Connect
Optimize
Secure
Live 62 Actions
Fountain MCP Server
for AI Agents
Connect your AI agent to StackOne's Fountain MCP server and give it 62 MCP tools out of the box. Auth, tool execution, and security all managed.
Fountain MCP Server
Built by 
StackOne
StackOne 
Coverage
62 Agent Actions
Create, read, update, and delete across Fountain — and extend your agent's capabilities with custom actions.
Authentication
Agent Tool Authentication
Per-user OAuth in one call. Your Fountain MCP server gets session-scoped tokens with zero credentials stored on your infra.
Agent Auth →
Security
Agent Protection
Every Fountain 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 Fountain call.
Tools Discovery →What is the Fountain MCP Server?
A Fountain MCP server lets AI agents read and write Fountain data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Fountain MCP server ships with 62 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 Fountain MCP Tools
Every action from Fountain's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.
Applicants
- Create Applicant
Create a new applicant
- List Applicants
Retrieve a list of applicants
- Get Applicant
Get detailed information for a specific applicant
- Update Applicant
Update applicant information
- Delete Applicant
Delete an applicant
Applicant Files
- Upload Applicant File
Upload a file to S3 for an applicant
- Get Applicant Files
Get files attached to an applicant
Company Attributes
- Create Company Attribute
Create a company attribute
- List Company Attributes
List all company attributes
- Get Company Attribute
Get a specific company attribute by type
Hiring Goals
- Create Hiring Goal
Create a new hiring goal
- List Hiring Goals
List all hiring goals
- Update Hiring Goal
Update a hiring goal
- Delete Hiring Goal
Delete a hiring goal
Location Groups
- Create Location Group
Create a new location group
- List Location Groups
List all location groups
- Get Location Group
Retrieve a specific location group
- Update Location Group
Update a location group
Locations
- Create Location
Create a new location
- List Locations
List all locations
- Get Location
Retrieve a specific location
- Update Location
Update a location
- Delete Location
Delete a location
Applicant Notes
- Create Applicant Note
Create a note for an applicant
- Get Applicant Notes
Get notes for an applicant
- Update Applicant Note
Update a note for an applicant
- Delete Applicant Note
Delete a note from an applicant
Openings
- Create Opening
Create a new job opening
- List Openings
Retrieve a list of job openings
- Get Opening
Retrieve details of a specific job opening
- Update Opening
Update a job opening
- Delete Opening
Delete a job opening
Available Slots
- Create Available Slot
Create a new available interview slot
- List Available Slots
List available interview slots for a stage
Positions
- Create Position
Create a new position
- List Positions
List all positions
- Get Position
Retrieve a specific position
- Update Position
Update a position
- Delete Position
Delete a position
Users
- Create User
Create a user
- List Users
List all users in the account
- Update User
Update a user
- Delete User
Delete a user
Webhook Settings
- Create Webhook Setting
Create a new webhook setting
- List Webhook Settings
List all webhook settings
- Get Webhook Setting
Retrieve a specific webhook setting
- Delete Webhook Setting
Delete a webhook setting
Hire Workers
- List Hire Workers
List posthire workers
- Get Hire Worker
Get details for a specific posthire worker
- Update Hire Worker
Update a posthire worker
Other (12)
- List Labels For Applicant
List labels assigned to an applicant
- List Stage Labels
List all available labels in a stage
- List Opening Stages
List all stages in a specific opening
- Get Stage
Retrieve details of a specific stage
- List Roles
List all user roles available in the account
- List Shifts
List shifts
- List Archived Reasons
List all reasons available for archiving applicants
- List Rejection Reasons
List all reasons available for rejecting applicants
- Get User Opening Access
Get openings a user has access to
- Update Applicant Label
Update a label for an applicant
- Advance Applicant
Advance an applicant to the next stage
- Approve Applicant Documents
Approve applicant documents
Fountain AI Agent Use Cases
Connect your AI agent to Fountain 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 Employee Onboarding
Use StackOne to connect your AI agent to your HRIS, identity management, and LMS to automate employee onboarding.
ViewSet Up Your Fountain MCP Server in Minutes
One endpoint. Any framework. Your agent is talking to Fountain 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
Fountain MCP Server FAQ
Does StackOne have a Fountain MCP server?
Yes. StackOne offers a hosted Fountain MCP server with 62 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.
Fountain MCP server vs direct API integration — what's the difference?
A Fountain MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software — backend code calling Fountain. A Fountain 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 Fountain at runtime. StackOne provides both.
How does Fountain authentication work for AI agents?
Fountain 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 Fountain account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via
origin_owner_id.Are Fountain MCP tools vulnerable to prompt injection?
Yes — Fountain 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 Fountain agent and how do I avoid it?
Context bloat happens when Fountain tool schemas and API responses eat your Fountain agent's memory, preventing it from reasoning effectively. A single Fountain 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 Fountain agent can access?
Yes — you can limit which actions your Fountain 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 Fountain MCP server?
Yes — you can create custom agent actions for your Fountain MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research Fountain's API, generate production-ready connector YAML, test against the live API, and validate before you ship.
When should I NOT use a Fountain MCP server?
Skip a Fountain MCP server if your integration is purely software-to-software — direct Fountain 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 Fountain actions at runtime.
What AI frameworks and AI clients does the StackOne Fountain MCP server support?
The StackOne Fountain 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.