SECOPS
Enrich GitLab MR security labels with a policy MCP decision service
Sends each GitLab MR's changed-file set to a custom policy MCP server, applies the label and merge-gate verdict it returns.
How it runs
The automated pipeline, trigger to output.
- TriggerGitLab MR opened or updatedGitLab
- ActionCollect MR changed-file pathsGitLab
- ActionCall policy MCP server for label + verdictCustom MCP server
- ActionApply returned sec:: label to MRGitLab
- LogicBranch on verdict (allow/review/deny)
- OutputPost deny reason to security Teams channelMicrosoft Teams
What it does
This workflow externalizes the labeling decision to your own policy engine. When an MR opens or updates, it gathers the changed-file paths and calls a custom MCP policy server that owns your org's security ruleset. The server returns a label and a verdict (allow, review, deny); the flow applies the label to the MR and, on a deny verdict, posts to the security Teams channel with the policy reason.
When to use it
Use it when security policy is centrally owned and versioned outside the workflow, and you want every repo's labeling to call one source of truth instead of duplicating rules per pipeline.
How it works
- 1A GitLab MR webhook fires on open or update.
- 2The flow collects the MR's changed-file paths.
- 3It calls the custom policy MCP server with the paths and MR metadata.
- 4It applies the returned `sec::*` label to the MR.
- 5A branch checks the verdict.
- 6On a deny, it posts the policy reason and MR link to the security Teams channel.
Set it up
What you configure once, before turning it on.
- 1Connect GitLabRepos, MRs, pipelines, registry.
- 2Connect Custom MCP serverConnect any MCP-compatible tool you own.
- 3Connect Microsoft TeamsChannels, chats, files.
- 4Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
- 5Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
- 6Test, then turn it onRun once against a sample, confirm the output, then enable the trigger.
More SecOps workflows
Post-Revocation Verification and Audit Logging
After a key is revoked, it confirms the old credential actually fails, verifies the replacement works.
Page on-call when a WAF rule mass-blocks legitimate traffic
On demand or every few minutes, it detects a single Cloudflare WAF rule suddenly blocking a broad spread of ASNs and paths (a likely false-positive storm).
PII Content Scan on New Dropbox External Share
When a file gets an external Dropbox link, it reads the file content, uses an AI classifier to detect PII or secrets.
Compile a weekly WAF tuning review with trends to Confluence
Every week an agent rolls up Cloudflare WAF block clusters by rule and ASN, compares them to prior weeks for trend direction.
Sensitive Dropbox Link Owner Remediation Loop
When a newly created Dropbox shared link points to a sensitive file, this workflow DMs the file owner, gives them a deadline to justify or revoke it.
GitLab Push Secret Detection to Block and History Purge
On a GitLab push that contains a detected secret, it revokes the exposed credential, opens a tracking issue with git-history purge instructions.
Run it inside a business
This workflow drops into a full company template. Import the org, and this is one of the playbooks its agents run.
Run this workflow in your colony.
14-day trial. No DevOps. No Sales call. Provisioned in under a minute.