C-

npm:sendblue-browser-mcp

https://www.npmjs.com/package/sendblue-browser-mcp
70/100 · MCP Trust Grade · checked 3h ago · MCP 0.2.3

What it offers — 13 tools · Web & Scraping

health

Check if the sendblue-browser-use daemon is reachable. Returns service metadata, active session count, and navScreenshotPolicy. No auth used (the /hea

list_sessions

List every active browser session on the daemon.

create_session

Create a new browser session. persistent=true follows the daemon default and backs to an on-disk profile that survives restarts but does NOT expose a

get_session

Inspect a session — current page URL/title, console message count, CDP url, and whether automatic nav screenshots are enabled.

navigate

Navigate the session

screenshot

Take a PNG screenshot of the session

script

Evaluate a JavaScript expression in the session

get_cookies

Read cookies from the session

set_cookies

Inject cookies. Each cookie needs name+value plus EITHER url OR (domain AND path).

get_console

Read recent console messages from the session

get_cdp_url

Return the CDP websocket URL and targetId for a non-persistent session so a Playwright/Puppeteer client can connectOverCDP() and select the session pa

purge_session

Clear cookies and permissions context-wide, then current open page/origin localStorage, sessionStorage, IndexedDB, ServiceWorkers, CacheStorage, and c

close_session

Close the session and delete its on-disk profile.

Spec / packaging20%100
Security (OWASP MCP)30%25
Maintenance / popularity20%92
Tool hygiene15%70
Transparency / provenance15%90

Findings

WARNMCP08 References sensitive file paths / environment secrets.
INFO Static analysis of npm package sendblue-browser-mcp@0.2.3 (stdio server — no remote endpoint). Reliability/behavioral signals require running it; not measured.
Grade another server

We re-grade npm:sendblue-browser-mcp on a schedule and alert your Slack/webhook the moment its tools change or its grade drops — rug-pull insurance for the connection.

Share this report card

A 1200×630 card with the grade + audit — drop it in a post, Slack, or your repo.

MCP Trust report card — npm:sendblue-browser-mcp grade C-
Share on X Open card image

Embed this grade

A live badge — it re-verifies itself and shows current stability. Static scorecards can't. Paste it in your README or site to show users you're independently audited.

MCP Trust Grade C- · wmcp.sh
[![MCP Trust Grade C-](https://wmcp.sh/mcp/grade/npm%3Asendblue-browser-mcp/badge.svg)](https://wmcp.sh/mcp/grade/npm%3Asendblue-browser-mcp)
<a href="https://wmcp.sh/mcp/grade/npm%3Asendblue-browser-mcp"><img src="https://wmcp.sh/mcp/grade/npm%3Asendblue-browser-mcp/badge.svg" alt="MCP Trust Grade C- · wmcp.sh"></a>

Agents: check this before connecting

Add the wmcp.sh trust oracle as an MCP server and call grade_mcp_server / check_mcp_drift in your agent's pre-connection gate:

https://wmcp.sh/mcp/trust
How this grade is computed. An open, independent rubric — Spec conformance (20%), Security mapped to the OWASP MCP Top 10 (30%), Reliability (20%), Tool hygiene (15%), Transparency (15%) — run by connecting to the server and inspecting its real MCP surface. The grade is free and identical whether or not the operator pays. v1 uses static + spec signals from a single connection; continuous uptime, real latency, and annotation-truthing (declared readOnly vs observed behavior) layer on via the wmcp.sh proxy.