Candidate MCP Server Library

@jhgaylor

リポジトリ

基本情報

カテゴリ

開発者ツール

ライセンス

MIT

トランスポート

stdio

作者

jhgaylor

Candidate MCP Server Library について

A Model Context Protocol (MCP) server library that gives LLMs access to information about a candidate.

#typescript #ai #mcp

Candidate MCP Server Library の設定

標準の設定はありません

このサーバーの README には解析可能な MCP 設定ブロックが含まれていません。インストール手順はリポジトリをご確認ください。

リポジトリ

Candidate MCP Server Library のツール

Returns the candidate's resume content as text

Returns the URL to the candidate's resume

Returns the candidate's LinkedIn profile URL

Returns the candidate's GitHub profile URL

Returns the candidate's personal website URL

Returns the content from the candidate's personal website

Sends an email to the candidate (requires Mailgun configuration)

概要

What is Candidate MCP Server Library?

A Model Context Protocol (MCP) server library that gives LLMs access to information about a candidate. It is designed to be integrated into other applications, not run as a standalone service, and provides resources and tools for retrieving candidate resume content, URLs, and contact details.

How to use Candidate MCP Server Library?

Install via npm install @jhgaylor/candidate-mcp-server. Import createServer, configure with serverConfig and candidateConfig, then connect to an MCP transport (Stdio, Streamable HTTP, or Express). The library provides resource URIs like candidate-info://resume-text and tools like get_resume_text and contact_candidate.

Key features of Candidate MCP Server Library

Library-first design for easy application integration
Modular resource system extensible with custom data
Full Model Context Protocol specification implementation
Supports STDIO, Streamable HTTP, and Express transports
TypeScript for type safety and developer experience
Minimal dependencies

Use cases of Candidate MCP Server Library

Allowing LLMs to retrieve a candidate's resume text during an interview workflow
Providing LLMs with links to a candidate's LinkedIn, GitHub, or personal website
Enabling LLMs to contact a candidate via email when configured with Mailgun

よくある質問

What is the purpose of this server?

It gives LLMs access to candidate information (resume, profile URLs, website content) through the Model Context Protocol, intended as a library to embed in other applications.

How do I configure candidate information?

Pass a `candidateConfig` object to `createServer` containing fields like `name`, `email`, `resumeUrl`, and other candidate properties. The email is required for the `contact_candidate` tool.

What dependencies and runtime are required?

Node.js 20+ and npm or yarn. No other required runtime dependencies are mentioned beyond the MCP SDK and Mailgun (optional).

Does this server support multiple transports?

Yes. The README demonstrates Stdio, Streamable HTTP, and Express transports. Transport choice depends on your integration environment.

Can I extend the server with custom resources or tools?

Yes. The library is designed to be extended. Examples show adding custom resource classes and registering custom tools with Zod schema validation.

「開発者ツール」の他のコンテンツ

JiCo for Jira & Confluence – PII-redacting MCP server with Human-in-the-Loop

drkv-com

JiCo for Jira & Confluence: local MCP server for Jira Data Center - redacts personal data before the AI model, holds every write for approval

Eddyter AI Rich Text Editor MCP

EddyterAI

Set up and manage the Eddyter AI rich text editor by talking to your AI agent — for Claude, Cursor, Codex and other MCP tools. A Model Context Protocol server that lets AI tools add Eddyter to a React, Next.js, Vite or R

OrangePro

Aamir Siddiqui

OrangePro local-first CLI + MCP server for behavior mapping, grounded test generation, and dynamic proof.

Modelglass

Modelglass turns "which model should I use?" into a lookup instead of a guess. Seven tools give your agent live pricing across image, language, video, and audio models. Sourced and versioned, not scraped once and forgott

Moxie Docs

Jackalope-Dev

Automated codebase documentation for GitHub: searchable docs, MCP context for AI agents, doc drift detection, and Friday Cleanup PRs.