Skip to content
MCP server

Revelara

Reliability risk checks grounded in public incident reports, read from your coding agent

Pricing
Free trial
Platforms
Web, API, CLI
Runs
Remotely
Version
1.26.0
Listing updated
today

About Revelara

Revelara is an MCP server for developer tools. It runs as a hosted remote server, so there is nothing to install locally.

Revelara aims at the moment before a commit: it reads the change you are about to ship, flags reliability risks such as missing circuit breakers or retries without backoff, and ties many of them to a real public production incident. The MCP server is the evidence layer behind that, and the plugin README says all 22 tools only read data, scoped to your organisation.

It exposes a corpus of public incidents with links to original reports, your organisation's risk register with controls and evidence, a controls catalogue with STPA-inspired safety views, distilled knowledge, a graph linking incidents, technologies, services and controls, and a service catalogue of tiers, owners and dependencies.

Scanning is done by the rvl command-line scanner, which the README says runs locally so code stays on your machine, and by slash commands like /scan, /ask, /fix and /risks. Access needs a Revelara account and OAuth 2.1 sign-in. Deeper analysis levels, Correlate and Architect, cost more.

Install

Run in a terminal

claude mcp add --transport http mcp https://api.revelara.ai/mcp

Add to Settings → Connectors → Add custom connector

https://api.revelara.ai/mcp
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "mcp": {
      "url": "https://api.revelara.ai/mcp"
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "mcp": {
      "type": "http",
      "url": "https://api.revelara.ai/mcp"
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "mcp": {
      "serverUrl": "https://api.revelara.ai/mcp"
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "mcp": {
      "type": "http",
      "url": "https://api.revelara.ai/mcp"
    }
  }
}

What it does

Incident corpus
Public production incidents with links to the original reports.
Risk register
Your organisation's risks with mapped controls and evidence.
Controls catalogue
Reliability controls with STPA-inspired safety views.
Knowledge graph
Links incidents, technologies, services and controls.
Service catalogue
Tiers, owners, stacks and dependencies of your services.
Read-only tools
All 22 tools only read data, scoped to your organisation.

Good for

  • Check a code change for reliability risks before committing
  • Look up past outages that match a failure pattern
  • Review open risks for the current project
  • Find which controls apply to a service

Pricing

Free trial, from $99 a month

21-day trial; Startup $99/mo, Plus $499/mo, Growth $1,999/mo; depth add-ons cost more

Prices change. Check revelara.ai before you buy.

Revelara FAQ

Does my code leave my machine?

The README says the rvl scanner runs locally and code does not leave it.

How do I sign in?

The server uses OAuth 2.1 with dynamic client registration.

What does it cost?

Plans start at $99 a month for up to 5 users, with a 21-day free trial and no card required.

Which agents does it work with?

The site lists Claude Code, Cursor, GitHub Copilot, Gemini CLI, Codex, Windsurf, Cline and Goose among others.

Is Revelara free?

Revelara is a paid product with a free trial. Paid plans start at $99 a month.

How do I add Revelara to Claude Code?

Run this command in your terminal: claude mcp add --transport http mcp https://api.revelara.ai/mcp

What are the best alternatives to Revelara?

The closest alternatives to Revelara are REA, Codebase Memory, GitHub, Serena MCP: the IDE for your agent and XERJ.

Alternatives to Revelara

  1. REA

    MCP server

    CLI and MCP server that lets coding agents reverse engineer apps and binaries

    Runs locally
    • Open source
    • 464K GitHub stars
    • Developer tools
  2. Codebase Memory

    MCP server

    Local MCP server that builds a code knowledge graph for AI coding agents

    Runs locally
    • Open source
    • 48.7K GitHub stars
    • Knowledge and memory
  3. GitHub

    MCP server

    Official MCP server connecting AI assistants to GitHub repos, issues and workflows

    Not checked yet
    • Remote
    • Open source
    • 34.5K GitHub stars
    • Developer tools
  4. MCP toolkit giving coding agents symbol-level code retrieval and editing

    Runs locally
    • Open source
    • 31.5K GitHub stars
    • Developer tools
  5. XERJ

    MCP server

    Local search engine for AI agents with cited answers over your code and docs

    Runs locally
    • Open source
    • 19.2K GitHub stars
    • Knowledge and memory
  6. Ouroboros

    MCP server

    Spec-first layer that pins requirements and verifies results of AI coding agent work

    Runs locally
    • Open source
    • 6.4K GitHub stars
    • Developer tools