Previously, MCP clients had to wait for the full daemon to boot before getting any response. Now, initialize and tools/list respond immediately from the bridge process:
Before: Client → wait 2-4s for daemon → get response
After: Client → get response in ~130ms → daemon boots in background
This means your AI coding agent gets tool definitions instantly and can start planning while the server finishes starting up. If you call a tool before the daemon is ready, you get a helpful retry message instead of a hang.
Gasoline v5.5.0 is a stability release focused on MCP protocol compliance. If you experienced “Unexpected end of JSON input” errors or connection issues with Claude Desktop or Cursor, this release fixes them all.
Go’s json.Encoder.Encode() adds a trailing newline to JSON output. Our stdio bridge then called fmt.Println(), adding a second newline. The empty line between messages was parsed as an empty JSON message, causing the parse error.
Fix: Changed fmt.Println(string(body)) to fmt.Print(string(body)) in the bridge — the HTTP response already includes the trailing newline.
JSON-RPC 2.0 notifications (requests without an id field) must not receive responses. We were responding to notifications/initialized with an empty response, violating the spec.
Fix: Notifications now return nil from the handler and receive no response. HTTP transport returns 204 No Content.
TestMCPProtocol_HTTPHandler — HTTP transport compliance
TestMCPProtocol_BridgeCodeVerification — static analysis of bridge code
These tests are designed to be unalterable — they verify the MCP spec, not implementation details. Any future change that breaks MCP compliance will fail these tests.
Gasoline v5.1.0 is a security-focused release that fixes a critical privacy vulnerability in how the extension captures browser telemetry. If you’re running any previous version, upgrade immediately.
Prior to v5.1.0, the extension captured console logs, network requests, and other telemetry from every open browser tab — regardless of whether tracking was enabled for that tab. If you had 40 tabs open and clicked “Track This Page” on one of them, data from all 40 tabs was forwarded to the MCP server.
This was a privacy vulnerability. Tabs containing banking sites, personal email, or other sensitive sessions would leak telemetry into the AI assistant’s context.