Connect
Optimize
Secure
Live 29 Actions
Flatchr MCP Server
for AI Agents
Connect your AI agent to StackOne's Flatchr MCP server and give it 29 MCP tools out of the box. Auth, tool execution, and security all managed.
Flatchr MCP Server
Built by 
StackOne
StackOne 
Coverage
29 Agent Actions
Create, read, update, and delete across Flatchr — and extend your agent's capabilities with custom actions.
Authentication
Agent Tool Authentication
Per-user OAuth in one call. Your Flatchr MCP server gets session-scoped tokens with zero credentials stored on your infra.
Agent Auth →
Security
Agent Protection
Every Flatchr 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 Flatchr call.
Tools Discovery →What is the Flatchr MCP Server?
A Flatchr MCP server lets AI agents read and write Flatchr data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Flatchr MCP server ships with 29 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 Flatchr MCP Tools
Every action from Flatchr's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.
Vacancys
- Create Vacancy
Create a new vacancy (job ad) for your company.
- Retrieve Vacancy
Get a single vacancy by its ID.
Candidates
- Search Candidates
Searches candidates (applicants) for a company in Flatchr using filters such as name, email, pipeline stage (column), job offer (vacancy), hired status and a creation date range.
- Move Candidate
Moves a candidate to a different column (pipeline stage) within a vacancy in Flatchr.
Comments
- Create Comment
Create a comment on a Flatchr applicant.
- Retrieve Comments
Retrieve the comments left on a Flatchr applicant.
- Delete Comment
Delete a comment from a Flatchr applicant.
Tasks
- Create Task
Create a recruitment task for the configured company.
- Retrieve Tasks
List the recruitment tasks for the configured company.
Other (20)
- Create Candidate (JSON)
Create a candidate application against a job vacancy using a JSON payload.
- Create Candidate (Custom)
Create a candidate application against a job vacancy using a custom payload.
- Create Candidate (Test)
Test candidate creation against a job vacancy without creating a real record.
- Retrieve Vacancies
List all vacancies (job ads) for your company.
- Retrieve Active Vacancies
List the active, publicly published vacancies for your company career site.
- Retrieve Candidate CV
Retrieves the downloadable CV document of a candidate in Flatchr using the unique CV key and file extension.
- Retrieve Messages
Retrieve the messages exchanged with a Flatchr applicant.
- Retrieve Company Tags
List the tags configured for the company.
- List Members
List the members (users) belonging to the company.
- List Columns
Retrieve the columns (pipeline stages) configured for a company in Flatchr.
- List Business Sectors
Retrieve the list of business sectors (industry categories) used in Flatchr.
- List Channels
List the job board channels available for distributing vacancies in Flatchr.
- List Channel Job Categories
List the job categories available for a specific channel in Flatchr.
- List Contract Types
List the contract types reference data available in Flatchr.
- List Education Levels
List the available education levels reference data from Flatchr.
- Update Candidate Meta Information
Adds or updates meta information on an existing candidate (applicant) in Flatchr, identified by their email reference.
- Archive Candidate
Archives (removes) a candidate from a vacancy in Flatchr.
- Close Task
Close (mark as done) a recruitment task for the configured company.
- Display Candidate Tags
Retrieve the tags attached to a Flatchr candidate.
- Fill A Candidate Tag
Add a tag (trait) to a Flatchr candidate.
Flatchr AI Agent Use Cases
Connect your AI agent to Flatchr 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 Flatchr MCP Server in Minutes
One endpoint. Any framework. Your agent is talking to Flatchr 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
Flatchr MCP Server FAQ
Does StackOne have a Flatchr MCP server?
Yes. StackOne offers a hosted Flatchr MCP server with 29 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.
Flatchr MCP server vs direct API integration — what's the difference?
A Flatchr MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software — backend code calling Flatchr. A Flatchr 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 Flatchr at runtime. StackOne provides both.
How does Flatchr authentication work for AI agents?
Flatchr 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 Flatchr account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via
origin_owner_id.Are Flatchr MCP tools vulnerable to prompt injection?
Yes — Flatchr 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 Flatchr agent and how do I avoid it?
Context bloat happens when Flatchr tool schemas and API responses eat your Flatchr agent's memory, preventing it from reasoning effectively. A single Flatchr 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 Flatchr agent can access?
Yes — you can limit which actions your Flatchr 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 Flatchr MCP server?
Yes — you can create custom agent actions for your Flatchr MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research Flatchr's API, generate production-ready connector YAML, test against the live API, and validate before you ship.
When should I NOT use a Flatchr MCP server?
Skip a Flatchr MCP server if your integration is purely software-to-software — direct Flatchr 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 Flatchr actions at runtime.
What AI frameworks and AI clients does the StackOne Flatchr MCP server support?
The StackOne Flatchr 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.