MCP NVD服务器
 
从国家漏洞数据库（NVD）检索CVE信息的MCP服务器。
安装
先决条件
安装以下部件。
建筑
\[！注意\] 该项目雇佣了 uv.- 同步依赖关系并更新锁文件。
uv sync调试
MCP检查员
使用 MCP检查员.
按如下方式启动MCP检查器：
npx @modelcontextprotocol/inspector uv --directory /path/to/mcp-nvd run mcp-nvd
测试
该项目雇佣了 pytest 用于测试。
pytest results
============================================================= test session starts =============================================================
platform win32 -- Python 3.12.9, pytest-8.3.5, pluggy-1.5.0
rootdir: D:\Users\ghays\src\mcp-nvd-server
configfile: pyproject.toml
plugins: anyio-4.9.0
collected 4 items
src/mcp_nvd/test_nvd.py::test_fetch_cve
---------------------------------------------------------------- live log call ----------------------------------------------------------------
2025-05-16 15:50:32 [ INFO] Fetching CVE: CVE-2025-30065... (nvd.py:42)
2025-05-16 15:50:33 [ INFO] Response: 200 (nvd.py:48)
2025-05-16 15:50:33 [ INFO] Description: Schema parsing in the parquet-avro module of Apache Parquet 1.15.0 and previous versions allows bad
actors to execute arbitrary code
Users are recommended to upgrade to version 1.15.1, which fixes the issue. (nvd.py:55)
2025-05-16 15:50:33 [ INFO] Using constructor method to fetch CVE data for CVE-2025-30065 (test_nvd.py:14)
2025-05-16 15:50:33 [ INFO] Description (en) value: Schema parsing in the parquet-avro module of Apache Parquet 1.15.0 and previous versions
allows bad actors to execute arbitrary code
Users are recommended to upgrade to version 1.15.1, which fixes the issue. (test_nvd.py:31)
2025-05-16 15:50:33 [ INFO] Description (es) value: El análisis del esquema en el módulo parquet-avro de Apache Parquet 1.15.0 y versiones anteriores permite que actores maliciosos ejecuten código arbitrario. Se recomienda a los usuarios actualizar a la versión 1.15.1, que soluciona el problema. (test_nvd.py:31)
2025-05-16 15:50:33 [ INFO] Reference check: https://lists.apache.org/thread/okzqb3kn479gqzxm21gg5vqr35om9gw5 (test_nvd.py:36)
PASSED [ 25%]
src/mcp_nvd/test_nvd.py::test_fetch_cve_no_constructor
---------------------------------------------------------------- live log call ----------------------------------------------------------------
2025-05-16 15:50:33 [ INFO] Fetching CVE: CVE-2025-30065... (nvd.py:42)
2025-05-16 15:50:34 [ INFO] Response: 200 (nvd.py:48)
2025-05-16 15:50:34 [ INFO] Description: Schema parsing in the parquet-avro module of Apache Parquet 1.15.0 and previous versions allows bad
actors to execute arbitrary code
Users are recommended to upgrade to version 1.15.1, which fixes the issue. (nvd.py:55)
2025-05-16 15:50:34 [ INFO] Using non-constructor method to fetch CVE data for CVE-2025-30065 (test_nvd.py:43)
PASSED [ 50%]
src/mcp_nvd/test_nvd.py::test_fetch_description
---------------------------------------------------------------- live log call ----------------------------------------------------------------
2025-05-16 15:50:34 [ INFO] Fetching CVE: CVE-2025-30065... (nvd.py:42)
2025-05-16 15:50:34 [ INFO] Response: 200 (nvd.py:48)
2025-05-16 15:50:34 [ INFO] Description: Schema parsing in the parquet-avro module of Apache Parquet 1.15.0 and previous versions allows bad
actors to execute arbitrary code
Users are recommended to upgrade to version 1.15.1, which fixes the issue. (nvd.py:55)
2025-05-16 15:50:34 [ INFO] Description for language 'en': Schema parsing in the parquet-avro module of Apache Parquet 1.15.0 and previous versions allows bad actors to execute arbitrary code
Users are recommended to upgrade to version 1.15.1, which fixes the issue. (test_nvd.py:69)
PASSED [ 75%]
src/mcp_nvd/test_nvd.py::test_fetch_references
---------------------------------------------------------------- live log call ----------------------------------------------------------------
2025-05-16 15:50:34 [ INFO] Fetching CVE: CVE-2025-30065... (nvd.py:42)
2025-05-16 15:50:34 [ INFO] Response: 200 (nvd.py:48)
2025-05-16 15:50:34 [ INFO] Description: Schema parsing in the parquet-avro module of Apache Parquet 1.15.0 and previous versions allows bad
actors to execute arbitrary code
Users are recommended to upgrade to version 1.15.1, which fixes the issue. (nvd.py:55)
2025-05-16 15:50:34 [ INFO] Reference URL: https://lists.apache.org/thread/okzqb3kn479gqzxm21gg5vqr35om9gw5 (test_nvd.py:82)
Users are recommended to upgrade to version 1.15.1, which fixes the issue. (nvd.py:55)
2025-05-16 15:50:34 [ INFO] Reference URL: https://lists.apache.org/thread/okzqb3kn479gqzxm21gg5vqr35om9gw5 (test_nvd.py:82)
Users are recommended to upgrade to version 1.15.1, which fixes the issue. (nvd.py:55)
2025-05-16 15:50:34 [ INFO] Reference URL: https://lists.apache.org/thread/okzqb3kn479gqzxm21gg5vqr35om9gw5 (test_nvd.py:82)
Users are recommended to upgrade to version 1.15.1, which fixes the issue. (nvd.py:55)
2025-05-16 15:50:34 [ INFO] Reference URL: https://lists.apache.org/thread/okzqb3kn479gqzxm21gg5vqr35om9gw5 (test_nvd.py:82)
Users are recommended to upgrade to version 1.15.1, which fixes the issue. (nvd.py:55)
Users are recommended to upgrade to version 1.15.1, which fixes the issue. (nvd.py:55)
2025-05-16 15:50:34 [ INFO] Reference URL: https://lists.apache.org/thread/okzqb3kn479gqzxm21gg5vqr35om9gw5 (test_nvd.py:82)
2025-05-16 15:50:34 [ INFO] Reference URL: http://www.openwall.com/lists/oss-security/2025/04/01/1 (test_nvd.py:82)
2025-05-16 15:50:34 [ INFO] Reference URL: https://access.redhat.com/security/cve/CVE-2025-30065 (test_nvd.py:82)
2025-05-16 15:50:34 [ INFO] Reference URL: https://github.com/apache/parquet-java/pull/3169 (test_nvd.py:82)
2025-05-16 15:50:34 [ INFO] Reference URL: https://news.ycombinator.com/item?id=43603091 (test_nvd.py:82)
2025-05-16 15:50:34 [ INFO] Reference URL: https://www.bleepingcomputer.com/news/security/max-severity-rce-flaw-discovered-in-widely-used-apache-parquet/ (test_nvd.py:82)
2025-05-16 15:50:34 [ INFO] Reference URL: https://github.com/h3st4k3r/CVE-2025-30065/blob/main/POC-CVE-2025-30065-ParquetExploitGenerator.java (test_nvd.py:82)
2025-05-16 15:50:34 [ INFO] Reference URL: https://github.com/mouadk/parquet-rce-poc-CVE-2025-30065/blob/main/src/main/java/com/evil/GenerateMaliciousParquetSSRF.java (test_nvd.py:82)
PASSED [100%]
============================================================== 4 passed in 2.74s ==============================================================