MCP Observatory
4m ago Tracked 56,807 Last 4m ago 24h 2,384
pypi Python analyzed 0.1.1

praisonai-mcp

v0.1.1
pypi

MCP server that exposes PraisonAI tools for Claude Desktop, Cursor, and other MCP clients

maintainer
—
licence
—
first seen
2026-08-13
last seen
2026-08-19
releases · 30d
2
short id
risk 47/100 · heuristic grade
C elevated inferred analyzer v33 (current)
  • capability exposure inferred + 35
  • tool safety inferred + 20
  • trust mitigators mixed − 8

inferred mixed

The A–E grade is our heuristic synthesis — a "review this" prompt, not a verdict. Each factor is tagged by what backs it: attested (a verifiable record), reported (a third party's claim), or inferred (our own heuristic, e.g. permissions). See methodology.

grade last moved 6d ago · see ecosystem CVEs →

capability exposure grade factor +35
Inferred surface — each links to servers holding it:
vulnerabilities 0 CVEs

No known CVEs for this server.

tool safety 7 findings · grade factor +20
  1. medium dangerous code

    dynamic exec: eval()/exec()

  2. medium toxic flow (lethal trifecta)

    lethal trifecta reachable across this server's tools: private-data access + untrusted-content ingestion + network exfil

  3. low exfiltration combo tavily_search

    single tool reads + sends: net, secrets

  4. low exfiltration combo exa_search

    single tool reads + sends: net, secrets

  5. low exfiltration combo ydc_search

    single tool reads + sends: net, secrets

  6. low exfiltration combo duckduckgo_search

    single tool reads + sends: net, secrets

  7. low exfiltration combo

    sensitive read and network capabilities split across this server's tools

skills & danger signals pypi-sdist
prompt-surface shipped agent-instruction files + hidden-content / dangerous-code findings — quoted from the analyzed source

analyzed v0.1.1 · analyzer v33 · 4w ago

danger signals1

  • dynamic code execution eval()/exec() praisonai_mcp-0.1.1/src/praisonai_mcp/tools.py :1156 exec(code, {"__builtins__": __builtins__}, local_vars)
embed badge readme-ready
live risk-grade badge preview [![MCP Observatory risk grade](https://mcpobservatory.com/servers/pypi:praisonai-mcp/badge.svg)](https://mcpobservatory.com/servers/pypi:praisonai-mcp/security)

Heuristic, inferred signals — false positives (legitimately powerful tools, forks, language ports) are expected. Treat each as "review this", not a verdict. See the ecosystem-wide picture on the security hub.