What it does
The server checks CI pipeline files for GitHub Actions, GitLab CI/CD, Jenkins, CircleCI, Azure Pipelines, Bitbucket Pipelines and Travis CI. It traces untrusted event data, such as pull request titles, branch names and commit messages, into shell or script steps, including when the value passes through step outputs, environment variables, matrix values or reusable-workflow inputs. It also flags privileged workflows that check out fork code, overly broad token permissions, secrets exposed to untrusted triggers, third-party actions pinned to mutable tags, self-hosted runners reachable from public pull requests, remote or moving-ref includes, and artifact or cache poisoning. A separate detector reviews OIDC trust policies in Terraform, CloudFormation, GCP and Azure definitions and correlates them with the CI workflows. Results are given as a CRITICAL, VULNERABLE, RISKY or HARDENED verdict with the specific flaws.
It suits reviews of CI configuration before a pull or merge request from an outside contributor can run with repository secrets, and checks that a standard YAML linter does not perform. It can be used from MCP-compatible agents such as Claude or Cursor, or through its HTTP API.
To run it, supply the pipeline files; each is routed automatically to the analyzer for its CI system. The HTTP API is billed per call.
Limitations and requirements
The HTTP API is pay-per-call and is paid either in x402 USDC or with a prepaid card key.
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
io.github.Baneado98/ci-sentinel
Multi-CI security scanner with a live threat-intel feed of compromised CI components
v0.1.0As shown on registry.modelcontextprotocol.io when we last read it