B-

npm:@vallt/mcp-server

https://www.npmjs.com/package/@vallt/mcp-server
80/100 · MCP Trust Grade · checked 2h ago · MCP 0.0.37

What it offers — 10 tools · Developer Tools

vlt_connect_integration

Start the guided integration flow for a third-party service (e.g. Stripe, Supabase, Twilio). Call without keys first to get setup instructions, then c

vlt_get_secret

Check whether a secret is available in the local vallt for a given service. Never exposes the raw value — only confirms availability.

vlt_list_integrations

List all connected integrations for the current project, with status and recommended next steps.

vlt_get_project_context

Fetch the full project context — build type, stack, connected integrations, recommended next. Call this at the start of a session to understand what

vlt_inject_env

Push all connected integration secrets into the project

vlt_validate_token

Check auth status and subscription tier. Surfaces an upgrade prompt if the free tier is exhausted. Run this after pasting a new API token.

vlt_health_check

Check whether connected integrations are still valid. Re-validates each key against its service and surfaces degraded tokens with specific remediation

vlt_scan_env

Scan .env files in the current directory for security issues: secrets not gitignored, test keys in production, unfilled placeholders, and services tha

vlt_import_env

Scan .env files in the current project, detect existing API keys for known services, validate them, and import them into Vallt in one shot. Use this w

vlt_disconnect_integration

Remove a connected integration from Vallt — deletes the keys from the OS keychain and frees up the integration slot. Use this to swap out a service or

Spec / packaging20%100
Security (OWASP MCP)30%70
Maintenance / popularity20%100
Tool hygiene15%95
Transparency / provenance15%30

Findings

INFO Static analysis of npm package @vallt/mcp-server@0.0.37 (stdio server — no remote endpoint). Reliability/behavioral signals require running it; not measured.
Grade another server

We re-grade npm:@vallt/mcp-server 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:@vallt/mcp-server grade B-
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 B- · wmcp.sh
[![MCP Trust Grade B-](https://wmcp.sh/mcp/grade/npm%3A%40vallt%2Fmcp-server/badge.svg)](https://wmcp.sh/mcp/grade/npm%3A%40vallt%2Fmcp-server)
<a href="https://wmcp.sh/mcp/grade/npm%3A%40vallt%2Fmcp-server"><img src="https://wmcp.sh/mcp/grade/npm%3A%40vallt%2Fmcp-server/badge.svg" alt="MCP Trust Grade B- · 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.