
cert-review
io.github.RaminNietzsche由 GitHub 帳號 RaminNietzsche 發布v1.2.0更新於 Nov 21, 2026
SEI CERT C/C++ code review: rule lookup, clang-tidy and cppcheck findings mapped to CERT rules
發布方自己的服務:Review Expert
概覽
本機 MCP 伺服器,用於 SEI CERT C/C++ 程式碼審查:規則查詢,並把 clang-tidy、cppcheck、Semgrep 結果對應到 CERT 規則編號。
- 可以做什麼
- 查詢、搜尋並依標準、語言、類別、等級與涵蓋度篩選 CERT C/C++ 規則與建議,含範例、風險列、CWE 標籤
- 對檔案、目錄或 diff 變更行執行 clang-tidy、Clang 靜態分析器、cppcheck 與內建 Semgrep 規則,可選用基線過濾
- 解釋單一發現:對應規則、最接近的合規/不合規範例對與修正步驟
- 產生審查包(程式碼片段與候選規則文字),並驗證發現必須引用真實規則編號與原文引述
- 將發現格式化為 markdown、GitHub、GitLab、SARIF 或 Code Quality 輸出
- 適用情境
- 需要依 SEI CERT、MISRA C:2012、MISRA C++:2023 或 AUTOSAR C++14 審查 C/C++ 變更,並希望分析器結果對應到具體規則編號時使用。適合 Ceph 專案(內建專用設定),也適合為人工或 LLM 輔助審查提供規則依據。
- 執行需求
- 以本機 stdio 程序執行,通常使用已發佈的 Docker 映像,或 Python 3.11+ 的原始碼檢出並安裝 mcp SDK。Docker 映像已內含 clang-tidy、cppcheck、Semgrep;本機安裝需自行準備。可靠解析通常需要 compile_commands.json。可選環境變數 CERT_REVIEW_HOME 及已授權的 MISRA/AUTOSAR 文字路徑。
安裝
在 SourceWeft 中
- 開啟 儀表板中的 cert-review,將其新增到工作區。
- 為需要使用其工具的對話啟用該服務。
Desktop only,透過 STDIO。 STDIO 服務會啟動本機處理程序,因此需要 SourceWeft 桌面主機。
其他 MCP 客戶端
參照 儲存庫 中的啟動說明。
README
cert-review-mcp
[cert-review MCP server – quality and maintenance score on Glama]
SEI CERT C and C++ code review as an MCP server, a CLI and two review skills, tuned for Ceph, with the same tools for MISRA C:2012, MISRA C++:2023 and AUTOSAR C++14 (docs/misra-autosar.md).
It does three things:
- Knows the standards.
data/rules.jsonholds every rule and recommendation of the SEI CERT C standard (122 rules, 183 recommendations) and every rule of the SEI CERT C++ standard (83 rules), with paired noncompliant/compliant examples, the risk row (severity, likelihood, detectable, repairable, priority, level), CWE tags and the automated-detection tables. It is built reproducibly from a pinned upstream commit and checked against the standards' own index pages. - Runs real analyzers and maps them to rule IDs. clang-tidy (
cert-*and mapped checks), the Clang Static Analyzer, cppcheck and 40 bundled Semgrep rules for INT, EXP, MEM, CON and other CERT rules; optionally Infer and the CodeQL CERT query packs (docs/analyzers.md). Findings are normalised to one schema, de-duplicated, filtered by a profile, and optionally limited to changed lines. - Prepares the rest for a manual review layer without letting it make things up. For rules
no checker covers,
build_review_packetselects code hunks and the few rule texts worth reading;validate_findingsrejects any finding that does not cite an existing rule ID and quote that rule's text. - Speaks MISRA and AUTOSAR too. A
standardfilter on every rule tool and astandardsselection for the checks (default: CERT only). Findings map to MISRA C:2012 (cppcheck MISRA addon), MISRA C++:2023 and AUTOSAR C++14 IDs. Their copyrighted texts are not bundled; you can load your licensed copy. See MISRA and AUTOSAR.
Comments are only drafted and formatted. Nothing is ever posted to GitHub or GitLab by this project.
Not an official CERT or CMU product. See NOTICE for attribution (CC BY 4.0 text, MIT examples) and the pinned source commit.
Architecture
[Architecture: data built by tools/, the engine in src/cert_review, and the MCP and CLI front ends]
The diagram source is in docs/architecture.md.
Coverage
Each rule is deterministic (a rule-specific checker exists: a clang-tidy cert-* check or a
CodeQL CERT query), partial (only general checkers or the bundled Semgrep pattern rules map)
or llm-only (no checker). The reference toolchain is what the Docker images run:
clang-tidy/clang 19.1.7, cppcheck 2.17.1 and Semgrep 1.186.0 with the bundled rules. The
extended toolchain adds Infer 1.3.0 and CodeQL 2.27 with the CERT packs 2.63.0, which are
optional and not in the images.
Before the Semgrep rules, the reference toolchain covered C rules 16 / 34 / 72 and C++ rules 18 / 29 / 36. A mapped checker is not a detection guarantee; the measured numbers follow.
MISRA C:2012 221 guidelines (131 / 28 / 62), MISRA C++:2023 178 (4 / 31 / 143), AUTOSAR C++14 397 (5 / 51 / 341); details and measurements in docs/misra-autosar.md.
Measured precision and recall on the CERT examples: docs/accuracy.md. Rule counts versus the official index pages: docs/rule-counts.md. Results on a real Ceph subtree: docs/ceph-trial.md.
Recall on real security fixes (Ceph CVEs and memory-safety fixes, curl, libtiff and others): docs/benchmark-real.md.
Install
The package reads data/ and profiles/ from the checkout (set CERT_REVIEW_HOME to point
elsewhere). Python 3.11+; works with the official mcp SDK 1.x (FastMCP, 1.15 or later) and 2.x (MCPServer).
Cursor
.cursor/mcp.json in your project (or ~/.cursor/mcp.json):
Then ask: "Use the cert-review ceph_review prompt on my current diff." Copy skills/ into your
skills folder to make the review procedure available.
Docker
Dockerfile.mcp builds the MCP server with the analyzers included (no local clang or
cppcheck needed). Mount your project at the same absolute path it has on the host:
The same mcpServers block works in Claude Desktop and Cursor. Release tags also publish
multi-arch images (amd64, arm64) to Docker Hub as
raminnietzsche/cert-review-mcp;
use raminnietzsche/cert-review-mcp:latest instead of cert-review-mcp to skip the build.
Details, the CLI from the image, and a tools/list check: docs/docker.md.
MCP Registry
The server is listed in the official MCP Registry
as io.github.RaminNietzsche/cert-review-mcp (server.json), so clients that read
the registry can install the Docker image from there.
Claude Code
Use as a GitHub Action
Diff mode on pull requests, SARIF, a job summary, and optional inline review comments
(review-comments: "true", off by default). A GitLab include template publishes Code Quality
and SAST reports. Inputs, outputs and examples: docs/action.md,
examples/github-workflow.yml.
MCP tools
Every tool is read-only: it reads local files and bundled data and runs local analyzers.
Nothing is written, uploaded or posted. All tools declare MCP annotations, a title and,
except format_findings, an output schema.
For check_diff and build_review_packet with pasted diff_text, files that are missing on
the MCP host are reconstructed from the patch under repo (the directory is created when needed).
On remote servers that cannot see your checkout, pass the unified diff and a logical root path
(for example /workspace/ceph); omit repo to use a disposable tree under the system temp
directory.
check_files and check_diff take an optional baseline_path: findings recorded in a
baseline file are hidden and counted (new, baselined, fixed). See docs/baseline.md.
MCP tool and parameter names changed after the v1 release; see CHANGELOG.md.
standard accepts cert (default), cert-c, cert-cpp, misra, misra-c-2012,
misra-cpp-2023, autosar, autosar-cpp14 or all.
Resources: rule://EXP34-C, profile://ceph. Prompts: cert_review, ceph_review.
CLI
--fail-on error|warning|note sets the exit code for CI; with --baseline only new findings count. Silence one rule on a line with
// cert-review: ignore EXP34-C reason.
Profiles
profiles/default.yaml is plain CERT. profiles/ceph.yaml encodes Ceph: C++23/C11,
priority and severity per rule, suppressions with reasons (ceph_assert, dout, crimson,
tests, vendored trees), and idioms (bufferlist, ceph::mutex, RefCountedObject, errno
returns, asio/seastar callbacks) that tell the reviewer how each project construct
changes a rule. Evidence for each idiom is cited inside the file.
profiles/misra.yaml and profiles/autosar.yaml select MISRA C:2012 + MISRA C++:2023 and
AUTOSAR C++14 (standards:), with severity taken from the guideline classification.
MISRA and AUTOSAR
The MISRA and AUTOSAR documents are copyrighted, so none of their guideline text is
included: only IDs, classification, AUTOSAR enforcement and target, checker mappings,
public SEI CERT cross-references and one-line summaries written for this project
(labelled as paraphrases). Point CERT_REVIEW_MISRA_C_TEXTS, CERT_REVIEW_MISRA_CPP_TEXTS,
CERT_REVIEW_AUTOSAR_TEXTS or a profile's rule_texts: at your licensed copy to see the
official headlines and to have validate_findings check quotes against them. Without it,
MISRA/AUTOSAR findings are accepted on a valid rule ID (grounding: "rule-id-only").
Mapping sources, measured results and file formats: docs/misra-autosar.md.
Rebuilding the data
Limitations
- Static coverage is thin by nature: most CERT rules are not decidable by tools; the
llm-onlyandpartialrules depend on the review layer and on a human. - Tools need compilable code. Without
compile_commands.jsonmany files do not parse and checks are skipped. The engine reports this instead of "no findings": the tool status becomespartial, the markdown, SARIF (executionSuccessful: falseplus atoolExecutionNotificationswarning), GitHub review, Action summary and CLI output carry a warning, and--fail-on-parse-error(alias--fail-on-partial; Action inputfail-on-parse-error) turns it into a failing exit code. A file on which an analyzer hits its 300 s timeout is treated the same way. - Ceph needs Linux. Its sources include Linux-only headers (
linux/version.h, ...) and Linux-only Boost.Asio features, so e.g.src/rgw/radosgw-admin/radosgw-admin.cccannot be parsed on macOS even with the SDK sysroot and Homebrew Boost. Analyse Ceph on Linux, with the Docker image, or with the GitHub Action.tools/ceph_compdb.pyadds-isysrooton macOS, which is enough for some directories (src/common) but not for all of them. - Mappings come from CodeChecker labels and clang-tidy aliases plus a small curated overlay; general analyzers can map to several rules, so the engine keeps the best few per line.
- Most MISRA C++ and AUTOSAR guidelines have no open-source checker; MISRA C coverage
depends on cppcheck's MISRA addon (needs
python3). - Ceph's profile is based on reading the code and on a limited trial, not on a full build.
License
Code: Apache-2.0 (LICENSE). Bundled CERT content: CC BY 4.0 (text) and MIT (examples); see NOTICE. MISRA and AUTOSAR: facts and original summaries only, no guideline text; see NOTICE and docs/misra-autosar.md.
來源:README.md,提交 63b3a81
工具
0版本歷史
1- v1.2.0最新Nov 21, 2026
評分
已滿足適用檢查項的 50%
該評分衡量此收錄條目的完整程度,依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價,也不表示伺服器安全或目前可用:可連通性是帶日期的檢查結果,評分也不包含安裝量或使用者評價。
- 近 30 天內可連通25 分
請保持端點能夠回應 MCP 握手;SourceWeft 每 30 天探測一次。
- 已宣告認證方式10 分
請在註冊中心條目中宣告憑證請求標頭,或保持端點能夠回應探測,以便判定其認證方式。
- 已列出工具15 分
請讓伺服器在無憑證時回應 tools/list,或發布可在沙箱中無憑證啟動的軟體包。
- 描述必需15 分
- 圖示10 分
- 文件15 分
- 授權條款10 分
其他 Review 整合

Review Expert
expert.review官方發布者
遠端 MCP 伺服器,經 OAuth 登入後讓助理讀取、搜尋與分析 App Store 和 Google Play 評論,並草擬回覆。

Trustpilot Review Alerts
由 GitHub 帳號 Berrkaydev 發布
一個託管在 Apify 上的遠端 MCP 伺服器,讓助理依公司設定 Trustpilot 新評論、商家回覆與評分變動的提醒。

Service isolation hardening review — Atom
org.aimlds
Service isolation hardening review — Atom 的託管 MCP 服務,由 aimlds.org 發布;需要憑證;Streamable HTTP。

Semantic html review — Atom
org.aimlds
Semantic html review — Atom 的託管 MCP 服務,由 aimlds.org 發布;需要憑證;Streamable HTTP。

Process waste review coaching — Atom
org.aimlds
Process waste review coaching — Atom 的託管 MCP 服務,由 aimlds.org 發布;需要憑證;Streamable HTTP。