Connect
Optimize
Secure
The #1 agentic semantic tool search: 91.6% first-try accuracy on S1 Search Bench • Explore Tool Discovery →
Connect your AI agent to StackOne's Spark Hire MCP server and give it 47 MCP tools out of the box. Auth, tool execution, and security all managed.
Coverage
Create, read, update, and delete across Spark Hire — and extend your agent's capabilities with custom actions.
Authentication
Per-user OAuth in one call. Your Spark Hire MCP server gets session-scoped tokens with zero credentials stored on your infra.
Agent Auth →Security
Every Spark Hire tool response scanned for prompt injection in milliseconds — 88.7% accuracy, all running on CPU.
Prompt Injection Defense →Performance
Free up to 96% of your agent's context window to enhance reasoning and reduce cost, on every Spark Hire call.
Tools Discovery →A Spark Hire MCP server lets AI agents read and write Spark Hire data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Spark Hire MCP server ships with 47 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.
Every action from Spark Hire's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.
Create a candidate assessment item
Delete a candidate assessment item
Create a job
Retrieve a job
Update a job
Delete a job
Create a job assessment
Retrieve a job assessment
Update a job assessment
Delete a job assessment
Create a job assessment link
Retrieve a job assessment link
Update a job assessment link
List share links
Retrieve a share link
Update a share link
Batch delete share links
Delete a share link
Create an interview share link
Retrieve an interview share link
Update an interview share link
Delete an interview share link
List question sets
Show a question set
List behavioral profiles
Retrieve a behavioral profile
List reference check surveys
Retrieve a reference check survey
Create advanced share links
Add interviews to a share link
Add or remove an interview on multiple advanced share links
List assessment items
Get a predictive assessment report
List jobs
List job assessments
Get authenticated partner client info
Batch cancel candidate assessment items
Batch reschedule candidate assessment items
Remove interviews from a share link
Show a candidate assessment item
Cancel a candidate assessment item
Reschedule a candidate assessment item
Activate a job
Deactivate a job
Activate a job assessment link
Deactivate a job assessment link
Destroy a job assessment link
Connect your AI agent to Spark Hire and help your team scale the recruiting operations they run by hand today.
Use StackOne to connect your AI agent to your ATS and job boards to automate job posting distribution.
ViewUse StackOne to connect your AI agent to your ATS, survey tools, and messaging systems to automate reference checks.
ViewUse StackOne to connect your AI agent to your ATS, HRIS, and document management tools to automate offer letter generation.
ViewOne endpoint. Any framework. Your agent is talking to Spark Hire in under 10 lines of code.
Agent Frameworks
{
"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>"
]
}
}
}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
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
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: 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 wraps APIs, it doesn't replace them. After building 200+ connectors that serve both, here's when each approach wins.
14 min read
origin_owner_id.All the tools you need to build and scale AI agent integrations, with best-in-class connectivity, execution, and security.