nonameuserd/paybond-kit
by Various
TypeScript SDK for agent spend governance around paid tool calls across MCP, LangGraph, OpenAI, Claude, and Gemini: spend authorization, evidence receipts, refunds, disputes, and s
MCP
nonameuserd/paybond-kit
Added 13 July 2026
Overview
A TypeScript SDK for governing agent spend on paid tool calls. It integrates with multiple AI frameworks including MCP, LangGraph, OpenAI, Claude, and Gemini to handle authorization, produce evidence receipts, and manage refunds, disputes, and settlement.
Best for
Best for
Developers building AI agents that need to manage and audit paid tool call costs
Use cases
- Implementing spend authorization for AI agent tool calls
- Tracking and reconciling costs across multiple AI provider APIs
- Handling refunds and disputes for agent-invoked paid tools
Notes
A TypeScript SDK for governing agent spend on paid tool calls. It integrates with multiple AI frameworks including MCP, LangGraph, OpenAI, Claude, and Gemini to handle authorization, produce evidence receipts, and manage refunds, disputes, and settlement.
1 stars on GitHub. Last updated 2026-07-13. Licensed Apache-2.0.
Use cases
- Implementing spend authorization for AI agent tool calls
- Tracking and reconciling costs across multiple AI provider APIs
- Handling refunds and disputes for agent-invoked paid tools
Pros
- Covers the full lifecycle of agent spend governance
- Works across several major AI frameworks and providers
- Provides structured evidence receipts for audit trails
Cons
- Very low community adoption (1 star) suggests limited tested use
- Documentation and support may be minimal
- Dependency on multiple rapidly changing AI APIs increases maintenance risk
Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.
Pros
- Covers the full lifecycle of agent spend governance
- Works across several major AI frameworks and providers
- Provides structured evidence receipts for audit trails
Cons
- Very low community adoption (1 star) suggests limited tested use
- Documentation and support may be minimal
- Dependency on multiple rapidly changing AI APIs increases maintenance risk
Pairs with
Other entries in the index that connect to this one. Click through to see the chain.
FastMCP
Various
🚀 The fast, Pythonic way to build MCP servers and clients.
AutoGen
Microsoft
Microsoft's framework for multi-agent conversations. Agents that talk to each other to solve hard problems.
Open Interpreter
Various
A natural language interface for computers
Get the free Developer’s Field Guide
A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.
Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.