Abacus.AI MCP Server
for AI Agents
Connect your AI agent to StackOne's Abacus.AI MCP server and give it 62 MCP tools out of the box. Auth, tool execution, and security all managed.
StackOne 
Coverage
62 Agent Actions
Create, read, update, and delete across Abacus.AI — and extend your agent's capabilities with custom actions.
Authentication
Agent Tool Authentication
Per-user OAuth in one call. Your Abacus.AI MCP server gets session-scoped tokens with zero credentials stored on your infra.
Agent Auth →
Security
Agent Protection
Every Abacus.AI 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 Abacus.AI call.
Tools Discovery →What is the Abacus.AI MCP Server?
A Abacus.AI MCP server lets AI agents read and write Abacus.AI data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Abacus.AI 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 Abacus.AI MCP Tools
Every action from Abacus.AI's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.
Predictions
- Create Batch Prediction
Create a reusable batch prediction job description for a deployment.
- List Batch Predictions
List the batch prediction jobs defined within a project.
- Get Batch Prediction
Retrieve the full description of a single batch prediction job.
Datasets
- List Datasets
List all datasets registered in the organization.
- Get Dataset
Retrieve the full details of a single dataset.
- Delete Dataset
Permanently delete a dataset from the organization.
Deployments
- Create Deployment
Create a deployment that serves a trained model or feature group for predictions.
- List Deployments
List every deployment belonging to a project.
- Get Deployment
Retrieve the full description of a single deployment.
- Update Deployment
Update the mutable properties of an existing deployment.
- Delete Deployment
Permanently delete a deployment without affecting its underlying models.
Feature Groups
- Create Feature Group
Create a new feature group defined by a SQL statement.
- List Feature Groups
Retrieve a paginated list of feature groups in your organization.
- Get Feature Group
Retrieve the details of a single feature group.
- Update Feature Group
Update a feature group's description.
- Delete Feature Group
Permanently delete a feature group.
Feature Group Versions
- Create Feature Group Version
Materialize a new version of a feature group.
- List Feature Group Versions
List the materialized versions of a feature group.
Model Monitors
- List Model Monitors
List the model monitors belonging to a project.
- Get Model Monitor
Retrieve the full description of a single model monitor by its ID.
Models
- List Models
List all models within a project.
- Get Model
Retrieve the full details of a single model.
- Delete Model
Permanently delete a model and all of its versions.
Model Versions
- List Model Versions
List all training versions of a model.
- Get Model Version
Retrieve the full details of a single model version.
Organization Groups
- List Organization Groups
List all permission groups in the organization.
- Get Organization Group
Retrieve the details of a single organization group by its ID.
Pipelines
- Create Pipeline
Create a new pipeline for executing multiple steps as one workflow.
- List Pipelines
List the pipelines for the organization, optionally scoped to one project.
- Get Pipeline
Retrieve the full description of a single pipeline by its ID.
- Delete Pipeline
Permanently delete a pipeline by its ID.
Projects
- Create Project
Create a new project for a given use case.
- List Projects
Retrieve a paginated list of all projects in your organization.
- Get Project
Retrieve the full details of a single project by its ID.
- Delete Project
Permanently delete a project along with its models and deployments.
Refresh Policys
- Create Refresh Policy
Create a refresh policy that re-runs a set of actions on a recurring cron schedule.
- Get Refresh Policy
Retrieve the full details of a single refresh policy by its ID.
- Delete Refresh Policy
Permanently delete a refresh policy by its ID.
Webhooks
- Get Webhook
Retrieve the full configuration of a single webhook by its ID.
- Update Webhook
Update the endpoint, event type, or payload template of an existing webhook.
- Delete Webhook
Permanently delete a webhook by its ID.
Deployment Webhooks
- Create Deployment Webhook
Create a webhook on a deployment that fires on a given event type.
- List Deployment Webhooks
List all webhooks attached to a given deployment.
Other (19)
- Create Dataset Version From File Connector
Create a new dataset version by re-importing from a file connector location.
- Add Feature Group To Project
Attach an existing feature group to a project.
- List Dataset Versions
List all versions of a dataset.
- Get Dataset Schema
Retrieve the column schema of a dataset.
- Get Feature Group Schema
Retrieve the schema (columns) of a feature group.
- Get Model Metrics
Retrieve the evaluation metrics for a model.
- List Organization Users
List all platform users in the organization, including pending invitees.
- Get User
Retrieve the profile of the currently authenticated user.
- List API Keys
List the API keys for the current user's organization.
- List Project Feature Groups
List the feature groups attached to a project.
- List Refresh Policies
List the organization's refresh policies, optionally narrowed to those attached to specific resources.
- Remove Feature Group From Project
Detach a feature group from a project.
- Start Batch Prediction
Start a new run (version) of an existing batch prediction job.
- Start Deployment
Restart a deployment that was previously stopped or suspended.
- Stop Deployment
Stop a running deployment to suspend prediction serving.
- Train Model
Create and start training a new model in a project.
- Run Pipeline
Trigger a run of a pipeline, optionally passing in argument values.
- Rename Project
Rename an existing project.
- Run Refresh Policy
Force an immediate run of a refresh policy outside its normal schedule.
Set Up Your Abacus.AI MCP Server in Minutes
One endpoint. Any framework. Your agent is talking to Abacus.AI 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>"
]
}
}
}Check More developer MCP Servers
113+ actions
62+ actions
61+ actions
54+ actions
50+ actions
43+ actions
31+ actions
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
Abacus.AI MCP Server FAQ
Does StackOne have a Abacus.AI MCP server?
Abacus.AI MCP server vs direct API integration — what's the difference?
How does Abacus.AI authentication work for AI agents?
origin_owner_id.Are Abacus.AI MCP tools vulnerable to prompt injection?
What is the context bloat of a Abacus.AI agent and how do I avoid it?
Can I limit which actions my Abacus.AI agent can access?
Can I create custom agent actions for my Abacus.AI MCP server?
When should I NOT use a Abacus.AI MCP server?
What AI frameworks and AI clients does the StackOne Abacus.AI MCP server support?
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.