mcp MCP server

Settings → Connectors → Add custom connector, then paste:
https://api.packetstream.io/v1/mcp

The entry also requires the header Authorization.

{
  "mcpServers": {
    "mcp": {
      "url": "https://api.packetstream.io/v1/mcp",
      "headers": {
        "Authorization": "<Authorization>"
      }
    }
  }
}

{
  "servers": {
    "mcp": {
      "type": "http",
      "url": "https://api.packetstream.io/v1/mcp",
      "headers": {
        "Authorization": "${input:authorization}"
      }
    }
  },
  "inputs": [
    {
      "type": "promptString",
      "id": "authorization",
      "description": "Authorization",
      "password": true
    }
  ]
}

claude mcp add --transport http mcp https://api.packetstream.io/v1/mcp --header "Authorization: <Authorization>"

{
  "mcpServers": {
    "mcp": {
      "type": "streamableHttp",
      "url": "https://api.packetstream.io/v1/mcp",
      "headers": {
        "Authorization": "<Authorization>"
      },
      "disabled": false,
      "autoApprove": []
    }
  }
}

{
  "mcpServers": {
    "mcp": {
      "httpUrl": "https://api.packetstream.io/v1/mcp",
      "headers": {
        "Authorization": "<Authorization>"
      }
    }
  }
}

[mcp_servers.mcp]
url = "https://api.packetstream.io/v1/mcp"
http_headers = { "Authorization" = "<Authorization>" }

{
  "context_servers": {
    "mcp": {
      "url": "https://api.packetstream.io/v1/mcp",
      "headers": {
        "Authorization": "<Authorization>"
      }
    }
  }
}

npx @modelcontextprotocol/inspector@2.11.0 --server-url https://api.packetstream.io/v1/mcp --transport http

Built from the server's registry entry with each client's documented format (checked 2026-10-14; the Cursor link and the VS Code command 2026-10-19; the MCP Inspector command 2026-10-21; Cline, Gemini CLI, OpenAI Codex and Zed 2026-10-26). Values in < > are yours to fill in; this page never contains a key. Where the server needs a setting the entry does not declare, it can still fail to start.

Facts about the publisher. We do not turn them into a trust score.

Source: the registry entry and api.github.com · 2026-11-05; security policy read from GitHub · 2026-11-05.

Publish this server? Run these checks against it yourself before release, from your own machine: a server the command starts, or your own server at its URL after a one-time proof that you control it: npx protocolprobe-selftest.

Needs the operator's credential

The server requires sign-in. We never use a credential its operator did not give us, so most checks could not run. No security score is given; a check we did not run is never counted as passed.

Why no live read-only session: The server required a sign-in before it would list anything, and we never use a credential its operator did not give us. Its operator can test it with their own credential, on their own machine, with our self-test command (/docs/selftest). — the server's own choice

Each check ends in exactly one state: exercised, not run (with the reason), or not applicable (with the reason). 1 of the 18 checks that apply to it was exercised. We do not publish security-check outcomes for named servers. These 18 checks are separate from the record checks at the top of this page, which read public records only.

Source: our own test, 2026-11-05, mcp-runtime-engine@0.1.0. Which checks count and why follows our published scoring model.

The steps in order, as the test record holds them.

1. 0 msStarted a session with the server's remote endpoint
2. The server asked for sign-in before listing anything.
3. 2,262 msFinished: 1 check exercised.

One value per field, each with its source. Fields written by AI models are marked. A field with no value says why.

“Not stated” means the source did not state it; “does not apply” means it does not apply to this kind of server; “our limit” means our own lookup failed. A linked value opens the directory filtered to the same value.