Lucene search
+L

16 matches found

Kitploit
Kitploit
•added 2026/10/04 3:54 a.m.•19 views

http-mcp-bridge

HTTP MCP Bridge 이 프로젝트는 mcp 파이썬 라이브러리GitHub를 사용하여 HTTP/1.1 요청과 원격 MCP 서버 간의 브리지 역할을 하는 HTTP 서버를 구현합니다. 이 이니셔티브의 주요 목적은 원격 전송 메커니즘HTTP+SSE 또는 Streamable HTTP을 사용하는 원격 MCP 서버를 테스트하기 위해 HTTP 보안 도구를 사용할 수 있게 하는 것입니다. 중요 참고 사항! 동일한 id를 가진 JSON-RPC-V2 메시지를 동시 스레드로 전송할 때 응답이 병합될 수 있다는 것이 관찰되었습니다. 평가 시 도...

6.3AI score
SaveExploits0References1
CVE
CVE
•added 2026/09/22 6:11 p.m.•25 views

CVE-2026-77254

The mcp-atlassian Model Context Protocol server (versions prior to 0.22.0 ) contains a vulnerability where unauthenticated HTTP MCP requests can bypass per-user identity checks. The flaw allows a network caller to reach tool handlers that utilize globally configured Jira and Confluence credential...

9.1CVSS5.9AI score0.0062EPSS
SaveExploits1References4Affected Software1
EUVD
EUVD
•added 2026/09/22 6:11 p.m.•11 views

EUVD-2026-84743

MCP Atlassian is a Model Context Protocol MCP server for Atlassian products Confluence and Jira. Prior to 0.22.0, requests to the HTTP MCP endpoint without a per-user identity are allowed to reach tool handlers, which then use globally configured Jira or Confluence credentials. A network caller c...

9.1CVSS5.9AI score0.0062EPSS
SaveExploits1References4
Vulnrichment
Vulnrichment
•added 2026/09/22 6:11 p.m.•11 views

CVE-2026-77254 MCP Atlassian: Unauthenticated HTTP MCP requests can use globally configured Jira and Confluence credentials

MCP Atlassian is a Model Context Protocol MCP server for Atlassian products Confluence and Jira. Prior to 0.22.0, requests to the HTTP MCP endpoint without a per-user identity are allowed to reach tool handlers, which then use globally configured Jira or Confluence credentials. A network caller c...

9.1CVSS5.9AI score0.0062EPSS
SaveExploits1References4
Cvelist
Cvelist
•added 2026/09/22 6:11 p.m.•41 views

CVE-2026-77254 MCP Atlassian: Unauthenticated HTTP MCP requests can use globally configured Jira and Confluence credentials

MCP Atlassian is a Model Context Protocol MCP server for Atlassian products Confluence and Jira. Prior to 0.22.0, requests to the HTTP MCP endpoint without a per-user identity are allowed to reach tool handlers, which then use globally configured Jira or Confluence credentials. A network caller c...

9.1CVSS0.0062EPSS
SaveExploits1References4
OSV
OSV
•added 2026/09/22 6:11 p.m.•9 views

CVE-2026-77254 MCP Atlassian: Unauthenticated HTTP MCP requests can use globally configured Jira and Confluence credentials

MCP Atlassian is a Model Context Protocol MCP server for Atlassian products Confluence and Jira. Prior to 0.22.0, requests to the HTTP MCP endpoint without a per-user identity are allowed to reach tool handlers, which then use globally configured Jira or Confluence credentials. A network caller c...

9.1CVSS5.8AI score
SaveExploits0References6
Rapid7 Vulnerability Database (full)
Rapid7 Vulnerability Database (full)
•added 2026/09/22 12:00 a.m.•12 views

CVE-2026-77254: Missing Authentication for Critical Function

MCP Atlassian is a Model Context Protocol MCP server for Atlassian products Confluence and Jira. Prior to 0.22.0, requests to the HTTP MCP endpoint without a per-user identity are allowed to reach tool handlers, which then use globally configured Jira or Confluence credentials. A network caller c...

9.1CVSS5.9AI score0.0062EPSS
SaveExploits1References6
Cvelist
Cvelist
•added 2026/09/15 3:18 p.m.•34 views

CVE-2026-91988 atomic-agents-stack before 1.1.0 Remote Code Execution via HTTP MCP

atomic-agents-stack before 1.1.0 accepts cleartext HTTP schemes in the HTTP MCP server-registry backend factory, allowing network man-in-the-middle attackers to rewrite catalog responses. Attackers can inject arbitrary command and argument values that are spawned as local subprocesses by...

9.2CVSS0.00318EPSS
SaveExploits0References2
Rapid7 Vulnerability Database (full)
Rapid7 Vulnerability Database (full)
•added 2026/09/15 12:00 a.m.•4 views

CVE-2026-61568: Reliance on Reverse DNS Resolution for a Security-Critical Action

@zereight/mcp-gitlab is a Model Context Protocol server for GitLab. Versions prior to 2.1.30 expose the Streamable HTTP MCP endpoint without an effective Host or Origin allowlist. A malicious web page can use DNS rebinding to route browser requests to a victim's local MCP listener while preservin...

9.6CVSS5.8AI score0.00532EPSS
SaveExploits1References2
Rapid7 Vulnerability Database (full)
Rapid7 Vulnerability Database (full)
•added 2026/09/15 12:00 a.m.•4 views

CVE-2026-91988: Cleartext Transmission of Sensitive Information

atomic-agents-stack before 1.1.0 accepts cleartext HTTP schemes in the HTTP MCP server-registry backend factory, allowing network man-in-the-middle attackers to rewrite catalog responses. Attackers can inject arbitrary command and argument values that are spawned as local subprocesses by...

9.2CVSS6.2AI score0.00318EPSS
SaveExploits0References2
Github Security Blog
Github Security Blog
•added 2026/08/17 9:49 p.m.•20 views

atomic-agents-stack: HTTP MCP catalog accepts cleartext http and spawns catalog-supplied commands (MITM to RCE)

The HTTP MCP server-registry backend factory atomicagents/mcpregistry/http.py, makehttpmcpserverregistrybackendfromurl accepts both http and https schemes. Catalog entries carry command/args that are type-validated but content-unrestricted, and are later spawned as local stdio subprocesses by...

6.2AI score
SaveExploits0References3Affected Software1
OSV
OSV
•added 2026/07/13 3:46 p.m.•21 views

PYSEC-2026-2482 flyto-core has Unauthenticated Command Execution via HTTP MCP `execute_module`

Unauthenticated Command Execution via HTTP MCP executemodule Summary The HTTP MCP endpoint POST /mcp in flyto-core accepts unauthenticated JSON-RPC tools/call requests and dispatches them to arbitrary registered modules, including sandbox.executeshell, which passes attacker-controlled input...

8.4CVSS6.5AI score
SaveExploits0References5
CVE
CVE
•added 2026/06/19 5:59 p.m.•72 views

CVE-2026-49291

mcp-memory-service (semantic memory layer for AI apps) exposed the HTTP MCP JSON-RPC endpoint at /mcp such that OAuth read scope allowed mutating actions. Before patch 10.65.3, a read-only OAuth client could invoke tools/call to reach store_memory and delete_memory, bypassing REST write scope che...

8.1CVSS5.7AI score0.00488EPSS
SaveExploits0References3
Rapid7 Vulnerability Database (full)
Rapid7 Vulnerability Database (full)
•added 2026/06/19 12:00 a.m.•1 views

CVE-2026-49291: Missing Authorization

mcp-memory-service is a semantic memory layer for AI applications. Prior to version 10.65.3, the HTTP MCP JSON-RPC endpoint at /mcp requires only OAuth read scope for all requests, then dispatches tools/call directly to handlers that include mutating tools. A read-only OAuth client can call...

8.1CVSS5.7AI score0.00488EPSS
SaveExploits0References2
attackerkb
attackerkb
•added 2026/06/18 9:01 p.m.•30 views

CVE-2026-49257

mcp-pinot is a Python-based Model Context Protocol MCP server for interacting with Apache Pinot. In versions 3.0.1 and below, mcp-pinot defaults to running an HTTP MCP server bound to 0.0.0.0:8080 with no authentication enabled. All MCP tools, including SQL query execution, schema creation, and...

10CVSS5.6AI score0.0093EPSS
SaveExploits0References5Affected Software1
Rapid7 Vulnerability Database (full)
Rapid7 Vulnerability Database (full)
•added 2026/06/16 12:00 a.m.•1 views

CVE-2026-53840: Insufficiently Protected Credentials

OpenClaw before 2026.5.12 contains an information disclosure vulnerability in streamable-http MCP servers that forwards operator-configured custom headers during cross-origin redirects. Attackers controlling or compromising an MCP endpoint can redirect requests to exfiltrate sensitive headers lik...

7.1CVSS5.8AI score0.0031EPSS
SaveExploits0References4
Rows per page
Query Builder