← back
CVE-2026-57139criticalCWE-1188CWE-306CWE-862

PraisonAI MCPServer exposes unauthenticated HTTP tools/call

28Vexday Risk Score

No sign of exploitation. No public exploitation artifact known so far.

ssvc Trackcvss 9.8epss 0.4%
exploitation probability
0.4%top 64% of all CVEs
observed exploitation
nono source reports it
PraisonAI is a multi-agent teams system. From 1.5.0 until 1.7.2, MCPServer.startHttp() in src/praisonai-ts/src/mcp/server.ts binds without a host restriction and forwards every HTTP POST request to handleRequest() without authentication or authorization. Any network client that can reach the port can call tools/list, tools/call, resources/read, or prompts/get, causing registered handlers to run with server-side credentials and process privileges or disclose registered data. An initial remediation was released in version 1.7.2.
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H