A2a Trustgate is listed as active in the registry but did not answer our last check. 92 installs a week from npm. Last commit 8 Aug 2026.
A2A TrustGate: 4-gate firewall that screens every AI-agent action before it runs. 50 tools.
We read the source, 23 h ago · rules 3dff92dd89df
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
этот файл ставится пользователю, но в репозитории его нет
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 8 min ago.
claude mcp add a2a-trustgate --transport http https://mcp.a2ainfrastructure.com/sse
{
"mcpServers": {
"a2a-trustgate": {
"url": "https://mcp.a2ainfrastructure.com/sse"
}
}
}
[mcp_servers.a2a-trustgate]
url = "https://mcp.a2ainfrastructure.com/sse"
{
"mcpServers": {
"a2a-trustgate": {
"url": "https://mcp.a2ainfrastructure.com/sse"
}
}
}
{
"mcpServers": {
"a2a-trustgate": {
"url": "https://mcp.a2ainfrastructure.com/sse"
}
}
}
This one needs environment variables set before it will start:
A2A_API_KEY (A2A TrustGate API key (a2a_...). Optional: without a key the server starts and can guide signup; most tools require a key to call the firewall.), A2A_URL (Base URL of the A2A TrustGate API. Defaults to https://a2ainfrastructure.com.).
The author declared them in the registry entry; get the values from the project itself.
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://mcp.a2ainfrastructure.com/sse | sse | answering | 182 ms | 8 min ago |
MCP proxy that checks every tools/call against Agent Trust policy, with evidence, before it runs.
Prompt-injection firewall for AI agents — scan untrusted text before LLM calls.
MCP enforcement layer that intercepts AI agent actions and blocks rule violations before execution.
AI Agent Firewall. Enforce signed authority before consequential actions. Free API key required.
Crypto transaction firewall and risk tools for MCP agents.
Tamper-evident action receipts, trust scoring & capability tokens for AI agents. 29 MCP tools.
The trust harness for AI agents. Set what an agent can do before it acts.
Security gateway for MCP agents: blocks prompt-injection-driven tool calls before they execute.
Answers built from our own checks of this server.