# AgentBond

> Use this tool when you need to manage and govern AI agents with fine-grained access control, auditable decision-making, and secure inter-agent agreements. AgentBond provides token-based authorization, intent proof, and contract management to solve problems in multi-agent systems, budget-constrained operations, and auditable governance. It takes inputs such as token requests, intent statements, and contract terms, and outputs audit logs, access controls, and verified intent proofs.

Canonical page: https://skillsregistry.net/skills/agentbond-mcp-server  
JSON: https://api.skillsregistry.net/v1/skills/agentbond-mcp-server

## Description

Authorization and governance infrastructure for AI agents. 17 MCP tools for token authorization, intent proof, contract management, action evaluation, and audit logging.

**Key Features:**
- Token-based authorization with scope, budget, and expiry controls
- Hierarchical delegation (parent → child token chains)
- Intent proof layer — record and verify why agents act
- Inter-agent contracts with lifecycle management
- Built-in audit trail for all governance decisions

**Use Cases:**
- Multi-agent systems requiring fine-grained access control
- Budget-constrained agent operations
- Auditable AI agent governance
- Inter-agent agreements and deliverable tracking

## Trust

- **Trust score (0–1):** 0.97
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-09-28

## Source

- **Source listing:** [Smithery](https://smithery.ai/server/agentbond/mcp-server)
- **Repository:** <https://github.com/wharfe/agentbond>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "agentbond-mcp-server"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/agentbond-mcp-server` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/agentbond-mcp-server/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt