agent-device
mcp0.21.31Mobile app automation and verification for AI coding agents. CLI, MCP server, and typed Node.js API for iOS, Android, HarmonyOS, TV, web, macOS, and Linux.
By callstack | 134 findings | Scanned 10/26/2026 | tooltrust-scanner/v0.3.20 | 5.1k
Repository health
Popularity and maintenance signals alongside the security grade.
5.1k
current snapshot
Not collected
GitHub metadata pending
Not collected
GitHub metadata pending
Not collected
GitHub metadata pending
Not collected
GitHub metadata pending
Not collected
Latest GitHub release
Stars trend
Daily star additions · githubarchive_bq · observed through Oct 26, 2026 · export updated Oct 26, 2026
Pull request activity
Weekly PR events · githubarchive_bq · observed through Oct 26, 2026 · export updated Oct 26, 2026
Data quality: observed_events. Charts show observed events, not a reconstructed historical total.
Risk Summary
Safe With Normal ControlsDep Visibility is the main signal, but overall risk remains within an acceptable range.
Potential impact: This finding indicates the tool should be reviewed before it is trusted.
Recommended action: No high-risk findings were detected in this scan, but you should still apply least-privilege defaults and rescan after changes.
Suggested policy: keep this tool behind manual approval, do not allow unattended runs, and re-scan after narrowing risky permissions.
Security Findings (134)
Tool set changed silently at v0.21.31: 46 tool(s) added, 1 tool(s) removed without a version bump.
+ 46 added
fetchonchain_agent_build_planonchain_agent_check_installonchain_agent_compare_listingsonchain_agent_create_agentonchain_agent_explain_numberonchain_agent_find_x402_serviceonchain_agent_get_agent_economyonchain_agent_get_agent_passportonchain_agent_get_chain_cardonchain_agent_get_changesonchain_agent_get_contract_factsonchain_agent_get_data_freshnessonchain_agent_get_deploy_speconchain_agent_get_listing_historyonchain_agent_get_metricsonchain_agent_get_newsonchain_agent_get_resourceonchain_agent_get_score_methodologyonchain_agent_get_sdk_lineageonchain_agent_get_trendonchain_agent_get_wiki_pageonchain_agent_get_x402_facilitatorsonchain_agent_inspect_listingonchain_agent_list_categoriesonchain_agent_list_chainsonchain_agent_list_wiki_pagesonchain_agent_preflightonchain_agent_recent_changesonchain_agent_recommend_stackonchain_agent_register_agentonchain_agent_resolve_tokenonchain_agent_route_agentonchain_agent_route_launchonchain_agent_route_lponchain_agent_route_swaponchain_agent_scaffold_planonchain_agent_scan_recipientonchain_agent_search_agentsonchain_agent_search_listingsonchain_agent_search_resourcesonchain_agent_search_skillsonchain_agent_submit_projectonchain_agent_swaponchain_agent_watchsearch− 1 removed
utility_parse_user_agentFix: The set of tools exposed by this server changed between scans of the same version — a sign the package was silently updated without a version bump. Audit the changelog and all tool definitions before trusting this server. Pin to a specific commit hash rather than a floating version tag.
input schema exposes 26 properties (threshold: 10)
onchain_agent_search_resourcesinput schema exposes 13 properties (threshold: 10)
onchain_agent_preflightinput schema exposes 14 properties (threshold: 10)
onchain_agent_register_agentonchain_agent_swapFix: 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
onchain_agent_search_resourcessearchfetchonchain_agent_get_deploy_speconchain_agent_get_newsonchain_agent_get_metricsonchain_agent_search_agentsonchain_agent_recommend_stackonchain_agent_get_changesonchain_agent_get_agent_economyonchain_agent_search_skillsonchain_agent_compare_listingsonchain_agent_explain_numberonchain_agent_get_score_methodologyonchain_agent_get_data_freshnessonchain_agent_search_listingsonchain_agent_inspect_listingonchain_agent_get_listing_historyonchain_agent_preflightonchain_agent_check_installonchain_agent_scan_recipientonchain_agent_route_swaponchain_agent_route_launchonchain_agent_build_planonchain_agent_create_agentonchain_agent_scaffold_planonchain_agent_submit_projectonchain_agent_register_agentonchain_agent_swaponchain_agent_resolve_tokenonchain_agent_find_x402_serviceonchain_agent_get_sdk_lineageonchain_agent_get_contract_factsonchain_agent_get_chain_cardonchain_agent_get_x402_facilitatorsFix: 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.
declared capabilities: network access, filesystem access, database access
onchain_agent_search_resourcessearchonchain_agent_search_agentsonchain_agent_search_listingsonchain_agent_get_sdk_lineagedeclared capabilities: filesystem access
onchain_agent_get_resourceonchain_agent_list_chainsonchain_agent_get_wiki_pageonchain_agent_get_agent_passportdeclared capabilities: network access, filesystem access
fetchonchain_agent_get_newsonchain_agent_get_metricsonchain_agent_recommend_stackonchain_agent_get_changesonchain_agent_compare_listingsonchain_agent_get_data_freshnessonchain_agent_inspect_listingdeclared capabilities: network access
onchain_agent_get_deploy_speconchain_agent_get_agent_economyonchain_agent_get_score_methodologyonchain_agent_get_listing_historyonchain_agent_scan_recipientonchain_agent_route_swaponchain_agent_route_launchonchain_agent_swaponchain_agent_find_x402_serviceonchain_agent_get_chain_carddeclared capabilities: code/command execution, network access, filesystem access, database access, HTTP requests
onchain_agent_search_skillsdeclared capabilities: network access, database access
onchain_agent_explain_numberonchain_agent_get_contract_factsonchain_agent_get_x402_facilitatorsdeclared capabilities: code/command execution, network access, filesystem access, HTTP requests
onchain_agent_preflightonchain_agent_check_installonchain_agent_build_plandeclared capabilities: network access, filesystem access, HTTP requests
onchain_agent_create_agentdeclared capabilities: code/command execution, network access, filesystem access
onchain_agent_scaffold_planonchain_agent_submit_projectonchain_agent_register_agentonchain_agent_resolve_tokenFix: Tool requests broad permissions (exec/fs/network). Validate input parameters using Enums where possible, and restrict file system operations to explicit allowed directories.
Tool did not expose metadata.dependencies or repo_url, so supply-chain coverage is limited.
onchain_agent_search_resourcesonchain_agent_get_resourcesearchfetchonchain_agent_get_deploy_speconchain_agent_recent_changesonchain_agent_list_categoriesonchain_agent_list_chainsonchain_agent_get_newsonchain_agent_get_metricsonchain_agent_get_wiki_pageonchain_agent_search_agentsonchain_agent_get_agent_passportonchain_agent_recommend_stackonchain_agent_list_wiki_pagesonchain_agent_get_changesonchain_agent_get_agent_economyonchain_agent_search_skillsonchain_agent_get_trendonchain_agent_compare_listingsonchain_agent_explain_numberonchain_agent_get_score_methodologyonchain_agent_get_data_freshnessonchain_agent_search_listingsonchain_agent_inspect_listingonchain_agent_get_listing_historyonchain_agent_preflightonchain_agent_check_installonchain_agent_scan_recipientonchain_agent_route_swaponchain_agent_route_agentonchain_agent_route_launchonchain_agent_build_planonchain_agent_route_lponchain_agent_create_agentonchain_agent_scaffold_planonchain_agent_watchonchain_agent_submit_projectonchain_agent_register_agentonchain_agent_swaponchain_agent_resolve_tokenonchain_agent_find_x402_serviceonchain_agent_get_sdk_lineageonchain_agent_get_contract_factsonchain_agent_get_chain_cardonchain_agent_get_x402_facilitatorsFix: Review and remediate the identified issue.
input parameter "token_limit" accepts a credential (informational; not evidence of insecure handling)
onchain_agent_get_metricsinput parameter "token" accepts a credential (informational; not evidence of insecure handling)
onchain_agent_preflightonchain_agent_scan_recipientonchain_agent_resolve_tokenonchain_agent_get_contract_factsinput parameter "token_in" accepts a credential (informational; not evidence of insecure handling)
onchain_agent_route_swaponchain_agent_swapinput parameter "token_out" accepts a credential (informational; not evidence of insecure handling)
onchain_agent_route_swaponchain_agent_swapFix: 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.
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 agent-device"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)