Skip to main content Announcing Tool Policies: AI agent permissions down to the field Read the announcement
Live 27 Actions

Keeper MCP Server
for AI Agents

Connect your AI agent to StackOne's Keeper MCP server and give it 27 MCP tools out of the box. Auth, tool execution, and security all managed.

Keeper logo
Keeper MCP Server
Built by StackOne StackOne
DrataGPLocalyzeFlipMindtoolsScreenloop

Coverage

27 Agent Actions

Agents can read, write and delete in Keeper. Extend your agent's capabilities with custom actions.

Authentication

Agent Tool Authentication

Per-user OAuth in one call. Your Keeper MCP server gets session-scoped tokens with zero credentials stored on your infra.

Agent Auth →

Security

Agent Protection

Every Keeper tool response scanned for prompt injection in milliseconds, with 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 Keeper call.

Tools Discovery →

What is the Keeper MCP Server?

A Keeper MCP server lets AI agents read and write Keeper data through the Model Context Protocol, Anthropic's open standard for connecting LLMs to external tools. StackOne's Keeper MCP server ships with 27 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 Keeper MCP Tools

Every StackOne action for Keeper, ready for your agent. Read, write and delete, scoped to exactly what you need.

Security Benchmarks

  • Get Security Benchmarks

    Get the enterprise's security benchmark results.

  • Set Security Benchmarks

    Update the enterprise's security benchmark settings.

Unified Groups

  • List Unified Groups

    List unified groups (Keeper teams) in the connected Keeper node.

  • Get Unified Group

    Get a unified Keeper group (team) by ID.

Unified Users

  • List Unified Users

    List unified users in the connected Keeper node.

  • Get Unified User

    Get a unified Keeper user by ID.

Teams

  • Create Team

    Create a team in the connected Keeper node through the SCIM API.

  • List Teams

    List teams in the connected Keeper node through the SCIM API.

  • Get Team

    Get a single Keeper team by team UID.

  • Delete Team

    Delete a team from the connected Keeper node through the SCIM API.

Users

  • Create User

    Create a user in the connected Keeper node through the SCIM API.

  • List Users

    List users in the connected Keeper node through the SCIM API.

  • Get User

    Get a single Keeper user by SCIM user ID.

  • Update User

    Replace a user in the connected Keeper node through the SCIM API (full replacement).

Other (13)

  • List Audit Events

    List enterprise audit events from Keeper's Admin REST API.

  • Get Enterprise Security Stats

    Get summary security-posture statistics for the enterprise.

  • Get Enterprise Security Stat Details

    Get detailed security-posture statistics for the enterprise.

  • Get Security Alerts Summary

    Get a summary of the enterprise's security alerts.

  • Get Security Alerts Detail

    Get the detailed list of the enterprise's security alerts for an audit event type.

  • Get MSP Billing Usage

    Get an MSP's billing usage for a given month.

  • Get MSP Current Usage

    Get an MSP's current billing usage.

  • Get Unified Credentials

    Get the current Keeper connection's unified credentials and identity.

  • Get SCIM Service Provider Config

    Get the SCIM service provider configuration of the connected Keeper node.

  • List SCIM Resource Types

    List the SCIM resource types exposed by the connected Keeper node.

  • List SCIM Schemas

    List the SCIM schemas supported by the connected Keeper node.

  • Patch Team

    Modify a Keeper team through the SCIM API, including adding and removing members.

  • Patch User

    Modify specific attributes of a Keeper user through the SCIM API.

Set Up Your Keeper MCP Server in Minutes

One endpoint. Any framework. Your agent is talking to Keeper in under 10 lines of code.

Agent Frameworks

Claude Desktop
{
  "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

Wiz

696+ actions

IONOS

501+ actions

Workiva

266+ actions

KnowBe4

259+ actions

HighLevel

251+ actions

WorkOS

234+ actions

SAP Concur

232+ actions

Keeper MCP Server FAQ

Does StackOne have a Keeper MCP server?
Yes. StackOne offers a managed Keeper MCP server with 27 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.
Keeper MCP server vs direct API integration: what's the difference?
A Keeper MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software work, where backend code calls Keeper. A Keeper MCP server is for AI agents that discover and call Keeper at runtime, such as MCP clients like Claude and Cursor, plus framework agents built with OpenAI, LangChain, or Vercel AI. StackOne provides both.
How does Keeper authentication work for AI agents?
Keeper authentication for AI agents works through a StackOne Connect Session. Create one via the dashboard or the SDK to get an auth link and ready-to-paste config for Claude Desktop, Cursor, and other MCP clients. Your user authenticates their own Keeper account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via origin_owner_id.
Are Keeper MCP tools vulnerable to prompt injection?
Yes. Keeper MCP tools can be vulnerable to indirect prompt injection. Any tool that reads user-written content, such as 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. It runs regex patterns in ~1ms, then a MiniLM classifier in ~4ms. Accuracy is 88.7%, and it runs entirely on CPU.
What is the context bloat of a Keeper agent and how do I avoid it?
Context bloat happens when Keeper tool schemas and API responses eat your Keeper agent's memory, preventing it from reasoning effectively. A single Keeper query can return a massive JSON response, and connecting multiple tools compounds the problem. Tools Discovery reduces it by loading only the tools relevant to each query.
Can I limit which actions my Keeper agent can access?
Yes. You can limit which actions your Keeper 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 Keeper MCP server?
Yes. You can create custom agent actions for your Keeper MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research Keeper's API, generate production-ready connector YAML, test against the live API, and validate before you ship.
When should I NOT use a Keeper MCP server?
Skip a Keeper MCP server if your integration is purely software-to-software, because direct Keeper 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 Keeper actions at runtime.
What AI frameworks and AI clients does the StackOne Keeper MCP server support?
The StackOne Keeper 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

Connect AI to every company system and control what it can do in each one, down to the field.