Connect
Optimize
Secure
Affinity MCP Server
for AI Agents
Production-ready Affinity MCP server with 34 extensible actions — plus built-in authentication, security, and optimized execution.
Affinity MCP Server
Built by 
StackOne
StackOne 
Coverage
34 Agent Actions
Create, read, update, and delete across Affinity — and extend your agent's capabilities with custom actions.
Authentication
Agent Tool Authentication
Per-user OAuth in one call. Your Affinity MCP server gets session-scoped tokens with zero credentials stored on your infra.
Agent Auth →
Security
Agent Protection
Every Affinity 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 Affinity call.
Tools Discovery →What is the Affinity MCP Server?
A Affinity MCP server lets AI agents read and write Affinity data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Affinity MCP server ships with 34 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 Affinity MCP Tools and Actions
Every action from Affinity's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.
Current Users
- Get Current User
Retrieve information about the currently authenticated user
Opportunities
- List Opportunities
Retrieve a paginated list of all opportunities (deals) in Affinity
Opportunitys
- Create Opportunity
Create a new opportunity (deal) in Affinity
- Get Opportunity
Retrieve a specific opportunity by its ID
- Update Opportunity
Update an existing opportunity in Affinity
- Delete Opportunity
Delete an opportunity from Affinity
Organizations
- Create Organization
Create a new organization (company) in Affinity
- List Organizations
Retrieve a paginated list of all organizations (companies) in Affinity
- Get Organization
Retrieve a specific organization by its ID
- Update Organization
Update an existing organization in Affinity
- Delete Organization
Delete an organization from Affinity
Persons
- Create Person
Create a new person (contact) in Affinity
- List Persons
Retrieve a paginated list of all persons (contacts) in Affinity
- Get Person
Retrieve a specific person by their ID
- Update Person
Update an existing person in Affinity
- Delete Person
Delete a person from Affinity
Lists
- List Lists
Retrieve all lists (pipelines) in Affinity
Get Lists
- Get List
Retrieve a specific list by its ID
Entries
- List List Entries
Retrieve all entries in a specific list
Entrys
- Create List Entry
Add an entity to a list in Affinity
- Get List Entry
Retrieve a specific list entry by its ID
- Delete List Entry
Remove an entry from a list in Affinity
Notes
- Create Note
Create a new note associated with a person, organization, or opportunity
- List Notes
Retrieve notes associated with a specific person, organization, or opportunity
- Get Note
Retrieve a specific note by its ID
- Update Note
Update an existing note in Affinity
- Delete Note
Delete a note from Affinity
Interactions
- List Interactions
Retrieve interactions (emails, meetings, etc.) associated with a person, organization, or opportunity
- Get Interaction
Retrieve a specific interaction by its ID
Fields
- List Fields
Retrieve field metadata definitions available in Affinity
Field Values
- Create Field Value
Set a field value on an entity in Affinity
- List Field Values
Retrieve field values for a specific entity in Affinity
- Update Field Value
Update an existing field value in Affinity
- Delete Field Value
Delete a field value from an entity in Affinity
Set Up Your Affinity MCP Server in Minutes
One endpoint. Any framework. Your agent is talking to Affinity 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>"
]
}
}
}Affinity 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
Affinity MCP Server FAQ
Affinity MCP server vs direct API integration — what's the difference?
A Affinity MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software — backend code calling Affinity. A Affinity 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 Affinity at runtime. StackOne provides both.
How does Affinity authentication work for AI agents?
Affinity 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 Affinity account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via
origin_owner_id.Are Affinity MCP tools vulnerable to prompt injection?
Yes — Affinity 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 Affinity agent and how do I avoid it?
Context bloat happens when Affinity tool schemas and API responses eat your Affinity agent's memory, preventing it from reasoning effectively. A single Affinity 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 Affinity agent can access?
Yes — you can limit which actions your Affinity 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 Affinity MCP server?
Yes — you can create custom agent actions for your Affinity MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research Affinity's API, generate production-ready connector YAML, test against the live API, and validate before you ship.
When should I NOT use a Affinity MCP server?
Skip a Affinity MCP server if your integration is purely software-to-software — direct Affinity 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 Affinity actions at runtime.
What AI frameworks and AI clients does the StackOne Affinity MCP server support?
The StackOne Affinity 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.