About Jobinja Jobs
Jobinja Jobs is a read-only MCP server for AI agents searching job ads and company information on Iran's Jobinja portal. It provides detailed vacancy data, company listings, and Jobinja's top-company scores.
Key features
- 01Search jobs by location, role, and conditions
- 02Read ad details, salary, and required skills
- 03Find companies and inspect their open and past ads
- 04View Jobinja's top-50 company scores
- 05Check job counts and salary statistics
Use cases
- 01Find remote or location-based jobs in Iran
- 02Check a vacancy's pay, skills, and requirements
- 03See what roles a company has open or previously listed
- 04Compare company scores and advertised salary ranges
MCP support
Exposes read-only tools to MCP clients for searching and reading public Jobinja job and company data. The site responds only to Iranian networks; an Iranian proxy can be configured.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
uvx jobinja-mcpJOBINJA_MCP_PROXYOptional HTTP proxy URL for the Jobinja requests; system proxy settings are ignored. Also accepts a comma-separated list: one is used until it gets blocked or fails to connect, then the next.Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEjobinja-mcp: Jobinja (جابینجا) Iran job search MCP server for AI agents
jobinja-mcp is an unofficial, read-only MCP server that gives AI agents the job ads and company pages of Jobinja (جابینجا, jobinja.ir), the Iranian job portal.
Its 7 tools search ads by keyword, province, category, remote, contract type, experience and minimum salary, read a full ad with its salary and skills,
look up companies and their open ads, and read Jobinja's top-50 company scores.
No API key or Jobinja account is needed. It works in Claude, Cursor, Copilot and any other MCP client.
For AI agents · Quick start · Tools · Limits · فارسی
For AI agents
- What: unofficial MCP server (model context protocol) for jobinja.ir: job ad search with filters, ad details (salary, skills, degree, military status, description), company profiles, a company's open and past ads, company search by name or industry, and the top-50 company scores.
- Install:
uvx jobinja-mcporclaude mcp add jobinja -- uvx jobinja-mcp. Transport: stdio. Needs uv (Python 3.10+). - Auth: none, no API key or account. Optional
JOBINJA_MCP_PROXY(HTTP proxy URL, or a comma-separated list); system proxy settings are ignored. - Access: read-only. It cannot log in, apply, post or save anything, so no confirmation is needed before calling any tool.
- Network: jobinja.ir answers only Iranian networks (other countries get HTTP 403). Run it from Iran, or route it through an Iranian proxy with
JOBINJA_MCP_PROXY. - Tools: 10, all prefixed
jj_. Typical sequences:jj_search_jobs->jj_job;jj_search_companies->jj_company->jj_company_jobs;jj_filterswhen a province, category or industry name is rejected. - Use when: the user wants jobs in Iran (استخدام), asks what a company is hiring for, what an ad pays or requires, or which companies Jobinja ranks best.
- Do not use when: the user wants reviews or ratings of a company's work culture (Jobinja has none), or jobs outside Iran.
- Output: compact JSON; names and descriptions are Persian as Jobinja has them. Salaries are monthly, in Toman.
Quick start
claude mcp add jobinja -- uvx jobinja-mcp
Or in any MCP client config:
{ "mcpServers": { "jobinja": { "command": "uvx", "args": ["jobinja-mcp"] } } }
Tools
| Tool | What it does |
|---|---|
jj_search_jobs | Ads by keyword, province, city, category, remote, full/part time, internship, experience, benefits (loan, esop, ...), minimum salary, sort; 20 per page |
jj_job | One ad: salary (monthly, Toman), contract, experience, skills, degree, gender, military status, description, similar ads |
jj_company | Company profile: founding year, industry, size, website, open job count, intro, culture and benefits text |
jj_company_jobs | A company's open ads, or its expired ads (hiring history) page by page, up to 100 rows |
jj_search_companies | Companies by name, or one industry, 8 per page |
jj_top_companies | Jobinja's top-50 companies with score out of 10 and three sub-scores |
jj_filters | Exact province, category and industry names, experience levels, salary steps |
jj_market | Live open-ad counts per category, province, city, industry and top skill |
jj_skills | Skills matching a word with how many ads ever listed each |
jj_salary_stats | Min/median/max of stated monthly salaries, sampled from the ad pages of the top results |
You: Remote Python jobs that pay at least 30 million Toman a month?
Agent: calls
jj_search_jobs(keyword="python", remote=True, min_salary=30), thenjj_jobon the best ids.
Limits
- Ad lists hide salaries from logged-out visitors; the salary is read from each ad page (
jj_job). - Jobinja has no employee reviews or salary surveys, so there are none here. The only rating is the top-50 score.
- A search with a single filter (only a province, only a category, only remote) is served from one of Jobinja's SEO pages; results are the same.
فارسی
jobinja-mcp یک سرور MCP غیررسمی و فقطخواندنی برای جابینجا (jobinja.ir) است: جستجوی آگهیهای استخدام با فیلتر استان، دستهبندی، دورکاری، نوع قرارداد، سابقه و حداقل حقوق، خواندن کامل آگهی (حقوق، مهارتها، مدرک)، پروفایل شرکتها و آگهیهای باز آنها، و امتیاز ۵۰ شرکت برتر. نیازی به کلید یا حساب کاربری نیست. جابینجا فقط از شبکههای ایران پاسخ میدهد.
License
MIT. Unofficial; not affiliated with Jobinja. Author: Sepehr Radmard (سپهر رادمرد), github.com/sepehr071.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.