Scepter
Checks GitHub-hosted MCP servers by reading repository metadata such as last push, archived status, license, releases, stars, maintainers, and open issues to assess health and maintenance.
Checks npm-published MCP servers by reading package registry metadata such as last publish, maintainers, releases, and links back to source to assess health and maintenance.
Generates a copy-paste Markdown health badge for an MCP server using Shields.io badge URLs.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Scepterscan my mcp.json for risky or abandoned servers"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Scepter
Is this MCP server alive, maintained, and safe to use?

More than half of published MCP servers are already dead, and only a fraction of the tens of thousands out there are actively maintained. Developers wire them into their AI agents without knowing which ones are abandoned, unmaintained, or risky. Scepter answers that question in one command.
npx scepter-mcp check owner/repoInstall
# run without installing
npx scepter-mcp check <server>
# or install the command globally
npm install -g scepter-mcp
scepter check <server>Requires Node 18 or newer. No runtime dependencies.
Related MCP server: meok-mcp-injection-scan-mcp
Usage
Check one server, by GitHub repo or npm package:
scepter check owner/repo
scepter check https://github.com/owner/repo
scepter check some-mcp-server
scepter check @scope/nameScan every server in an MCP config file:
scepter scan ./mcp.json HEALTHY 88 owner/weather-mcp
CAUTION 61 another/mcp-thing
RISKY 22 abandoned/old-mcp
1 healthy 1 caution 1 riskyOptions:
Flag | Effect |
| read the target as a GitHub repo |
| read the target as an npm package |
| print JSON instead of a report |
| show help |
Set GITHUB_TOKEN in your environment to raise the GitHub API rate limit.
Exit code is 1 when the verdict is risky, so you can use Scepter in CI.
Add a health badge to your README
scepter badge owner/repoPrints a copy-paste Markdown badge:
[](https://github.com/owner/repo)See what your agent actually calls
Static checks tell you if a server looks healthy. wrap tells you how it really
behaves. Put Scepter in front of the real server in your MCP client config:
{
"mcpServers": {
"weather": {
"command": "npx",
"args": ["-y", "scepter-mcp", "wrap", "--", "npx", "-y", "@scope/weather-mcp"]
}
}
}Scepter forwards every byte unchanged, so your agent works exactly as before,
while recording each tool call, its result, timing, and any error locally under
~/.scepter. Then:
scepter report Recent MCP sessions (2)
SERVER CALLS ERR AVG SLOW
weather-mcp 42 3 88ms 310ms
files-mcp 17 0 12ms 40ms
Heads up
- weather-mcp failed 3 of 42 calls (last: "upstream timeout"). Check it: scepter check weather-mcpNothing leaves your machine.
What it checks (v1)
Signal | Reads |
Activity | last publish (npm) or last push (GitHub) |
Maintained | archived flag, license, releases, link back to source |
Provenance | stars, maintainers, open issues, description |
MCP fit | whether it declares itself an MCP server |
These come from registry and repository metadata. That is enough to answer the headline question honestly: is this server dead or alive, and is it worth trusting?
What it does not do (yet)
Scepter v1 does not run the server, complete a live MCP handshake, inspect the exact permissions it requests at runtime, or watch for unexpected network calls. Those are on the roadmap. Scepter never claims a server is "safe" or "undetectable", only what the metadata shows.
Roadmap
v1 — health and trust check from metadata (
check,scan,badge)v2 — see which servers your agent actually calls, and their failures (
wrap,report) (this release)v3 — full traces, per-task cost, and replay, with the health check as one view
License
MIT
This server cannot be deployed
Maintenance
Related MCP Connectors
Trust checks for MCP servers: trust scores, tool-drift detection, signed diligence receipts. Free.
Scan any MCP server for tool-poisoning, security, auth & license. Trust score before install.
Independent trust scores, tool surfaces and change history for MCP servers.
The MCP server that vets MCP servers: identity, risk grade and per-tool risk before you install.
Related MCP Servers
- AlicenseBqualityAmaintenanceFinds problems in your MCP servers before your users do. Scans your Claude config, checks every server's capabilities, actually calls tools to make sure they work, and catches breaking changes between versions.13866 npm146MIT
- AlicenseAqualityDmaintenanceScans MCP servers for prompt-injection, tool-poisoning, and SSRF vulnerabilities using 30+ canonical rules across 5 severity tiers, with optional signed safety reports for procurement.5MIT
- FlicenseNot gradedqualityFmaintenanceScans MCP servers for security hardening issues including capability declarations, transport, and tool descriptions.1-
- -licenseNot gradedqualityNot gradedmaintenanceAn MCP server that validates tool calls against JSON Schema, performs deterministic repair, redacts secrets, and maintains a hash-chained audit ledger.-