lnd_live_your_token_here"
]
}
}
}Restart Claude Desktop.
Claude Desktop bridges remote HTTP servers through
mcp-remote. If your build has native Custom Connectors (Settings → Connectors → Add custom connector), you can instead pastehttps://mcp.landed.jobs/mcpdirectly.
Cursor
Create .cursor/mcp.json in your project (or ~/.cursor/mcp.json globally):
{
"mcpServers": {
"landed-jobs": {
"url": "https://mcp.landed.jobs/mcp",
"headers": { "Authorization": "Bearer lnd_live_your_token_here" }
}
}
}Then enable landed-jobs under Settings → MCP.
VS Code (GitHub Copilot / Agent Mode)
Create .vscode/mcp.json:
{
"servers": {
"landed-jobs": {
"type": "http",
"url": "https://mcp.landed.jobs/mcp",
"headers": { "Authorization": "Bearer lnd_live_your_token_here" }
}
}
}Open the Chat view → Agent mode → the tools appear under the 🔧 picker.
Windsurf
Edit ~/.codeium/windsurf/mcp_config.json:
{
"mcpServers": {
"landed-jobs": {
"serverUrl": "https://mcp.landed.jobs/mcp",
"headers": { "Authorization": "Bearer lnd_live_your_token_here" }
}
}
}Cline (VS Code extension)
Open Cline → MCP Servers → Configure, or edit cline_mcp_settings.json:
{
"mcpServers": {
"landed-jobs": {
"type": "streamableHttp",
"url": "https://mcp.landed.jobs/mcp",
"headers": { "Authorization": "Bearer lnd_live_your_token_here" }
}
}
}Gemini CLI
Edit ~/.gemini/settings.json (or .gemini/settings.json in your project):
{
"mcpServers": {
"landed-jobs": {
"httpUrl": "https://mcp.landed.jobs/mcp",
"headers": { "Authorization": "Bearer lnd_live_your_token_here" }
}
}
}Restart gemini and run /mcp to see the tools.
Any other MCP client
Point it at https://mcp.landed.jobs/mcp using the Streamable HTTP transport and pass
Authorization: Bearer <token>. Quick sanity check from a terminal:
curl -s -X POST https://mcp.landed.jobs/mcp \
-H 'content-type: application/json' \
-H 'accept: application/json, text/event-stream' \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'Registries
Landed is listed on the Official MCP Registry as
io.github.landedjobs/landed, and on Glama and
MCP Market. Clients that read the registry can discover and install it
without any manual configuration.
Tools
Tool | What it does | Access |
| Ranked, fit-scored jobs, each with a | signed in, daily limit by plan |
| Curated interview-prep, portfolio, and roadmap resources. | signed in |
search_jobs returns one of three statuses:
ok:jobs(each withjobId,title,company,location,fitLabel,oneLineWhy,productUrl).sign_in_required: the token was not accepted; reconnect landed in your AI app.limit_reached: the day's searches for the plan are used; the result hasmessage,limitandresetsAt.
Prompts (guided workflows)
MCP prompts are reusable, user-invocable skills that teach the agent how to chain the tools and present results as a clean shortlist — never raw JSON. In most clients they show up as slash-commands.
Prompt | Args | What it guides |
|
| Search, then present a ranked, fit-scored shortlist with links to apply in landed. |
|
| Pull learning resources for a role and suggest a study order. |
The server also ships always-on instructions (access and limits, tool overview, presentation rules)
that compliant clients load automatically.
Location parameters
Location eligibility is structured rather than keyword-matched:
locations: physical cities/countries, with country included for ambiguous cities, e.g.["Bengaluru, India"]countryCodes: ISO alpha-2 remote/base eligibility, e.g.["IN"]regionCodes:apac,emea, oramericasworkAuthorizationCountryCodes: ISO alpha-2 work-authorization countriesremote: work mode (remote,hybrid, oronsite)
The hosted API resolves human city labels to stable place identities. Callers must not invent place
IDs. The legacy regions field remains accepted for compatibility.
Auth & pricing
The server uses OAuth 2.1 (authorization code with PKCE, dynamic client registration). A request with no
token gets 401 with WWW-Authenticate: Bearer resource_metadata="https://mcp.landed.jobs/.well-known/oauth-protected-resource",
and the client discovers the rest from there:
/.well-known/oauth-protected-resourceand/.well-known/oauth-authorization-serverPOST /oauth/register(dynamic client registration),POST /oauth/token(code exchange)the Allow screen at
https://app.landed.jobs/oauth/authorize
The token an app receives is an ordinary landed API token, listed in Settings → API tokens. A token you
create there by hand works the same way, as Authorization: Bearer lnd_live_…. Privacy:
mcp.landed.jobs/privacy.
Each search counts against a daily limit set by your landed plan:
Plan | Searches per day |
Free | 10 |
Plus | 50 |
Pro and Max | 200 |
At the limit, search_jobs returns limit_reached with when it resets.
Architecture
This repository is a thin, self-hostable proxy. It speaks MCP and forwards to the hosted Landed API — it holds no database, no ranking engine, and no job data.
MCP client landed-mcp (this repo) Landed API
┌─────────────┐ HTTP ┌────────────────────────┐ HTTPS ┌────────────────────────┐
│ Claude / │ ───────▶ │ • MCP protocol + tools │ ──────▶ │ • search engine │
│ Cursor / │ /mcp │ • forwards caller creds│ │ • job corpus │
│ VS Code … │ ◀─────── │ • local learning list │ ◀────── │ • auth · plan limits │
└─────────────┘ └────────────────────────┘ └────────────────────────┘The proxy forwards the caller's API token to the Landed API, which validates it, runs the search,
counts it against the plan limit, and returns the result. A request without a token is answered by the
proxy itself with 401, so it never reaches the API. The get_learning_content catalog is static and lives in this repo
(src/mcp/catalog/learning.ts) — that tool works with no backend at all.
Self-host
Run your own proxy against the Landed API (or your own deployment of it).
Prerequisites
Node.js ≥ 20
pnpm (
npm i -g pnpm)A Landed API base URL and its shared internal secret
Run
git clone git@github.com:landedjobs/landed-mcp.git
cd landed-mcp
pnpm install
cp .env.example .env # then fill in the values below
pnpm dev # hot-reload dev server
# → [mcp] listening on :8090 — POST /mcp → https://api.landed.jobs/api/v1For production: pnpm start.
Stdio and Docker
For clients that start the server as a process, pnpm start:stdio speaks MCP over stdio instead of HTTP. Set LANDED_API_TOKEN to your API token; without it search_jobs answers sign_in_required.
docker build -t landed-mcp .
docker run -i --rm landed-mcpThe image runs the stdio server against the hosted API.
Environment variables
Variable | Required | Default | Description |
| ✓ |
| Hosted Landed API base, including the |
| ✓ | — | Shared secret authenticating this proxy to the API (must match the server's |
|
| HTTP port to listen on. | |
|
| Comma-separated allowlist of origins, or | |
|
| Per-IP first-line request cap. Each person's plan search limit is the real economic cap. | |
|
| Sign-up link in |
Endpoints
Method | Path | Purpose |
|
| MCP Streamable HTTP endpoint (stateless). |
|
| Liveness probe ( |
Development
pnpm dev # watch + reload
pnpm check-types # tsc --noEmit
pnpm test # input-contract and search-result tests
pnpm start # run onceThe repository includes official MCP Registry metadata in server.json. It describes
the public Streamable HTTP endpoint but does not imply that the server has been submitted to or
accepted by any external registry.
Project layout
src/
├── index.ts # bootstrap: start the HTTP server
├── config/ # env → typed config
├── http/ # express shell + per-IP rate limiter
├── services/api-client.ts # typed fetch client → Landed API
├── types.ts # the API response contract (owned here)
└── mcp/
├── server.ts # instructions + tool/prompt registration
├── prompts.ts # find_jobs / prep_for_role
├── catalog/learning.ts # static, public learning resources
└── tools/ # search_jobs · get_learning_contentStack: TypeScript · Express · @modelcontextprotocol/sdk · Zod. No database, no build step (runs on tsx).
Contributing
Issues and PRs welcome — bug fixes, new client setup guides, and learning-catalog additions especially.
Please run pnpm check-types and pnpm test before opening a PR. For private vulnerability reports,
follow SECURITY.md.
License
MIT © Landed
Available Tools
3 toolsget_job_formGet job application formAInspect
Get the application form for a job (by the jobId returned from search_jobs), so you can prepare answers before the user applies. Fields are grouped: "standard" (auto-fillable from a candidate profile via mapsTo), "screening" (free-text questions to draft from the résumé/experience), and "eeo" (leave to the user). Always free — a job's form is only reachable once you've already found the job via search_jobs.
Inputs: jobId (required).
get_learning_contentGet learning contentAInspect
Get Landed's free learning content to help the user prepare — curated interview-prep repos (real questions, company guides, worked system designs), portfolio-project catalogs, and role roadmaps from the landedjobs GitHub org. Filter by topic, role, and/or category. Always free, for any caller.
Inputs: role, topic, category.
search_jobsSearch jobsAInspect
Search Landed's live job corpus for AI-native roles and get a ranked, fit-scored shortlist. Fill the structured fields (role, skills, work mode, physical locations, remote-eligibility countries/regions, seniority, comp, industries…) from the user's request — they drive the ranking. Physical locations are resolved to stable places; use ISO country codes and canonical region codes when known. You may also pass a free-text "query"; it's parsed into the same filters and used as a semantic nudge. Free tier: up to a shared budget of jobs for anonymous callers (each returned job counts). Authenticated callers (Authorization: Bearer ) get unlimited, brief-personalized results.
Inputs: role, avoid, limit, query, +12 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 3 tools
Each tool targets a distinct stage of the job-search workflow: discovery (search_jobs), application preparation (get_job_form), and learning resources (get_learning_content). There is no meaningful overlap, and the dependency between search_jobs and get_job_form is explicitly documented.
All three names follow a consistent snake_case verb_noun convention (search_jobs, get_job_form, get_learning_content). The verb variation between search and get maps cleanly to distinct operations rather than inconsistency.
Three tools is on the thin side for a job platform, but each has a clear, non-redundant role within a focused prep-and-discovery scope. It reads as intentionally minimal rather than an incomplete afterthought.
The surface covers discovery, form inspection, and learning content, but stops short of core lifecycle operations like actually submitting an application, saving/bookmarking jobs, or managing a candidate profile. These gaps may force agents into dead ends when users want to act rather than just prepare.
Maintenance
Related MCP Connectors
Search Thousands of jobs, Thousands of companies. MCP for Claude, ChatGPT, Codex and Cursor.
MCP for 8,700+ current AI jobs. 13 tools: search, match, salaries, companies, commerce quotes.
Resume builder with native MCP — create and edit resumes from your AI assistant.
Search live startup jobs from Claude, Cursor, or ChatGPT via MCP. Free, no account needed.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceAI job search, resume builder, and career advice via MCP2MIT
- AlicenseAqualityCmaintenanceAn AI job-hunt copilot that enables searching live job boards, shortlisting openings, tracking application pipelines, and generating tailored resumes and cover letters from any MCP client.14Apache 2.0
- AlicenseNot gradedqualityCmaintenanceAn MCP server that exposes job-search and application-management capabilities to compatible AI clients, enabling discovery of vacancies, drafting of tailored application materials, and coordinated human-approved submissions.MIT
- AlicenseAqualityBmaintenanceLive job postings read straight from 139 employers' own ATS APIs (Greenhouse, Lever, Ashby, Beisen, Moka). Every listing carries the employer's real posting date, days_open and a ghost_score — a board's "posted 2 days ago" is routinely 300 days old underneath. Heavy on AI infra, autonomous driving and embodied AI across the US, EU and China. No account, no signup, no résumé upload.15946 PyPI16MIT