MCP servers · barglabs

Cejel: offline engineering-trust certificates for repositories

An offline, deterministic tool that scores a repository's engineering-trust signals and issues a certificate pinned to one commit.

This text was machine-translated from the publisher's own information and has not been checked by a human editor. The publisher's original text is the reference.

This resource was imported automatically from the sources listed below and has not been reviewed by the AI Gate team yet. The description is the publisher's own, as published. Check the repository before installing.

What it does

Cejel reads a repository's own evidence, such as whether tests assert something, whether secrets are committed, and whether CI gates changes, and writes a certificate pinned to one commit. Its scoring core is deterministic and uses no LLM. The publisher states that the free path makes no network calls and needs no account. It can also aggregate SARIF-compatible output from other scanners, together with OpenSSF Scorecard, into a single certificate and badge.

It is suited to repositories where much of the code was written by AI, where trust is hard to judge by reading. It also fits cases where a customer, buyer or acquirer needs to check a result independently: the recipient can run the same version on the same commit, offline, and get the same output. Results are reported as what holds, what is wrong, and what could not be established. The publisher says it scores trust signals and does not detect software defects or prove code is safe; defect and vulnerability scanners remain separate evidence sources.

It runs from a shell with npx against a directory, or as a GitHub Action whose result is posted to the job summary. The Action needs full git history, so checkout must not be shallow.

Limitations and requirements

A shallow clone is rated Unrated, with no score or verdict, until the full history is checked out. A directory without a .git folder, such as an uploaded snapshot or archive, is also rated Unrated. The tool does not claim to detect defects or prove code is safe. The public default rubric is fixed, and later rubrics are available only to explicit evaluation harnesses.

Safety

Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.

  • Runs code or changes an assistant's behaviour

Sources

  • Official MCP Registry first seen 13 Nov 2026 · last seen 13 Nov 2026 · its page on the source
    Cejel

    Offline deterministic engineering-trust certificates for repositories, with no telemetry.

    v0.6.11
    As shown on registry.modelcontextprotocol.io when we last read it
MCP servers
awslabs

MCP servers for AWS (AWS Labs)

A large open-source collection of MCP servers from AWS Labs for building and operating on AWS: documentation, infrastructure, databases, AI services, cost and more.

9.9K GitHub starsCloud & DevOpsData & databases
Updated 17 Nov 2026
MCP servers
microsoft

Playwright MCP (browser automation)

Microsoft's MCP server that lets an AI assistant open web pages, click, type and read them through a real browser, using the page structure instead of screenshots.

39.6K GitHub starsTesting & QAWeb, search & browser
Updated 17 Nov 2026
MCP servers
docker

Docker Hub MCP Server

Docker's MCP server that helps an AI assistant find and compare container images on Docker Hub and, with your token, manage your own repositories and tags.

171 GitHub starsCloud & DevOpsSoftware development
Updated 13 Nov 2026
MCP servers
cloudflare

Cloudflare MCP servers

Cloudflare's hosted MCP servers for its products: documentation search, sandbox containers, browser rendering, Radar internet data, logs and analytics, Workers and more.

4.5K GitHub starsCloud & DevOpsSoftware development
Updated 17 Nov 2026