Connect
Optimize
Secure
Veremark MCP Server
for AI Agents
Production-ready Veremark MCP server with 22 extensible actions — plus built-in authentication, security, and optimized execution.
Veremark MCP Server
Built by 
StackOne
StackOne 
Coverage
22 Agent Actions
Create, read, update, and delete across Veremark — and extend your agent's capabilities with custom actions.
Authentication
Agent Tool Authentication
Per-user OAuth in one call. Your Veremark MCP server gets session-scoped tokens with zero credentials stored on your infra.
Agent Auth →
Security
Agent Protection
Every Veremark 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 Veremark call.
Tools Discovery →What is the Veremark MCP Server?
A Veremark MCP server lets AI agents read and write Veremark data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Veremark MCP server ships with 22 pre-built actions, fully extensible via the Connector Builder — plus managed authentication, prompt injection defense, and optimized agent context. Connect it from MCP clients like Claude Desktop, Cursor, and VS Code, or from agent frameworks like OpenAI Agents SDK, LangChain, and Vercel AI SDK.
All Veremark MCP Tools and Actions
Every action from Veremark's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.
Candidates
- List Candidates
Retrieve a list of all candidates in your Veremark account.
- Delete Candidate
Soft delete a specific candidate from your Veremark account by their GUID.
Checks
- List Checks
Retrieve a list of all available background checks, optionally filtered by country.
Criterias
- Create Criteria
Create a new background check criteria template with specified checks and country.
- List Criteria
Retrieve a list of all background check criteria templates in your Veremark account.
- Get Criteria
Retrieve details of a specific criteria template by its GUID.
- Delete Criteria
Delete a specific criteria template by its GUID.
Documents
- Upload Document
Upload a document to Veremark as multipart/form-data for use in background check verification.
- Get Document
Download the binary content of a specific document by its GUID.
Requests
- Create Request
Create a new background check request for a candidate using specified criteria.
- List Requests
Retrieve a list of all background check requests, optionally filtered by status change date.
- Get Request
Retrieve details of a specific background check request by its GUID.
- Delete Request
Delete a background check request by its GUID. Only requests in expired, requested, or draft status can be deleted.
Check Status
- Update Check Status
Update the status of a specific check within a background check request.
Magic Links
- Create Magic Links
Create time-limited magic links for accessing the report of a specific background check request.
Force Check Status
- Force Check Status
Force a specific check status transition within a background check request using the restricted endpoint.
Full Reports
- Get Full Report
Download the full PDF report for a background check request.
Check Reports
- Get Check Report
Download the PDF report for a specific individual check within a background check request.
Users
- Create User
Create a new user in your Veremark account with a specified role.
- List Users
Retrieve a list of all external users in your Veremark account.
- Get User
Retrieve details of a specific user in your Veremark account by their GUID.
- Delete User
Delete a specific user from your Veremark account by their GUID.
Set Up Your Veremark MCP Server in Minutes
One endpoint. Any framework. Your agent is talking to Veremark in under 10 lines of code.
MCP Clients
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>"
]
}
}
}More Recruiting MCP Servers
JobAdder
246+ actions
Vincere
206+ actions
SmartRecruiters
164+ actions
Ashby
137+ actions
Factorial
127+ actions
HiBob
123+ actions
HiBob (with Webhooks)
123+ actions
Veremark MCP Server 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
Veremark MCP Server FAQ
Veremark MCP server vs direct API integration — what's the difference?
A Veremark MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software — backend code calling Veremark. A Veremark 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 Veremark at runtime. StackOne provides both.
How does Veremark authentication work for AI agents?
Veremark 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 Veremark account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via
origin_owner_id.Are Veremark MCP tools vulnerable to prompt injection?
Yes — Veremark 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 Veremark agent and how do I avoid it?
Context bloat happens when Veremark tool schemas and API responses eat your Veremark agent's memory, preventing it from reasoning effectively. A single Veremark 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 Veremark agent can access?
Yes — you can limit which actions your Veremark 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 Veremark MCP server?
Yes — you can create custom agent actions for your Veremark MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research Veremark's API, generate production-ready connector YAML, test against the live API, and validate before you ship.
When should I NOT use a Veremark MCP server?
Skip a Veremark MCP server if your integration is purely software-to-software — direct Veremark 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 Veremark actions at runtime.
What AI frameworks and AI clients does the StackOne Veremark MCP server support?
The StackOne Veremark 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.