Connect
Optimize
Secure
Live 32 Actions
softgarden MCP Server
for AI Agents
Connect your AI agent to StackOne's softgarden MCP server and give it 32 MCP tools out of the box. Auth, tool execution, and security all managed.
softgarden MCP Server
Built by 
StackOne
StackOne 
Coverage
32 Agent Actions
Create, read, update, and delete across softgarden — and extend your agent's capabilities with custom actions.
Authentication
Agent Tool Authentication
Per-user OAuth in one call. Your softgarden MCP server gets session-scoped tokens with zero credentials stored on your infra.
Agent Auth →
Security
Agent Protection
Every softgarden 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 softgarden call.
Tools Discovery →What is the softgarden MCP Server?
A softgarden MCP server lets AI agents read and write softgarden data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's softgarden MCP server ships with 32 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 softgarden MCP Tools
Every action from softgarden's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.
Applications
- List Applications
List all applications belonging to the authenticated applicant.
- Get Application
Retrieve a single application by its ID.
Attachments
- Upload Attachment
Upload a file attachment to an application.
- Delete Attachment
Delete an attachment from an application.
Jobboards
- List Jobboards
Retrieve all configured jobboards (channels) for the tenant.
- Get Jobboard
Retrieve details of a single jobboard channel by ID.
Other (26)
- Create Applicant Account
Register a new applicant account on the softgarden tenant.
- Upload Profile Picture
Upload an applicant profile picture to an application.
- Upload CV
Upload a CV (résumé) to an application.
- List Application Sources
Retrieve the configured application sources for the tenant.
- Get Application ID For Job
Retrieve the application ID for an applicant's application to a specific job.
- Get Attachment Metadata
Retrieve metadata for an attachment by ID.
- Get Attachment Content
Download the actual file content of an attachment.
- Get Catalog Values
Resolve catalog values for a specific catalog type.
- Search Jobs In Channel
List or search the jobs published in a specific jobboard channel.
- List Posting Channels (v3)
List all posting channels configured for the tenant (Frontend API v3).
- List Jobs Of Channel (v3)
List all jobs published in a specific posting channel.
- Get Job By ID (v3)
Retrieve a single job by its softgarden internal job ID, scoped to a channel.
- Get Job By Project Number (v3)
Retrieve a single job by its project number (the human-readable identifier displayed on the career site), scoped to a channel.
- Get Job Details HTML
Retrieve a job posting's details as a rendered HTML string.
- Get Job Name
Retrieve a job posting's name as a plain string.
- Get Job Prescreening Questions
Retrieve the mandatory prescreening questions for a job.
- Update Application Information
Update applicant information on a draft application (PUT — replaces the entire ApplicationProfileDTO).
- Delete Draft Application
Delete an unsubmitted (draft) application.
- Check Email Existence
Check whether an email address is already registered as an applicant account.
- Check Username Existence
Check whether a username is already registered as an applicant account.
- Withdraw Application
Withdraw a submitted application.
- Check Job Applied
Check whether the authenticated applicant has applied to a job.
- Start Application
Create a draft application for a job posting.
- Store Application Information
Save applicant information to a draft application.
- Submit Application
Finalize and submit a completed application.
- Check Application Exists For Job
Check whether the authenticated applicant has an application for the given job.
softgarden AI Agent Use Cases
Connect your AI agent to softgarden 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 softgarden MCP Server in Minutes
One endpoint. Any framework. Your agent is talking to softgarden 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
softgarden MCP Server FAQ
Does StackOne have a softgarden MCP server?
Yes. StackOne offers a hosted softgarden MCP server with 32 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.
softgarden MCP server vs direct API integration — what's the difference?
A softgarden MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software — backend code calling softgarden. A softgarden 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 softgarden at runtime. StackOne provides both.
How does softgarden authentication work for AI agents?
softgarden 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 softgarden account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via
origin_owner_id.Are softgarden MCP tools vulnerable to prompt injection?
Yes — softgarden 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 softgarden agent and how do I avoid it?
Context bloat happens when softgarden tool schemas and API responses eat your softgarden agent's memory, preventing it from reasoning effectively. A single softgarden 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 softgarden agent can access?
Yes — you can limit which actions your softgarden 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 softgarden MCP server?
Yes — you can create custom agent actions for your softgarden MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research softgarden's API, generate production-ready connector YAML, test against the live API, and validate before you ship.
When should I NOT use a softgarden MCP server?
Skip a softgarden MCP server if your integration is purely software-to-software — direct softgarden 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 softgarden actions at runtime.
What AI frameworks and AI clients does the StackOne softgarden MCP server support?
The StackOne softgarden 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.