# Coral — AI Coding Tool Review & Pricing

> Coral is an open-source, self-hosted gateway that sits between AI agents and the systems they work on. Agents connect over MCP and call provider tools by writing short TypeScript programs; Coral checks every call against workspace policy before adding credentials, and lets agents save programs that work as custom tools to reuse.

Source: https://ai.dosa.dev/tools/coral · Updated Nov 16, 2026 · Category: Developer Productivity & Workflow · Published by dosa.dev

## At a glance

- **Tool**: Coral
- **Company**: Coral
- **Category**: [Developer Productivity & Workflow](https://ai.dosa.dev/category/productivity)
- **Pricing model**: Open Source
- **Official website**: https://withcoral.com

## Key features

- One MCP URL for Claude Code, Codex, Cursor, VS Code, OpenCode and other MCP clients
- Agents write TypeScript programs that run in a V8 isolate with no network access, credentials or imports
- Allow, Ask or Block policy for each provider tool and custom tool, with per-call human approval
- Successful programs saved as private custom tools and published to the workspace as shared tools
- Credentials stored by Coral, with providers that can use each caller's own account
- Connects any service with an MCP server or OpenAPI document
- Desktop app for macOS, Windows and Linux, or a shared server via Docker Compose or Kubernetes
- Written in Rust; every run attributed to the person or agent that started it

## Pricing

**Model**: Open Source

Coral is free and open-source under the Apache 2.0 licence with no limits on users, agents or volume, run as a desktop app or on your own server. A separately licensed Coral Enterprise edition with SAML, SCIM, advanced RBAC, an immutable audit log and support SLAs is announced as coming soon.

## Who it is for

- **Best for**: Teams giving coding and operations agents access to GitHub, Slack, Linear, Datadog and internal APIs who want fine-grained permissions, approvals and reusable tools without handing agents raw tokens.
- **Not ideal for**: Solo users who only need a local MCP server or two, or organizations that need SSO, SCIM and an audit log today, since Coral Enterprise is not yet available.

## Verdict

A thoughtful step beyond MCP gateways that only filter tool lists, combining code mode, per-call policy and reusable custom tools in a self-hosted package.

## Recent updates

v1.8.0 was released on November 13, 2026, adding operator-defined Secret Stores for credentials, after v1.7.0 on November 12 and v1.6.0 on November 10; a Show HN post on November 16, 2026 reached the front page.

## Frequently asked questions

### Is Coral free?

Yes - Coral is Open Source. Coral is free and open-source under the Apache 2.0 licence with no limits on users, agents or volume, run as a desktop app or on your own server. A separately licensed Coral Enterprise edition with SAML, SCIM, advanced RBAC, an immutable audit log and support SLAs is announced as coming soon.

### Is Coral open source?

Yes - Coral is open source. Coral is free and open-source under the Apache 2.0 licence with no limits on users, agents or volume, run as a desktop app or on your own server. A separately licensed Coral Enterprise edition with SAML, SCIM, advanced RBAC, an immutable audit log and support SLAs is announced as coming soon.

### Who is Coral best for?

Teams giving coding and operations agents access to GitHub, Slack, Linear, Datadog and internal APIs who want fine-grained permissions, approvals and reusable tools without handing agents raw tokens.

### Who is Coral not ideal for?

Solo users who only need a local MCP server or two, or organizations that need SSO, SCIM and an audit log today, since Coral Enterprise is not yet available.

### What are the best Coral alternatives?

The closest Coral alternatives on ai.dosa.dev are Pieces for Developers, agenttrace, Vibe Kanban - all listed under Developer Productivity & Workflow.

### Who makes Coral?

Coral is developed by Coral. It is listed in the Developer Productivity & Workflow category on ai.dosa.dev.

## Top alternatives

- [Pieces for Developers](https://ai.dosa.dev/tools/pieces-for-developers) (Paid) — Developers who work across multiple tools, IDEs, and environments and need to maintain a persistent, searchable history of code snippets, research, and workflow context.
- [agenttrace](https://ai.dosa.dev/tools/agenttrace) (Open Source) — Developers and teams needing to monitor and debug the efficiency, cost, and health of AI coding agents across multiple workflows.
- [Vibe Kanban](https://ai.dosa.dev/tools/vibe-kanban) (Open Source) — Software engineers who use multiple AI coding agents and need a structured environment to manage, plan, and review their output in parallel.
- [ai-memory](https://ai.dosa.dev/tools/ai-memory) (Open Source) — Developers or teams using multiple AI coding agents who need consistent context and project history persistence across different tools, machines, and sessions.
- [smolvm](https://ai.dosa.dev/tools/smolvm) (Open Source) — Running isolated coding agent sandboxes, untrusted code, and persistent local development environments that require a real Linux kernel boundary.
- [coop](https://ai.dosa.dev/tools/coop) (Open Source) — Running autonomous AI coding agents that require broad system access while maintaining a strong security boundary for the host machine.
- Full alternatives guide: https://ai.dosa.dev/tools/coral/alternatives
