Skip to main content
Glama

initiate_deep_research

Start comprehensive research by combining multiple search variations with optional contact enrichment to find LinkedIn profiles matching specific criteria.

Instructions

Initiate a deep research job that combines multiple search variations with optional email enrichment. Each result costs 1 credit.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
queryYesThe search query to research
limitNoMaximum number of results to return (default: 30, max: 100)
schoolNoFilter results by school names
enrich_emailsNoWhether to enrich results with contact information (default: true)
acceptance_thresholdNoAcceptance score threshold (0-100) for a match (default: 60)

Implementation Reference

  • The async handler function that executes the tool logic: constructs a request to the deep research API endpoint, handles parameters with defaults and bounds checking, makes the POST request using makeLinkdRequest, parses response, throws error if failed, and returns formatted content.
    export const initiateDeepResearchTool = async ({ query, limit = 30, school, enrich_emails = true, acceptance_threshold = 60, }: InitiateDeepResearchParams) => { const apiUrl = new URL("https://search.linkd.inc/api/search/deep_research"); const body = { query, limit: Math.min(limit, 100), school, enrich_emails, acceptance_threshold: Math.max(0, Math.min(100, acceptance_threshold)), }; const response = await makeLinkdRequest(apiUrl.toString(), { method: "POST", headers: { "Content-Type": "application/json", }, body: JSON.stringify(body), }); const responseData = await response.json(); if (responseData.error) { throw new Error( `Failed to initiate deep research: ${JSON.stringify(responseData.error)}` ); } return { content: [ { type: "text" as const, text: `deep research job initiated: ${JSON.stringify(responseData, null, 2)}` } ] }; };
  • Zod schema defining the input parameters for the tool, including descriptions, defaults, and constraints.
    export const initiateDeepResearchSchema = { query: z.string().describe("The search query to research"), limit: z.number().max(100).default(30).describe("Maximum number of results to return (default: 30, max: 100)"), school: z.array(z.string()).optional().describe("Filter results by school names"), enrich_emails: z.boolean().default(true).describe("Whether to enrich results with contact information (default: true)"), acceptance_threshold: z.number().min(0).max(100).default(60).describe("Acceptance score threshold (0-100) for a match (default: 60)"), };
  • Registration of the 'initiate_deep_research' tool with the MCP server using server.tool().
    server.tool( initiateDeepResearchName, initiateDeepResearchDescription, initiateDeepResearchSchema, initiateDeepResearchTool );

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/automcp-app/linkd-mcp'

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