AI agents call search_jobs to retrieve information from Lapras without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
page | number | — | Page number for pagination |
db_ids | array | — | List of database IDs (28: MySQL, 10: PostgreSQL, 419: SQL Server, 318: Oracle, 33: Aurora, 60: Redis, 221: DynamoDB, 170: MongoDB, 169: Elasticsearch, 200: BigQ |
keyword | string | — | The keyword to search for in job listings |
infra_ids | array | — | List of infrastructure and CI/CD IDs (15: AWS, 52: GCP, 165: Azure, 18: Docker, 17: Terraform, 224: Kubernetes, 51: Firebase, 16: CircleCI, 122: Jenkins, 180: G |
positions | array | — | List of job position keys (e.g., FRONTEND_ENGINEER, BACKEND_ENGINEER, WEB_APPLICATION_ENGINEER, INFRA_ENGINEER, SITE_RELIABILITY_ENGINEER, ANDROID_ENGINEER, IOS |
sort_type | string | — | Sort order (人気順: popularity_desc, 新着順: updated_at_desc, 年収が低い順: annual_salary_at_asc, 年収が高い順: annual_salary_at_desc) |
work_styles | array | — | List of work style IDs (1: フルリモート, 2: 一部リモート) |
framework_ids | array | — | List of framework IDs (4: Vue.js, 1428: React, 20: Next.js, 31: Nuxt.js, 6: Angular, 172: Redux, 21: Ruby on Rails, 76: Laravel, 140: Spring Boot, 8: Django, 23 |
prog_lang_ids | array | — | List of programming language IDs (3: TypeScript, 39: JavaScript, 5: Python, 32: Go, 2: Ruby, 25: PHP, 45: Java, 40: Kotlin, 27: Node.js, 43: Swift, 82: Scala, 4 |
business_types | array | — | List of business type IDs (1: 自社開発, 2: 受託開発, 3: SES) |
employment_types | array | — | List of employment type IDs (1: 正社員, 2: 業務委託, 3: インターンシップ, 4: その他) |
annual_salary_min | number | — | Minimum annual salary requirement in JPY |
Parameters from the server's own tool schema.
This tool retrieves or filters job listings based on search criteria (keyword, position, salary). It has no side effects and does not modify, create, or delete any data. It is a straightforward read/search operation, classified as Read with low severity since misuse would only expose information already intended to be searchable.
From the tool's definition Tool description: 'Search job by keyword, position, and minimum annual salary' — a query operation with no modification, creation, or deletion of data.
Risk signalsHigh parameter count (13 properties)
Attacks that exploit this kind of access
Search job by keyword, position, and minimum annual salary. It is categorised as a Read tool in the Lapras MCP Server, which means it retrieves data without modifying state.
search_jobs accepts 12 parameters: page, db_ids, keyword, infra_ids, positions, sort_type, work_styles, framework_ids, prog_lang_ids, business_types, employment_types, annual_salary_min. The full parameter table on this page comes from the server's own tool schema.
Register the Lapras MCP server in PolicyLayer and add a rule for search_jobs: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Lapras. Nothing to install.
search_jobs is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the search_jobs rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for search_jobs. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
search_jobs is provided by the Lapras MCP server (@lapras-inc/lapras-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
search_jobs is one line of Lapras's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →