# paperclip: Managing AI Agents with Org Charts & Cost Control MCP Client

> paperclip is an open-source TypeScript MCP Client for managing AI agents within an organizational structure. It allows developers to integrate any agent, track costs, and enforce governance, solving the challenge of deploying and overseeing AI workforces at scale.

**Published:** 2026-10-21T12:00:50.077+00:00

**Keywords:** paperclip,mcp-client,paperclipai,ai-agent-management,typescript

# paperclip: Managing AI Agents with Org Charts & Cost Control

paperclip is an open-source TypeScript MCP Client designed for managing AI agents within a structured organizational context. It provides the tools necessary for companies to integrate diverse agents, align their work with business goals, and maintain oversight on costs and governance, making it a robust solution for deploying AI workforces.

## Integrating Diverse Agents and Aligning Goals

At its core, paperclip allows organizations to "Bring Your Own Agent." This means any agent, regardless of its underlying runtime, can be integrated into a unified organizational chart, provided it can receive a heartbeat. Agents are not just standalone entities; they are assigned roles and reporting lines within an "Org Chart," complete with titles and job descriptions.

This integration extends to "Goal Alignment," where tasks and projects are directly linked to broader organizational objectives. Agents receive the full context of these goals, ensuring their work contributes meaningfully to company-wide aims.

## Operational Control and Governance

Managing an AI workforce requires robust operational control, and paperclip addresses this through several key features. "Heartbeats" ensure agents wake for assigned work, follow-up messages, or configured schedules, enabling delegation up and down the established organizational hierarchy.

"Task Threads" are central to maintaining context. Conversations, plans, blockers, files, and run histories are all kept attached to specific tasks, which can be assigned to either agents or human team members. This ensures a complete audit trail and facilitates collaboration.

For governance, paperclip includes configurable "review and approval stages." Organizations can approve agent hires, and pause, reassign, or stop work as needed, providing critical oversight. This is complemented by "Multi-Organization" support, allowing a single deployment to manage separate tasks, agents, permissions, and activity histories for multiple distinct organizations.

## Cost Control and Budgeting

A critical aspect of managing AI agents is cost. paperclip offers granular "Cost Control" through company, agent, and project budgets. The system tracks reported spend, issues threshold alerts, and can pause work automatically when configured limits are reached. This direct financial oversight is crucial for scaling AI initiatives responsibly.

## References
- [paperclip on GitHub](https://github.com/paperclipai/paperclip)
- [Model Context Protocol Documentation](https://modelcontextprotocol.io/introduction)
- [paperclip on model-context-protocol.com](https://model-context-protocol.com/clients/)

## Related Repository

- [paperclip](https://model-context-protocol.com/clients/paperclip)

**Source:** https://model-context-protocol.com/blog/paperclip-managing-ai-agents-with-org-charts-cost-control-mcp-mcp-client-guide