Works with the AI Agents you already use
Trustcard Operations
Operate and verify cryptographic safety gates for MCP tools across local agent fleets.
$9.99
Trustcard Operations
Example session with this skill installed
Audit my MCP client configuration, identify every direct or expired Trustcard route, preview safe renewals, and explain any blocked tools without exposing credentials. Do not write changes until I approve them.
- Read your context and instructions
- Compiled the trustcard operations
Trustcard fleet audit
I inspected the selected MCP client configuration and preserved its existing transports, environment references, and credentials. No business tools were invoked.
| Server | Route | Manifest | Result |
|---|---|---|---|
| filesystem | stdio proxy | Valid, expires in 11 days | Renewal preview is safe |
| linear | direct HTTP | None | Ungated route found |
| internal-search | stdio proxy | Contract changed | Reapproval required |
Recommended actions
- Renew
filesystem because its complete observed contract still matches the approved contract. The preview preserves its deny rules and required scopes.
2. Gate linear through the loopback HTTP proxy. I prepared the command and config diff, but did not apply it.
3. Review
internal-search manually: one tool description and input schema changed. Renewal is refused because this is contract drift, not expiry maintenance.
Evidence and limits
Publisher signatures establish key and content binding; they do not prove safe runtime behavior. The behavioral harness isolates the working directory and environment, but it is not an OS sandbox and does not block filesystem or network access. A successful manifest write also does not prove that a running client reloaded it.
No files were changed. Next step: approve the filesystem renewal and the proposed Linear gate separately.
Connects securely to your tools. The creator never sees your data.
About this skill
Set up, inspect, renew, and troubleshoot Trustcard enforcement for MCP servers without exposing credentials or weakening policy. The skill guides agents through fleet status checks, manifest expiry and drift handling, HTTP and stdio gating, scoped authorization, signed evidence, safe reapproval, and runtime verification. It clearly separates local proxy policy from publisher attestation and documents the limits of process isolation.
Trustcard verifies manifests, contracts, and proxy policy; it does not prove that a remote publisher or runtime is trustworthy. Behavioral checks use process-level isolation rather than an OS sandbox, so untrusted servers may still access the host filesystem or network. Runtime reload behavior varies by MCP client, and TOML-only client configs require an adapter or manual integration.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 1 month ago
Requires
Permissions
Reads the MCP client configuration and Trustcard manifests selected by the user. Writes only during explicitly authorized gate, renew, or reapprove operations. Network access is used for npm package checks and live HTTP MCP discovery. Environment variables may supply server configuration; credential values must never be printed or copied into URLs or command arguments.