Connect
Optimize
Secure
Live 40 Actions
JobScore MCP Server
for AI Agents
Connect your AI agent to StackOne's JobScore MCP server and give it 40 MCP tools out of the box. Auth, tool execution, and security all managed.
JobScore MCP Server
Built by 
StackOne
StackOne 
Coverage
40 Agent Actions
Create, read, update, and delete across JobScore — and extend your agent's capabilities with custom actions.
Authentication
Agent Tool Authentication
Per-user OAuth in one call. Your JobScore MCP server gets session-scoped tokens with zero credentials stored on your infra.
Agent Auth →
Security
Agent Protection
Every JobScore tool response scanned for prompt injection in milliseconds — 88.7% accuracy, all running on CPU.
Prompt Injection Defense →
Performance
Max Agent Context. Min Cost.
Free up to 96% of your agent's context window to enhance reasoning and reduce cost, on every JobScore call.
Tools Discovery →What is the JobScore MCP Server?
A JobScore MCP server lets AI agents read and write JobScore data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's JobScore MCP server ships with 40 pre-built actions, fully extensible via the Connector Builder — plus managed authentication, prompt injection defense, observability, and agent execution runtime. Connect it from MCP clients like Claude Desktop, Claude Code, Cursor, Goose, and VS Code, or from agent frameworks like OpenAI Agents SDK, LangChain, and Vercel AI SDK.
All JobScore MCP Tools
Every action from JobScore's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.
Candidates
- Create Candidate
Create a new candidate profile with contact details, source information, and optionally an initial job application.
- List Candidates
Retrieve a paginated list of candidates with optional filtering by job, status, stage, tags, and date ranges.
- Get Candidate
Retrieve detailed profile information for a specific candidate by their ID.
- Update Candidate
Update an existing candidate's profile information including contact details, tags, source, and employment history.
Applications
- Create Application
Create a new job application for an existing candidate.
- List Applications
Retrieve a paginated list of job applications for a specific candidate.
- Get Application
Retrieve detailed information for a specific job application by its ID.
- Update Application
Update the status or stage of an existing job application.
Jobs
- List Jobs
Retrieve a paginated list of jobs with optional filtering and sorting.
- Get Job
Retrieve detailed information for a specific job posting by its ID.
Documents
- Upload Document
Upload a document and attach it to a candidate's profile.
- List Documents
Retrieve a paginated list of documents attached to a specific candidate.
- Get Document
Retrieve metadata for a specific document by its ID.
- Download Document
Download the file content of a specific document.
Notes
- Create Note
Create a new note on a candidate's profile.
- List Notes
Retrieve a paginated list of notes for a specific candidate.
- Get Note
Retrieve a specific note by its ID.
Offers
- List Offers
Retrieve a paginated list of all offers across all candidates.
- Get Offer
Retrieve detailed information for a specific offer by its ID.
Tasks
- Create Task
Create a new task or meeting for a candidate.
- List Tasks
Retrieve a paginated list of all tasks across the account.
- Get Task
Retrieve detailed information for a specific task by its ID.
Candidate Tasks
- List Candidate Tasks
Retrieve all tasks associated with a specific candidate.
- Get Candidate Task
Retrieve a specific task for a candidate by candidate ID and task ID.
Users
- List Users
Retrieve all users in the JobScore account
- Get User
Retrieve a single user by ID
Departments
- Create Department
Create a new department in JobScore
- List Departments
Retrieve all departments in the JobScore account
- Get Department
Retrieve a single department by ID
Locations
- List Locations
Retrieve all locations in the JobScore account
- Get Location
Retrieve a single location by ID
Candidate EEOs
- List Candidate EEO
Retrieve EEO data for candidates in the JobScore account
- Get Candidate EEO
Retrieve EEO data for a specific candidate
Other (7)
- Add Candidate Tags
Add one or more tags to a candidate's profile.
- List Candidate Offers
Retrieve all offers associated with a specific candidate.
- Get Application Offer
Retrieve the offer associated with a specific job application.
- List Tags
Retrieve a paginated list of all candidate tags defined in the account.
- Get Current User
Retrieve the currently authenticated user
- List Disposition Codes
Retrieve all disposition codes in the JobScore account
- List Workflow Stages
Retrieve all workflow stages for a specific job
JobScore AI Agent Use Cases
Connect your AI agent to JobScore and help your team scale the recruiting operations they run by hand today.
Job Posting Distribution
Use StackOne to connect your AI agent to your ATS and job boards to automate job posting distribution.
View Reference Check Automation
Use StackOne to connect your AI agent to your ATS, survey tools, and messaging systems to automate reference checks.
View Offer Letter Generation
Use StackOne to connect your AI agent to your ATS, HRIS, and document management tools to automate offer letter generation.
ViewSet Up Your JobScore MCP Server in Minutes
One endpoint. Any framework. Your agent is talking to JobScore in under 10 lines of code.
Agent Frameworks
JSON{
"mcpServers": {
"stackone": {
"command": "npx",
"args": [
"-y",
"mcp-remote@latest",
"https://api.stackone.com/mcp?x-account-id=<account_id>",
"--header",
"Authorization: Basic <YOUR_BASE64_TOKEN>"
]
}
}
}Platform Resources
MCP Code Mode: Keeping Tool Responses Out of Agent Context
Anthropic's code_execution processes data already in context. Custom MCP code mode keeps raw tool responses in a sandbox. 14K tokens vs 500.
11 min
Comparing BM25, TF-IDF, and Hybrid Search for MCP Tool Discovery
Benchmarking BM25, TF-IDF, and hybrid search for MCP tool discovery across 916 tools. The 80/20 TF-IDF/BM25 hybrid hits 21% Top-1 accuracy in under 1ms.
10 min
Indirect Prompt Injection Defense for MCP Tools: A Technical Guide
MCP tools that read emails, CRM records, and tickets are indirect prompt injection vectors. Here's how we built a two-tier defense that scans tool results in ~11ms.
12 min
MCP vs A2A: Architecture, Security, and When to Use Each
MCP vs A2A: what each protocol standardizes, how they differ, their shared security risks including indirect prompt injection, and when to use one, both, or a hybrid architecture.
12 min
MCP vs API: What 200+ Connector Builds Taught Us
MCP wraps APIs, it doesn't replace them. After building 200+ connectors that serve both, here's when each approach wins.
14 min read
JobScore MCP Server FAQ
Does StackOne have a JobScore MCP server?
Yes. StackOne offers a hosted JobScore MCP server with 40 pre-built actions, and every action is tested and QA'd by StackOne. Connect it to Claude, Cursor, and any other MCP client, or to any agent framework through the AI Action SDK. It ships with managed agent authentication, prompt injection defense, and tool discovery with server-side execution that preserve your agent's context window and keep reasoning performance.
JobScore MCP server vs direct API integration — what's the difference?
A JobScore MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software — backend code calling JobScore. A JobScore MCP server is for AI agents — MCP clients like Claude and Cursor, plus framework agents built with OpenAI, LangChain, or Vercel AI — discovering and calling JobScore at runtime. StackOne provides both.
How does JobScore authentication work for AI agents?
JobScore authentication for AI agents works through a StackOne Connect Session. Create one via the dashboard or the SDK — you get an auth link and ready-to-paste config for Claude Desktop, Cursor, and other MCP clients. Your user authenticates their own JobScore account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via
origin_owner_id.Are JobScore MCP tools vulnerable to prompt injection?
Yes — JobScore MCP tools can be vulnerable to indirect prompt injection. Any tool that reads user-written content — documents, messages, tickets, records, or free-text fields — is a potential vector. StackOne Defender scans every tool response before it enters the agent's context — regex patterns in ~1ms, then a MiniLM classifier in ~4ms. 88.7% accuracy, CPU-only.
What is the context bloat of a JobScore agent and how do I avoid it?
Context bloat happens when JobScore tool schemas and API responses eat your JobScore agent's memory, preventing it from reasoning effectively. A single JobScore query can return a massive JSON response, and connecting multiple tools compounds the problem. Tools Discovery and Code Mode reduce context bloat — loading only relevant tools per query and keeping raw responses out of the agent's context.
Can I limit which actions my JobScore agent can access?
Yes — you can limit which actions your JobScore agent can access directly from the StackOne dashboard. Toggle actions on or off, or restrict them to specific accounts, with no code changes to your agent. Session tokens can be scoped to exact actions so if one leaks, exposure stays contained.
Can I create custom agent actions for my JobScore MCP server?
Yes — you can create custom agent actions for your JobScore MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research JobScore's API, generate production-ready connector YAML, test against the live API, and validate before you ship.
When should I NOT use a JobScore MCP server?
Skip a JobScore MCP server if your integration is purely software-to-software — direct JobScore API integration is simpler when no AI agent is involved. For deterministic, compliance-critical operations (financial transactions, regulatory reporting), direct API gives you predictable behavior without agent-driven decision-making. MCP shines when AI agents need to dynamically discover and call JobScore actions at runtime.
What AI frameworks and AI clients does the StackOne JobScore MCP server support?
The StackOne JobScore MCP server supports both. MCP clients (paste-and-go apps): Claude Desktop, Claude Code, Cursor, VS Code, Goose. Agent frameworks (code SDKs you build with): OpenAI Agents SDK, Anthropic, Vercel AI, Google ADK, CrewAI, Pydantic AI, LangChain, LangGraph, Azure AI Foundry.
Put your AI agents to work
All the tools you need to build and scale AI agent integrations, with best-in-class connectivity, execution, and security.