agentbond-mcp-server
mcpsmitheryAuthorization 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
By Smithery | 41 findings | Scanned 5/10/2026 | tooltrust-scanner/v0.3.9
Risk Summary
Needs ApprovalDep Visibility plus Secret Handling raises enough risk that this tool should not be auto-trusted.
Potential impact: This finding indicates the tool should be reviewed before it is trusted.
Recommended action: Keep this tool behind manual approval and avoid unattended runs until the risky capabilities are narrowed or removed.
Suggested policy: keep this tool behind manual approval, do not allow unattended runs, and re-scan after narrowing risky permissions.
Security Findings (41)
input parameter "parentTokenId" appears to accept a secret or credential
agentbond_issue_tokeninput parameter "tokenId" appears to accept a secret or credential
agentbond_evaluate_actionagentbond_revoke_tokenagentbond_suspend_tokenagentbond_reactivate_tokenagentbond_get_tokenagentbond_get_audit_by_tokenagentbond_record_intentagentbond_evaluate_intent_policyinput parameter "authorizationTokenRef" appears to accept a secret or credential
agentbond_create_contractFix: Avoid accepting raw credentials as input parameters. Use secret managers (e.g. 1Password CLI, AWS Secrets Manager) and ensure credentials are never logged or stored in agent traces.
tool declares exec permission
agentbond_evaluate_actionagentbond_revoke_tokenagentbond_record_intentagentbond_evaluate_intent_policyagentbond_create_contractagentbond_evaluate_contractFix: Tool requests broad permissions (exec/fs/network). Validate input parameters using Enums where possible, and restrict file system operations to explicit allowed directories.
tool declares db permission
agentbond_get_audit_logtool declares fs permission
agentbond_create_contractFix: Tool requests broad permissions (exec/fs/network). Validate input parameters using Enums where possible, and restrict file system operations to explicit allowed directories.
tool performs network or execution operations but declares no rate-limit, timeout, or retry configuration
agentbond_evaluate_actionagentbond_revoke_tokenagentbond_record_intentagentbond_evaluate_intent_policyagentbond_create_contractagentbond_evaluate_contractFix: Declare explicit rate-limit, timeout, and retry configuration for all network and execution tools. Implement exponential back-off and surface resource state to the calling agent.
Tool did not expose metadata.dependencies or repo_url, so supply-chain coverage is limited.
agentbond_issue_tokenagentbond_evaluate_actionagentbond_revoke_tokenagentbond_suspend_tokenagentbond_reactivate_tokenagentbond_get_tokenagentbond_get_audit_logagentbond_get_audit_by_actionagentbond_get_audit_by_tokenagentbond_record_intentagentbond_evaluate_intent_policyagentbond_get_intentagentbond_get_intent_by_actionagentbond_create_contractagentbond_transition_contractagentbond_evaluate_contractagentbond_get_contractFix: Review and remediate the identified issue.
Scan this tool yourself
Reproduce this audit locally, integrate into CI, or let your agent audit its own tools.
Install once, then scan any MCP server:
$ curl -sfL https://raw.githubusercontent.com/AgentSafe-AI/tooltrust-scanner/main/install.sh | bash$ tooltrust-scanner scan --server "npx -y agentbond-mcp-server"Adjust the package name if your npm registry name differs from the tool ID. View source
Add badge to your README
Copy this Markdown to show your ToolTrust grade on GitHub.
[](https://github.com/AgentSafe-AI/tooltrust-directory)