Claude, Cursor, Windsurf 또는 기타 MCP 호환 AI 도구에서 20,000개 이상의 기업이 제공하는 1,000,000개 이상의 강화된 채용 정보를 직접 검색하세요.
무료 사용 — 가입 불필요. 일일 500회 호출이 포함되어 있습니다.
Claude Code 또는 Claude Desktop MCP 설정에 다음을 추가하세요:
{
"mcpServers": {
"jobdatalake": {
"command": "npx",
"args": ["-y", "@jobdatalake/mcp-server"]
}
}
}이것으로 끝입니다. API 키가 필요 없습니다. 그런 다음 다음과 같이 질문하세요:
"연봉 15만 달러 이상의 원격 시니어 React 채용 정보를 찾아줘"
"이번 주에 올라온 신입 데이터 과학 채용 정보"
"연봉 20만 달러 이상의 Anthropic 채용 정보"
jobdatalake.com에서 가입하여 나만의 API 키를 받은 후 추가하세요:
{
"mcpServers": {
"jobdatalake": {
"command": "npx",
"args": ["-y", "@jobdatalake/mcp-server"],
"env": {
"JDL_API_KEY": "jdl_your_key_here"
}
}
}
}Related MCP server: LinkedIn Job Search MCP Server
search_jobs키워드, 기술, 연봉, 원격 유형, 연차, 위치, 날짜 등으로 채용 정보를 검색하고 필터링합니다.
필터:
query — 키워드 검색 (제목, 회사, 기술)
skills — AND 필터: Python,AWS,Kubernetes (모두 일치해야 함)
salary_min / salary_max — USD 기준 (전체 금액 입력, 예: 150000)
remote_type — fully_remote, hybrid, on_site
seniority — Entry, Mid Level, Senior, Staff, Principal, Manager, Director, C Level
location — 도시, 국가 또는 대륙 (Europe, Asia, Latin America, Scandinavia 등)
countries — ISO 코드: US,GB,DE
job_function — eng, data, design, sales, marketing, product 등
employment_type — full_time, part_time, contract, internship
posted_within — 24h, 7d, 30d
sort_by — posted_at:desc, salary_max_usd:desc, salary_min_usd:asc
company — 도메인별 필터: stripe.com
get_job설명, 요구 사항, 연봉, 지원 링크를 포함한 특정 채용 정보의 전체 세부 정보를 가져옵니다. 검색 결과의 job_handle ID를 사용하세요.
get_company기업 프로필(산업, 규모, 투자 유치, 채용 페이지)을 가져옵니다. 도메인(stripe.com) 또는 핸들을 허용합니다.
get_filter_options채용 건수와 함께 사용 가능한 필터 값을 확인합니다. 데이터셋에 무엇이 있는지 탐색하는 데 유용합니다.
find_similar_jobsAI 벡터 유사도를 사용하여 특정 채용 정보와 유사한 채용 정보를 찾습니다. 원격 및 기술 관련 채용 정보에 사용할 수 있습니다.
무료 티어 (가입 불필요): 일일 500회 호출, 매일 초기화.
개인 API 키 사용 시:
무료: 가입 시 1,000 크레딧 제공
스타터: 1,000,000 크레딧 — $200
성장: 2,000,000 크레딧 — $300
비즈니스: 4,000,000 크레딧 — $400
크레딧은 만료되지 않습니다. API 키 받기.
20,000개 이상의 기업에서 제공하는 100만 개 이상의 활성 채용 정보
40개 이상의 ATS 플랫폼 (Greenhouse, Lever, Workday, Ashby 등)
매시간 업데이트
AI 강화: 연봉(USD), 기술, 연차, 원격 정책, 직무 기능
100ms 미만의 검색 응답 속도
쿼리 | 기능 |
"Remote Python jobs over $150k" | 기술 + 연봉 + 원격 필터 |
"Jobs at Stripe" | 기업 필터 |
"Entry level data science" | 연차 필터 |
"New remote jobs today" | 날짜 + 원격 필터 |
"React AND TypeScript jobs in Europe" | 다중 기술 AND + 대륙 |
"Highest paying remote jobs" | 연봉 정렬 |
"What skills are most in demand?" | 필터 옵션 도구 |
MIT — LICENSE 참조.
웹사이트: jobdatalake.com
Find jobs similar to a given job listing using AI vector similarity. Great for "more like this" discovery.
| Name | Required | Description | Default |
|---|---|---|---|
| job_id | Yes | Job handle or ID to find similar jobs for | |
| per_page | No | Number of results |
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 behavioral disclosure. It mentions the method ('AI vector similarity') but lacks details on performance (e.g., speed, accuracy), limitations (e.g., data freshness, similarity thresholds), or output format (e.g., list structure, fields returned). For a tool with no annotation coverage, this leaves significant gaps in understanding how it behaves.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is front-loaded with the core purpose in the first sentence and adds a brief use case note in the second. Both sentences earn their place by providing essential information without redundancy or fluff, making it highly efficient and well-structured.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's moderate complexity (AI-based similarity search) and lack of annotations and output schema, the description is incomplete. It explains the purpose and method but misses behavioral details (e.g., what 'similar' means, response format) and usage nuances. This is adequate as a minimum viable description but has clear gaps for effective agent use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already documents both parameters (job_id and per_page) adequately. The description does not add any additional meaning beyond what the schema provides, such as explaining how job_id is used in similarity calculations or constraints on per_page values. Baseline 3 is appropriate when the schema does the heavy lifting.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the specific action ('Find jobs similar to a given job listing') and the method ('using AI vector similarity'), distinguishing it from sibling tools like get_job (retrieve single job) and search_jobs (general search). It explicitly mentions the use case ('more like this' discovery), making the purpose highly specific and differentiated.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides clear context for when to use this tool ('Great for "more like this" discovery'), implying it's for similarity-based recommendations rather than direct retrieval or general search. However, it does not explicitly state when not to use it or name alternatives like search_jobs for different query types, which would be needed for a perfect score.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get company profile including open job count, industry, size, and career page URL.
| Name | Required | Description | Default |
|---|---|---|---|
| company | Yes | Company domain (e.g. "stripe.com") or handle |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden for behavioral disclosure. It states this is a 'Get' operation which implies read-only behavior, but doesn't specify whether it requires authentication, has rate limits, returns partial vs complete data, or handles errors. For a tool with zero annotation coverage, this leaves significant behavioral gaps.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence that front-loads the core purpose ('Get company profile') followed by specific data points included. Every word serves a purpose with no redundancy or unnecessary elaboration.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple read operation with one parameter and no output schema, the description adequately covers what data is returned. However, without annotations or output schema, it doesn't specify the return format, error conditions, or data freshness. The description is minimally complete but leaves the agent to assume standard behavior.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% description coverage, with the single parameter 'company' documented as accepting domain or handle. The description doesn't add any parameter-specific information beyond what's in the schema, but doesn't need to since schema coverage is complete. This meets the baseline for high schema coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Get' and the resource 'company profile', specifying what information is included (open job count, industry, size, career page URL). It distinguishes from sibling tools like 'get_job' by focusing on company-level data rather than job-specific information, though it doesn't explicitly contrast with all siblings.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
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 alternatives like 'search_jobs' or 'find_similar_jobs'. It doesn't mention prerequisites, constraints, or typical use cases, leaving the agent to infer usage context from the tool name and description alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get full details for a specific job listing including description, requirements, salary, and apply link.
| Name | Required | Description | Default |
|---|---|---|---|
| job_id | Yes | Job handle or ID |
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 behavioral disclosure. It states the tool retrieves 'full details' but doesn't cover critical aspects like error handling (e.g., if the job ID is invalid), response format, authentication needs, rate limits, or whether it's a read-only operation. The description is minimal and leaves behavioral traits largely unspecified.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence that front-loads the core action ('Get full details') and lists key data points. There's no wasted verbiage, and it's appropriately sized for a simple lookup tool. However, it could be slightly more structured by separating usage hints, but this is minor.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of annotations and output schema, the description is incomplete for a tool that retrieves data. It mentions what details are included but doesn't explain the return structure, potential errors, or dependencies. For a read operation with no structured output, more context on the response is needed to be fully helpful to an agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% description coverage, with the single parameter 'job_id' documented as 'Job handle or ID.' The description adds no additional meaning beyond this, such as format examples or sourcing hints. With high schema coverage, the baseline is 3, as the description doesn't compensate but also doesn't detract from the schema's clarity.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose with a specific verb ('Get') and resource ('job listing'), listing key data fields like description, requirements, salary, and apply link. It distinguishes from sibling tools like 'search_jobs' (which likely returns multiple results) and 'find_similar_jobs' (which suggests broader matching), but doesn't explicitly contrast them. The purpose is unambiguous but could be more precise about differentiation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
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 alternatives. It doesn't mention prerequisites (e.g., needing a job ID), exclusions, or comparisons to siblings like 'search_jobs' (for broader queries) or 'find_similar_jobs' (for related listings). Usage is implied by the focus on 'specific job listing,' but explicit context is lacking.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search 1M+ job listings from 20K+ companies. Supports keyword search, AI semantic search, filters for location, salary, remote type, seniority, skills, and more.
| Name | Required | Description | Default |
|---|---|---|---|
| query | No | Keyword search (title, company, skills). Use * for all jobs. | |
| semantic_query | No | Natural language search, e.g. "backend engineer at a climate tech startup" | |
| location | No | Location filter, e.g. "Remote", "San Francisco", "Germany" | |
| remote_type | No | Remote work policy | |
| countries | No | Comma-separated ISO country codes, e.g. "US,GB,DE" | |
| job_function | No | ||
| seniority | No | Comma-separated: junior, mid, senior, staff, principal | |
| employment_type | No | ||
| salary_min | No | Minimum annual salary in USD | |
| salary_max | No | Maximum annual salary in USD | |
| skills | No | Comma-separated required skills, e.g. "Python,AWS,Kubernetes" | |
| company | No | Company domain filter, e.g. "stripe.com" | |
| page | No | ||
| per_page | No | Results per page (max 100) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden for behavioral disclosure. It mentions the dataset scale (1M+ jobs, 20K+ companies) and search capabilities, but lacks critical behavioral details: whether this is a read-only operation (implied but not stated), pagination behavior beyond parameters, rate limits, authentication requirements, error handling, or response format. For a search tool with 14 parameters, this leaves significant gaps.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is efficiently structured in two sentences: first establishes scope and scale, second enumerates capabilities. Every phrase adds value (scale numbers, search types, filter categories). Could be slightly more front-loaded by mentioning it's a search tool earlier, but overall well-sized without wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a complex search tool with 14 parameters, no annotations, and no output schema, the description is insufficient. It doesn't explain what results look like (structure, fields returned), pagination strategy beyond parameters, sorting options, performance characteristics, or error scenarios. The agent must rely heavily on the input schema alone, missing critical context for effective tool use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 79%, providing good baseline documentation. The description adds value by summarizing filter categories (location, salary, remote type, seniority, skills) and mentioning AI semantic search capability, which helps contextualize parameters like 'semantic_query'. However, it doesn't explain parameter interactions, default behaviors beyond schema defaults, or special syntax requirements beyond what's in schema descriptions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool searches job listings with specific capabilities (keyword search, AI semantic search, filters). It distinguishes from siblings like 'find_similar_jobs' by emphasizing broad search across 1M+ listings rather than similarity matching, and from 'get_job' by focusing on search rather than retrieval of a specific job. However, it doesn't explicitly contrast with 'get_company', leaving some ambiguity.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for searching job listings with various filters, but doesn't explicitly state when to use this tool versus alternatives like 'find_similar_jobs' (which likely finds similar jobs to a given one) or 'get_job' (which retrieves a specific job by ID). No guidance on prerequisites, error conditions, or performance considerations is provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v1.0.0find_similar_jobsget_companyget_jobsearch_jobsScored across 4 tools
Each tool has a clearly distinct purpose: find_similar_jobs focuses on AI-based similarity matching for job discovery, get_company retrieves company profiles, get_job fetches specific job details, and search_jobs handles broad keyword/semantic search with filtering. There is no overlap in functionality, making tool selection unambiguous.
All tool names follow a consistent verb_noun pattern with snake_case (e.g., find_similar_jobs, get_company, get_job, search_jobs). The verbs (find, get, search) are appropriately descriptive and maintain a predictable naming convention throughout the set.
With 4 tools, the server is well-scoped for job data exploration, covering key operations like searching, retrieving details, finding similar items, and company profiling. It feels slightly lean but reasonable, as core workflows are supported without unnecessary bloat.
The toolset provides comprehensive coverage for job data querying and discovery, including search, detailed retrieval, similarity matching, and company context. Minor gaps exist, such as no explicit update or delete operations, but these are likely unnecessary for a read-only data lake, and agents can work effectively with the available tools.
MCP for 8,700+ current AI jobs. 13 tools: search, match, salaries, companies, commerce quotes.
AI job search MCP — fact-checked jobs, application tracker, alerts. ChatGPT, Claude, Cursor.
Search live startup jobs from Claude, Cursor, or ChatGPT via MCP. Free, no account needed.
7 recruiting tools over one MCP endpoint: ATS boards, LinkedIn jobs, profiles, companies, Naukri.
