# Odin

> Odin is an MCP server for security. Read security findings, link fix pull requests and track retests from Odin. It can run locally on your machine or as a hosted remote server.

- **Kind:** MCP server
- **Platforms:** Web, API, CLI
- **Website:** https://docs.borghq.io/platform/odin-mcp
- **MCP Registry name:** io.github.BorgDevelopment/odin-mcp
- **Categories:** [security](https://ai-powered.com/categories/security)
- **Listing updated:** 2026-11-18

## About

Odin's server is about closing the loop on pentest and security findings, not just listing them. An agent can read a finding with remediation context, the suggested branch, linked pull requests, workflow blockers and the latest retest state, then link an existing GitHub PR and move the finding to Fixing, Open for Retest or Risk accepted. Retest history is read-only and never triggers a retest or spends credits.

The tool set also covers pentests, attack-surface assets, aggregate counts by severity and status, exports with revision content, assignee changes, and the discussion thread on each finding including Slack-synced messages.

Access is organisation-scoped. With OAuth sign-in you pick one organisation and either Read only or Read and write. The client acts as you, never beyond your role, tokens last an hour and unused connections expire after 30 days. Alternatively use an organisation API key with the npm package for stdio. Connected apps can be disconnected under Workspace settings.

## Features

- **Remediation context:** Get suggested branch, linked PRs, blockers and retest state.
- **Status updates:** Move findings to Fixing, Open for Retest or Risk accepted.
- **Link fix PRs:** Attach an existing GitHub pull request to a finding.
- **Retest history:** Read retest results without spending credits.
- **Finding discussions:** Read, post and resolve discussion messages.
- **Scoped access:** Choose read-only or read and write per connection.

## Good for

- Ask an agent which critical findings are still open
- Link a fix pull request and mark a finding ready for retest
- Export findings for a repository
- Summarize unresolved discussions on findings
- Check the scope and schedule of a pentest

## Install

### Claude Code (Terminal)

```sh
claude mcp add --transport http odin-mcp https://odin.borghq.io/api/mcp
```

### Claude Desktop (Settings → Connectors → Add custom connector)

```sh
https://odin.borghq.io/api/mcp
```

### Cursor (~/.cursor/mcp.json)

```json
{
  "mcpServers": {
    "odin-mcp": {
      "url": "https://odin.borghq.io/api/mcp"
    }
  }
}
```

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "odin-mcp": {
      "type": "http",
      "url": "https://odin.borghq.io/api/mcp"
    }
  }
}
```

### Windsurf (~/.codeium/windsurf/mcp_config.json)

```json
{
  "mcpServers": {
    "odin-mcp": {
      "serverUrl": "https://odin.borghq.io/api/mcp"
    }
  }
}
```

### Other clients (your client's MCP settings (most use this shape))

```json
{
  "mcpServers": {
    "odin-mcp": {
      "type": "http",
      "url": "https://odin.borghq.io/api/mcp"
    }
  }
}
```

## Tools

- `list_findings`: List findings with status, severity, repository and assignee.
- `get_finding`: Return remediation context, suggested branch, linked PRs and retest state.
- `update_finding_status`: Move a finding to Fixing, Open for Retest or Risk accepted.
- `link_finding_pull_request`: Link an existing GitHub pull request to a finding.
- `get_finding_retests`: Read retest history without triggering one.
- `list_pentests`: List the organisation's pentests.
- `get_pentest`: Fetch a pentest's status, schedule and scope.
- `list_assets`: List attack-surface assets.
- `get_asset`: Fetch an asset and the findings that reference it.
- `get_finding_stats`: Aggregate counts by severity and status.
- `export_findings`: Export matching findings with revision content.
- `assign_finding`: Assign a member or clear the assignee.
- `get_finding_discussion`: Read discussion blocks and messages.
- `create_finding_message`: Post a discussion message.
- `edit_finding_message`: Edit a message you authored.
- `delete_finding_message`: Delete a message you authored.

## FAQ

### How do I sign in?

Use OAuth sign-in with your Odin account, or an organisation API key created under Workspace > API Keys.

### Can the client change findings?

Only if you grant Read and write; otherwise access is read-only.

### Does it create pull requests?

No. It links one existing accessible GitHub PR and does not create or change it.

### How long do tokens last?

Access tokens last an hour and a connection unused for 30 days expires.

### How do I add Odin to Claude Code?

Run this command in your terminal: claude mcp add --transport http odin-mcp https://odin.borghq.io/api/mcp

### What are the best alternatives to Odin?

The closest alternatives to Odin are REA, AiSOC, redamon, x64dbg-mcp-server and Agent Roast.

## Where this comes from

- Description: written from the project's website.
- Install steps: from the official MCP Registry entry.

## Alternatives

- [REA](https://ai-powered.com/mcp/rea): REA is an open-source MCP server for developer tools.
- [AiSOC](https://ai-powered.com/mcp/aisoc): AiSOC is an open-source MCP server for ai models and llm tooling.
- [redamon](https://ai-powered.com/mcp/redamon): redamon is an open-source MCP server for ai models and llm tooling.
- [x64dbg-mcp-server](https://ai-powered.com/mcp/x64dbg-mcp-server): x64dbg-mcp-server is an open-source MCP server for ai models and llm tooling.
- [Agent Roast](https://ai-powered.com/mcp/agent-roast): Agent Roast is an open-source MCP server for developer tools.
- [Midplane](https://ai-powered.com/mcp/midplane): Midplane is an open-source MCP server for databases.
- [Leash](https://ai-powered.com/mcp/leash): Leash is a free MCP server for security.
- [Cisa Kev](https://ai-powered.com/mcp/cisa-kev): Cisa Kev is a freemium MCP server for security.

---
Source: https://ai-powered.com/mcp/odin
