Skip to main content
Glama
felipfr

LinkedIn MCP Server

by felipfr

search_jobs

Search LinkedIn jobs using advanced filters for keywords, location, company, experience level, job type, date posted, salary, industry, and function.

Instructions

Search LinkedIn jobs with advanced filters and criteria

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
keywordsNoJob search keywords
locationNoJob location
companyNoCompany name
experienceLevelNoExperience level
jobTypeNoJob type (full-time, part-time, etc.)
datePostedNoDate posted filter
salaryNoSalary range
industryIdNoIndustry ID
functionIdNoFunction ID

Implementation Reference

  • src/server.ts:104-122 (registration)
    Registers the 'search-jobs' tool with MCP server, linking the schema and handler. Uses 'search-jobs' as the tool name with linkedinApiSchemas.searchJobs schema and an async callback that calls clientService.searchJobs(params).
    // Search Jobs Tool
    this.server.tool(
      'search-jobs',
      'Search for LinkedIn job postings based on various criteria',
      linkedinApiSchemas.searchJobs,
      async (params) => {
        this.logger.info('Executing LinkedIn Job Search', {
          keywords: params.keywords,
          location: params.location
        })
        try {
          const jobs = await this.clientService.searchJobs(params)
          return this.createResourceResponse(jobs)
        } catch (error) {
          this.logger.error('LinkedIn Job Search Failed', error)
          throw error
        }
      }
    )
  • Core handler that executes the LinkedIn job search API call. Builds query parameters from keywords, location, companies, and jobType, then makes a GET request to '/jobs/search' endpoint.
    public async searchJobs(params: SearchJobsParams): Promise<SearchJobsResult> {
      const queryParams = new URLSearchParams()
    
      const paramMapping: Record<string, string | undefined> = {
        keywords: params.keywords,
        location: params.location
      }
    
      Object.entries(paramMapping)
        .filter(([_, value]) => value !== undefined)
        .forEach(([key, value]) => queryParams.append(key, value as string))
    
      this.appendArrayParams(queryParams, {
        'company-name': params.companies,
        'job-type': params.jobType
      })
    
      return this.makeRequest<SearchJobsResult>('get', `/jobs/search?${queryParams.toString()}`)
    }
  • Zod schema defining input validation for search_jobs tool: optional companies (string[]), jobType (string[]), keywords (string), and location (string).
    searchJobs: {
      companies: z.array(z.string()).optional().describe('Filter by companies'),
      jobType: z.array(z.string()).optional().describe('Filter by job type (e.g., Full-Time, Contract)'),
      keywords: z.string().optional().describe('Keywords to search for in job postings'),
      location: z.string().optional().describe('Filter by location')
    },
  • TypeScript interface for the input parameters of searchJobs: keywords?, location?, companies?, jobType?.
    export interface SearchJobsParams {
      keywords?: string
      location?: string
      companies?: string[]
      jobType?: string[]
    }
  • TypeScript interface for the result shape of searchJobs: array of jobs with id, title, companyName, location, description, listedAt, expireAt, and paging metadata.
    export interface SearchJobsResult {
      jobs: {
        id: string
        title: string
        companyName: string
        location: string
        description?: string
        listedAt: number
        expireAt?: number
      }[]
      paging: {
        count: number
        start: number
        total: number
      }
    }
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries full burden. It only says 'search' which implies read-only, but lacks details on pagination, result limits, or other behavioral traits. The description adds minimal value beyond the name.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence that is front-loaded with the action and resource. It is concise with no unnecessary words, but could benefit from additional context without becoming verbose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With 9 parameters, no output schema, and no instructions on result pagination or default behavior, the description is insufficient. A search tool typically needs guidance on result limits, ordering, or the scope of 'advanced filters'.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% with all 9 parameters described. The description's phrase 'advanced filters' adds a small hint but does not exceed what the schema already conveys. Baseline of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses the verb 'search' and resource 'jobs' with the qualifier 'advanced filters and criteria', which clearly indicates the tool's purpose. It distinguishes from siblings like 'get_job' (single job) and 'get_saved_jobs' (saved list).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit guidance on when to use this tool versus alternatives such as 'get_job' or 'get_saved_jobs'. The description merely states what it does without providing context or exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/felipfr/linkedin-mcpserver'

If you have feedback or need assistance with the MCP directory API, please join our Discord server