# Exeris AI Bridge

> Exeris AI Bridge is an open-source MCP server for developer tools. Read-only MCP server giving agents Exeris build output, SDK contract and ADR context. It runs locally on your machine and is started by your AI client.

- **Kind:** MCP server
- **Pricing:** Open source
- **Platforms:** CLI, self-hosted
- **Repository:** https://github.com/exeris-systems/exeris-ai-bridge
- **MCP Registry name:** io.github.exeris-systems/ai-bridge
- **Categories:** [developer tools](https://ai-powered.com/categories/developer-tools)
- **Listing updated:** 2026-11-18

## About

Exeris AI Bridge is aimed at developers writing an application on the Exeris Java platform. It runs as its own process, separate from the Java kernel, and every tool is a read: it never writes to the project and never calls a model API.

The 34 tools are grouped by family. build-* explains what the last build emitted and what a diagnostic means, caps-* reports the validated capability composition, sdk-* lists annotations and deprecations, docs-* serves ADRs, the architecture overview and the whitepaper, kernel-* inspects a running kernel, and lsp-* covers domain types from the Studio language server. A family whose dependency is missing returns a structured family_unavailable result with the reason and remedy.

It also publishes the ADR registry as markdown resources and nine prompt templates, such as draft-adr and diagnose-build-failure. Reference data ships inside the npm package, and nothing is fetched at run time.

## Features

- **34 read-only tools:** Tools are named family-tool and span build, caps, sdk, docs, kernel, lsp and bridge families.
- **ADR and docs access:** ADRs, the high-level architecture and the whitepaper are served from a checkout or a bundled snapshot.
- **Build introspection:** Explains emitted artefacts, detach state, diagnostics and generator previews for your project.
- **Resources and prompts:** ADR index and documents appear as markdown resources, plus nine stateless prompt templates.
- **Graceful degradation:** Missing dependencies produce a family_unavailable result naming the remedy.
- **Claude Desktop bundle:** An .mcpb package is attached to GitHub releases for Desktop users.

## Good for

- Ask an agent what a build diagnostic means
- Look up an ADR while reviewing a change
- Check which SDK annotations are deprecated before upgrading
- Draft a new ADR from the template and registry index
- Inspect a running kernel's providers and bootstrap graph

## Install

### Claude Code (Terminal)

```sh
claude mcp add ai-bridge -- npx -y @exeris/ai-bridge
```

### Claude Desktop (claude_desktop_config.json)

```json
{
  "mcpServers": {
    "ai-bridge": {
      "command": "npx",
      "args": [
        "-y",
        "@exeris/ai-bridge"
      ]
    }
  }
}
```

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

```json
{
  "mcpServers": {
    "ai-bridge": {
      "command": "npx",
      "args": [
        "-y",
        "@exeris/ai-bridge"
      ]
    }
  }
}
```

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

```json
{
  "servers": {
    "ai-bridge": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@exeris/ai-bridge"
      ]
    }
  }
}
```

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

```json
{
  "mcpServers": {
    "ai-bridge": {
      "command": "npx",
      "args": [
        "-y",
        "@exeris/ai-bridge"
      ]
    }
  }
}
```

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

```json
{
  "mcpServers": {
    "ai-bridge": {
      "command": "npx",
      "args": [
        "-y",
        "@exeris/ai-bridge"
      ]
    }
  }
}
```

## Tools

- `build-list_domains`
- `build-explain_diagnostic`: Explains what a build diagnostic means.
- `build-preview_generation`: Shows what the generator would write now.
- `caps-describe_composition`: Describes the capability composition your build validated.
- `sdk-list_annotations`
- `sdk-list_deprecations`
- `docs-list_adrs`
- `docs-get_adr`
- `docs-search`
- `kernel-list_providers`
- `kernel-get_bootstrap_dag`
- `lsp-preview_mutation`: Previews a source edit as a diff.
- `bridge-version`
- `bridge-health`

## FAQ

### What does the server need to run?

Node 20 or newer. The kernel-* tools also need JDK 25 or newer and the diagnostics CLI in your local Maven repository.

### Does it change my project?

No. Every tool is a read and the bridge never writes to the project.

### Does it need network access?

No. It reads artefacts already in ~/.m2 and never downloads.

### How is it installed in Claude Code?

Run claude mcp add exeris -- npx -y @exeris/ai-bridge from inside your project.

### Is Exeris AI Bridge free?

Yes. Exeris AI Bridge is open source, so you can use and self-host it for free.

### How do I add Exeris AI Bridge to Claude Code?

Run this command in your terminal: claude mcp add ai-bridge -- npx -y @exeris/ai-bridge

### What are the best alternatives to Exeris AI Bridge?

The closest alternatives to Exeris AI Bridge are REA, Context7, Chrome DevTools MCP, Codebase Memory and GitHub.

## Where this comes from

- Description: written from the project's README.
- 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.
- [Context7](https://ai-powered.com/mcp/context7): Context7 is a freemium MCP server for developer tools.
- [Chrome DevTools MCP](https://ai-powered.com/mcp/chrome-devtools-mcp-2): Chrome DevTools MCP is an open-source MCP server for browser automation.
- [Codebase Memory](https://ai-powered.com/mcp/codebase-memory): Codebase Memory is an open-source MCP server for knowledge and memory.
- [GitHub](https://ai-powered.com/mcp/github-2): GitHub is an open-source MCP server for developer tools.
- [Serena MCP: the IDE for your agent](https://ai-powered.com/mcp/serena-mcp-the-ide-for-your-agent): Serena MCP: the IDE for your agent is an open-source MCP server for developer tools.
- [awesome-mcp-servers](https://ai-powered.com/mcp/awesome-mcp-servers-2): awesome-mcp-servers is an open-source MCP server for developer tools.
- [XERJ](https://ai-powered.com/mcp/xerj): XERJ is an open-source MCP server for knowledge and memory.

---
Source: https://ai-powered.com/mcp/exeris-ai-bridge
