MCP.Market

Guardian MCP server

by OraclesTech·io.github.OraclesTech/guardian-mcp·v0.1.2

Runtime AI-threat screening for coding agents: analyze, scan tool calls/outputs & docs (paid).

C55/100grade C
What users say
No reviews yet
Be the first
Safety scan
C55/100

full report

Adoption
New

296 downloads/wk

Reviews

Write one

Nobody has reviewed Guardian yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Guardian tools (4)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • analyze

    Scan text for prompt injection, jailbreaks, data-exfiltration and related threats. `source_type` (e.g. 'document', 'tool_output', 'web_page') raises the weighting for untrusted sources. Returns Guardian's verdict + reasoning.

  • scan_documents

    Decode and scan documents at the ingestion boundary. Each item is {"filename": "...", "data": "<base64>"} (PDF/DOCX/PPTX/XLSX/RTF/TXT). Scans all and reports per-document verdicts; with `return_text=True`, also returns the server-side extracted safe text for API callers.

  • scan_tool_call

    Screen a tool/function call the model wants to make BEFORE you execute it — catches dangerous invocations (shell, package installs, exfiltration, destructive ops). Returns whether the call is dangerous + the recommended action.

  • scan_tool_output

    Screen a tool / API / RAG result BEFORE it re-enters the model's context — catches indirect (injection) payloads hidden in fetched content.

Public scan report

scanner v0.1.10 · 2026-10-01 · same rubric, same numbers if you re-run it

no findings
  • Code scan6 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitystatic API keys via environment variables6/15
  • Maintenancerepository not readable: unknown3/15
  • Maintainer identityno repository or website to verify2/10
Overall 55/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Guardian compares

Against every graded Productivity MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
55/100
higher than 9% of 1,299 Productivity servers
Tools
4
the typical Productivity server has 7
Tools that change things
0%
typical: 0%. Fewer write tools means less an agent can break
Downloads a week
296
more than 76% of 427 Productivity servers with a package

What its tools let an agent do: 4 read

Install Guardian in Claude Code, Cursor or VS Code

claude mcp add guardian-mcp -- uvx ethicore-guardian-mcp
Add to Cursor

Guardian: common questions

Is Guardian MCP server safe?
With care: it is graded C, so read the findings first (55/100). Read the Guardian safety report
How do I install Guardian?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Guardian need an API key?
Yes. The registry entry asks for ETHICORE_API_KEY, ETHICORE_SELFHOST_LICENSE.
Is Guardian maintained?
The latest release is v0.1.2.
What can I use instead of Guardian?
Servers from other publishers that do the same job: Tidewave Phoenix MCP server, WTFM MCP server and @imqueue MCP server.
How does Guardian compare with other Productivity MCP servers?
safety score 55/100 (higher than 9% of 1,299 Productivity servers); tools 4 (the typical Productivity server has 7); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to Guardian

Same job from other publishers: the closest match first, then the best rated.

  • Tidewave Phoenix
    Runtime-level MCP server for Phoenix development: run code, read logs, query the DB, read docs.
    B
  • WTFM
    Your coding agent writes the user docs from your codebase, screenshots included.
    A
  • @imqueue
    Search @imqueue docs and scaffold typed services & clients from your AI coding agent.
    A
  • Context7
    Up-to-date docs for AI agents
    A
  • Argent
    Drive iOS Simulators, Android emulators, TVs and Electron/web apps from your coding agent
    A