Greptile MCP
for LuumenAI

Search code, read reviews, and add review rules that stick across repositories.

Connect Greptile MCP and your agent can read the engineering context behind a change: code-review runs, pull request history, review findings by repository or author, and published knowledge-base documents. When a recurring review comment should become a standing rule, the agent drafts it and holds the write for your approval. Luumen authenticates with OAuth dynamic client registration.

Book a DemoDownload Luumen

The Greptile MCP toolbox

21 tools: 19 read, 2 write. Reads answer instantly. Writes require approval by default. Everything is logged.

  • ReadGet analytics overviewGet review analytics for repositories visible to the caller, optionally intersected by exact team, repository, and author filters.
  • ReadGet code reviewGet one code-review run by its stable id.
  • ReadGet custom contextGet one saved review rule or pattern and up to 10 linked review-comment references.
  • ReadGet knowledge base documentRead one current knowledge-base markdown document after listing its path.
  • ReadGet meIdentify the caller and discover the organizations available to other tools.
  • ReadGet merge requestGet one pull request or merge request with metadata, statistics, comments, up to 10 recent review records, and summary citations for the latest completed review.
  • ReadList analytics filter optionsList exact team names, repository names, or author logins available to the caller for analytics filters.
  • ReadList analytics findingsList review findings visible to the caller, newest first, with optional exact scope, severity, security, stored-addressed-status, text, and date filters.
  • ReadList code reviewsList code-review runs visible to the caller, newest first, optionally filtered by repository, PR number, or status.
  • ReadList custom contextList saved review rules and learned patterns visible to the caller, newest first.
  • ReadList knowledge base documentsList paths in one repository's current published knowledge base to map its documented subsystems before reading.
  • ReadList knowledge basesDiscover repositories with reachable Greptile knowledge-base data; start here before asking how an unfamiliar repository works.
  • ReadList merge request commentsList all matching comments for one pull request or merge request, newest first.
  • ReadList merge requestsList merge requests and pull requests visible to the caller, newest first.
  • ReadList pull requestsAlias of list_merge_requests with the same filters and result contract.
  • ReadList repositoriesList repositories visible to the caller in the selected organization, sorted by name.
  • ReadSearch custom contextSearch visible custom-context bodies by case-insensitive substring, newest matches first.
  • ReadSearch greptile commentsSearch Greptile-generated review comments by case-insensitive body substring across PR and CLI/headless reviews, newest first.
  • ReadSearch knowledge baseSearch one repository's current knowledge base for a case-insensitive substring when you know the term, symbol, endpoint, or convention to investigate.
  • WriteCreate custom contextCreate a persistent review rule or pattern in the selected organization. Approval by default
  • WriteTrigger code reviewRequest a new asynchronous Greptile review for an existing GitHub pull request or GitLab merge request. Approval by default

One prompt, start to finish

What a governed Greptile MCP run looks like inside Luumen.

Questions

How does LuumenAI connect to Greptile MCP?

Authorize once with OAuth 2.0. Luumen lists the scopes each action needs before you approve the connection, and credentials never appear in the chat.

Can LuumenAI change things in Greptile MCP on its own?

Read actions answer immediately. Anything that writes — create custom context, trigger code review — is shown as a plan and requires approval by default, including the 1 action classified as destructive. Administrators configure that per tool, so you decide exactly which actions can ever run unattended.

Who gets access to the integration?

You decide. Actions are granted per agent, skill, and team, and per environment — production is not staging. Read access can be broad while writes stay narrow.

Is there an audit trail?

Every call to Greptile MCP — read or write, approved or declined — is recorded with the actor, the input, and the result, and can be linked to the ticket or change record.

All integrations
Adobe Marketing Agent MCPAdobe Experience Platform context, sandbox switches, and async task statusAffindaRead parsed documents, collections, and annotations — change them with approvalAgent MailGive the agent its own mailbox for reading threads and sending updatesAI/ML APIInspect assistants, threads, and runs — and change them as approved steps

Put Greptile MCP to work with Luumen

Connect in minutes. Every action scoped, approved, and audited from day one.

Book a DemoDownload Luumen