rafaelkocurek-nvob-agentview
mcpsmithery# agentView Premium digital signage control plane for AI agents. Create and manage displays, send HTML or live URLs to any screen, allocate licenses, and orchestrate organizations and team members — all through natural language. ## What you can do - **Send content to any display**: `send_html` for rich cinematic layouts, `send_url` for live web pages, `clear_display` to reset - **Pair new screens instantly**: open [display.agentview.de](https://display.agentview.de) on any TV or browser, read the 6-character code, call `pair_by_code`, and the display is live - **Manage fleets**: create organizations, invite members, allocate licenses, assign grants, lock displays - **Design cinematic content**: the `render_premium_display_html` prompt plus the `agentview://public/design-system` resource give you a full signage design system — glassmorphism panels, fluid typography, public-API integrations, no API keys needed ## Authentication Connect with **OAuth 2.1 + PKCE** (with Dynamic Client Registration). No API keys to paste — Smithery handles the browser handshake automatically, then your agent gets scoped access tokens for the duration of the session. ## Learn more - Homepage: [agentview.de](https://agentview.de) - Setup guide for AI agents: [agentview.de/agent-instructions](https://agentview.de/agent-instructions) - Developer docs: [agentview.de/developers.html](https://agentview.de/developers.html)
By Smithery | 172 findings | Scanned 7/3/2026 | tooltrust-scanner/v0.3.19
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 (172)
set_org_connectivity:tool name "set_org_connectivity" implies local write operation but only remote/network-class permissions were detected
Fix: Ensure tool names, descriptions, and permission declarations are internally consistent. Use explicit naming conventions that fully reflect actual capabilities.
tool performs network or execution operations but declares no rate-limit, timeout, or retry configuration
create_auth_sessionauthenticateget_public_statussearchfetchsearch_public_apislist_displaysinvite_memberget_billing_urlbroadcast_contentget_display_capabilitiescreate_displaysend_htmlsend_urlset_idle_contentget_display_contentlock_displayunlock_displaypair_by_codeunassign_licensecreate_api_keylist_api_keysrevoke_api_keyupload_assetlist_assetsget_assetupdate_assetset_org_connectivityFix: 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
create_auth_sessionlist_displayscreate_displaypair_by_codecreate_api_keydeclared capabilities: network access
authenticateget_public_statusfetchsearch_public_apisinvite_memberget_billing_urlget_display_capabilitiesget_display_contentlock_displayunlock_displaylist_api_keysrevoke_api_keylist_assetsget_assetset_org_connectivitydeclared capabilities: network access, database access
searchdeclared capabilities: filesystem access
get_accountcreate_organizationdelete_organizationupdate_member_roleremove_memberremove_display_from_orgremove_display_grantcreate_org_displaydelete_displayclaim_displaydelete_assetdeclared capabilities: code/command execution
broadcast_contentset_idle_contentdeclared capabilities: code/command execution, network access, filesystem access
send_htmlsend_urlupload_assetupdate_assetdeclared capabilities: HTTP requests
unassign_licenseFix: 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.
create_auth_sessionget_auth_sessionauthenticatelogoutget_public_statussearchfetchget_pricingsearch_public_apisget_accountlist_displayslist_organizationsget_organizationinvite_memberget_billing_urlallocate_licensescreate_organizationrename_organizationdelete_organizationupdate_member_roleremove_memberlist_org_displaysget_license_inforemove_display_from_orgset_display_grantremove_display_grantbroadcast_contentcreate_org_displayget_displayget_display_capabilitiescreate_displayrename_displaydelete_displaysend_htmlsend_urlclear_displayset_idle_contentget_display_contentread_display_htmllock_displayunlock_displayconfigure_displaypair_by_codeclaim_displayassign_licenseunassign_licensecreate_api_keylist_api_keysrevoke_api_keyupload_assetlist_assetsget_assetupdate_assetdelete_assetset_org_connectivityFix: Review and remediate the identified issue.
input parameter "token" accepts a credential (informational; not evidence of insecure handling)
authenticatesend_htmlinput parameter "access_token" accepts a credential (informational; not evidence of insecure handling)
authenticateget_accountlist_displayslist_organizationsget_organizationinvite_memberget_billing_urlallocate_licensescreate_organizationrename_organizationdelete_organizationupdate_member_roleremove_memberlist_org_displaysget_license_inforemove_display_from_orgset_display_grantremove_display_grantbroadcast_contentcreate_org_displayget_displayget_display_capabilitiescreate_displayrename_displaydelete_displaysend_htmlsend_urlclear_displayset_idle_contentget_display_contentread_display_htmllock_displayunlock_displayconfigure_displaypair_by_codeclaim_displayassign_licenseunassign_licensecreate_api_keylist_api_keysrevoke_api_keyupload_assetlist_assetsget_assetupdate_assetdelete_assetset_org_connectivityFix: 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 rafaelkocurek-nvob-agentview"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)