Products
Developer tools
Give your agent the outages it never read.
Connect Revelara over the Model Context Protocol, and your agent can ground a reliability decision in evidence while it works: real incidents, your open risks, and the controls that address them.
Connect from Claude Code
$ claude mcp add --transport http revelara https://api.revelara.ai/mcp --header "Authorization: Bearer pk_live_YOUR_KEY"
IncidentsKnowledgeRisksControlsGraphCatalog
Six tool groups. Every tool is read-only, and every result is scoped to your organization.
What your agent can reach
One endpoint, six groups of tools. The agent picks the group by the question.
- Incidents. What has failed before, and how. Search the corpus, and find incidents similar to a scenario.
- Knowledge. Distilled facts and procedures, higher signal than raw incident text.
- Risks. Your organization’s open exposure, each risk with its mapped controls and evidence.
- Controls. What to implement, with an STPA-inspired view of how a control can fail.
- Graph. Causal chains across the corpus, and a contrast of two incident populations.
- Catalog. Your services: tier, owners, stack, and dependencies.
Read-only, and scoped to you
All tools are read-only, and every result is scoped to your organization. The agent can research. It cannot change your register.
Two ways to authenticate
Use an API key as a Bearer token with Claude Code and any MCP client that supports custom headers. On claude.ai, add Revelara as a custom connector and sign in with OAuth, with no key to handle.
It works with the agent you already use
Revelara installs over MCP, so it reaches your agent and your editor without a new place to log in. Included in every plan.
Works over MCP
Claude CodeCursorGitHub CopilotGoogle Gemini CLIOpenAI CodexWindsurfClineContinueGooseWarpand 12 more
Run your first scan free.
Install the CLI, scan a repo, and read the findings in your terminal. Your source code stays on your machine.