MCP.Market

Is Deepsleuth MCP server safe?

Probably. Read the findings first.

C55/100grade C

Use with care. Some checks failed or could not be verified.

What to know before installing
  • highWhole environment serialized (possible credential exfil)

How Deepsleuth compares

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

Safety score
55/100
higher than 12% of 4,460 AI and agents servers
Tools that change things
0%
typical: 0%. Fewer write tools means less an agent can break

What its tools let an agent do: 2 read

Public scan report

scanner v0.1.10 · 2026-10-13 · same rubric, same numbers if you re-run it

1 high2 medium
  • Code scan47 source files scanned3/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 6 days ago15/15
  • Maintainer identityregistry namespace matches repository owner6/10

Findings (3)

  • mediumsubprocess with shell=Trueexec.shell-true
    security_scanner_deepsleuth_mcp-1.0.4/deepsleuth/analysis/buildbackend.py: …n``/``os.exec*``, ``subprocess`` with ``shell=True`` or with a shell / downloader as arg…
  • mediumeval / new Function usedexec.eval
    security_scanner_deepsleuth_mcp-1.0.4/deepsleuth/analysis/constfold.py: …o] = {} self.steps = 0 def eval(self, node: ast.AST, loc: Dict[str, Any]…
  • highWhole environment serialized (possible credential exfil)env.dump
    security_scanner_deepsleuth_mcp-1.0.4/deepsleuth/analysis/envdump.py: …ronment -- ``str(dict(os.environ))``, ``json.dumps(dict(os.environ))``, a loop over ``os.environ.items()`` …
Overall 55/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

Other servers that do what Deepsleuth does

  • Agent Security Scanner
    Security layer for AI agents: blocks prompt injection, detects fake packages, scans vulnerabilities.
    C
  • HOL Guard
    Local-first AI agent security evidence and approval workflows through HOL Guard's stdio MCP server.
    A
  • Decionis Commerce Gate MCP
    Commerce preflights, D365 authorization; opt-in agent writes require authorized backend connectors.
    A

Deepsleuth reviews, tools and install