How do I install D'AUBE // BRIDGE²?

Copy the stdio config for Cursor, Claude Desktop, Claude Code, or VS Code on this page. It uses the publisher's install, not a PlugMCP proxy.

Does D'AUBE // BRIDGE² need an API key?

No required environment variable is listed on this record.

What transport does D'AUBE // BRIDGE² use?

D'AUBE // BRIDGE² runs locally over stdio.

When was D'AUBE // BRIDGE² last checked?

Last checked 2026-11-09. Universal AI skill compiler and MCP bridge. Write once, run across agents.

D'AUBE // BRIDGE² MCP server

Power your agent

Add this server

The publisher's own command. Not a PlugMCP endpoint.

Add to Cursor Add to VS Code Run on PlugMCP

Host a copy with our keys and logs.

Local command

mcpb https://github.com/daubesonntag-dotcom/daube-agent-bridge/releases/download/v0.1.3/daube-agent-bridge-0.1.3.mcpb

Claude Code has no install link for a local command. Copy the command below and run it in a terminal.

shClaude Code

1claude mcp add io.github.daubesonntag-dotcom-daube-agent-bridge -- mcpb https://github.com/daubesonntag-dotcom/daube-agent-bridge/releases/download/v0.1.3/daube-agent-bridge-0.1.3.mcpb

Run in a terminal.

jsonClaude Desktop

1{2  "mcpServers": {3    "io.github.daubesonntag-dotcom-daube-agent-bridge": {4      "command": "mcpb",5      "args": [6        "https://github.com/daubesonntag-dotcom/daube-agent-bridge/releases/download/v0.1.3/daube-agent-bridge-0.1.3.mcpb"7      ]8    }9  }10}

claude_desktop_config.json

Local · mcpbPublisher installStep-by-step: add this in Claude

Remote URL or a command on your machine? How the two installs differ

Run on PlugMCP

Host a copy with our keys and logs.

A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.

Launch

Server facts

Local

Transport: stdio
Version: 0.1.3
Last checked

Tools

No tool list yet. Remote servers get one after the first health check.

FAQ

Questions

D'AUBE // BRIDGE²

Write once. Run across agents.

D'AUBE // BRIDGE² is an open-source universal AI skill compiler and MCP bridge. Define one portable capability spec, then compile it into integration artifacts for ChatGPT/Codex, Claude, Gemini, DeepSeek, Meta/Llama, MCP hosts, and Chromium browsers.

External review

On 2026-09-18, the BRIDGE² deployment record was AI Deploy Network Approved after review of the submitted implementation evidence. This means the deployment record passed AI Deploy Network review; it is not a client-confirmed commercial outcome or a guarantee of production performance.

The canonical publication narrative is maintained in docs/AI_DEPLOY_CASE_STUDY.md. The reviewed case study is now publicly available on AI Deploy Network.

Why BRIDGE²

AI tooling is fragmented. The same capability is repeatedly rewritten as MCP tools, provider function schemas, skills, plugins, and browser configuration. BRIDGE² treats those surfaces as compiler targets while keeping capability logic provider-neutral.

skill.yaml
  |
  +-- MCP tool schema
  +-- OpenAI / ChatGPT / Codex artifacts
  +-- Claude plugin + SKILL.md
  +-- Gemini SKILL.md + MCP config
  +-- DeepSeek tool schemas
  +-- Meta/Llama function schemas
  +-- Chromium extension manifest

Current release: 7 target families, 15 deterministic artifacts, one MCP server.

30-second start

git clone https://github.com/daubesonntag-dotcom/daube-agent-bridge.git
cd daube-agent-bridge
python -m pip install -e ".[dev]"
daube-bridge validate examples/skill.yaml
daube-bridge compile examples/skill.yaml -o build/sample

Install the verified v0.1.3 wheel directly from GitHub Releases:

python -m pip install https://github.com/daubesonntag-dotcom/daube-agent-bridge/releases/download/v0.1.3/daube_agent_bridge-0.1.3-py3-none-any.whl
python -m daube_bridge doctor

python -m daube_bridge ... is the shim-free CLI path for Windows environments where Application Control blocks generated console-script executables.

Run BRIDGE² as a local stdio MCP server:

python -m daube_bridge.server

Or expose the HTTP MCP endpoint for remote/local integrations:

daube-bridge serve
# http://127.0.0.1:8000/mcp

One-click MCPB

BRIDGE² ships an MCPB v0.4 bundle definition using the cross-platform uv runtime. Build the deterministic bundle with:

python scripts/build_mcpb.py

The build is reproducible: identical source produces an identical archive hash. Official MCP Registry metadata lives in server.json.

Target matrix

Surface	Output	Strategy
MCP hosts	MCP server + tool schemas	Shared transport/tool backbone
OpenAI / ChatGPT / Codex	`SKILL.md`, MCP descriptor, function schemas	Skills + MCP/tool calling
Claude	`.claude-plugin/plugin.json`, `.mcp.json`, `SKILL.md`	Plugin + portable skill + MCP
Gemini / Google agents	`SKILL.md`, MCP config	Portable skill + MCP
DeepSeek	OpenAI-style `tools.json`	Function/tool calling adapter
Meta / Llama	neutral `tools.json`	Application/router function schema
Chromium browsers	Manifest V3 side panel	Endpoint/config control surface

This matrix describes integration artifacts BRIDGE² generates. It does not invent provider capabilities that do not exist.

Portable skill format

name: My Research Skill
version: 0.1.0
description: Research and compare options.
tools:
  - name: compare_options
    description: Compare options against explicit criteria.
    parameters:
      type: object
      properties:
        options:
          type: array
          items: {type: string}
      required: [options]

MCP tools

The bundled server exposes three small primitives:

bridge_targets — discover supported compilation targets.
validate_skill — validate a portable skill object.
compile_skill — compile a skill in-memory for another agent or tool.

That makes BRIDGE² usable both as a CLI and as infrastructure callable by other agents.

Verify before release

python scripts/verify.py
python scripts/build_mcpb.py
.tools/mcp-publisher.exe validate

The verification gate covers tests, Ruff, target discovery, sample compilation, wheel creation, deterministic MCPB creation, and official MCP Registry metadata validation.

After publishing a GitHub Release, smoke-test the public wheel in an isolated environment:

python scripts/smoke_release.py 0.1.3

Roadmap

ChatGPT Apps SDK interactive widget target.
npx / TypeScript compiler parity.
Provider capability detection and compatibility linting.
Signed bundles and provenance manifests.
Remote registry + searchable skill catalog.
One-click adapters for agent IDEs and orchestration frameworks.
Golden interoperability fixtures across providers.

Project principles

Portable by default. Prefer MCP and open schemas over provider lock-in.
Evidence over pretending. Never claim native support that a provider does not have.
Readable outputs. Generated artifacts stay human-auditable and diffable.
Safe boundaries. Authentication and sensitive actions remain explicit.
Fast adoption. A useful first result should take minutes, not a framework migration.

Contributing

Issues, adapters, compatibility fixtures, docs, and provider integrations are welcome. Provider-format changes should include a link to authoritative documentation and a minimal reproducible fixture.

Useful starting points:

D'AUBE // BRIDGE²

Add this server

Host a copy with our keys and logs.

Server facts

Tools

Questions

How do I install D'AUBE // BRIDGE²?

Does D'AUBE // BRIDGE² need an API key?

What transport does D'AUBE // BRIDGE² use?

When was D'AUBE // BRIDGE² last checked?

Documentation

D'AUBE // BRIDGE²

External review

Why BRIDGE²

30-second start

One-click MCPB

Target matrix

Portable skill format

MCP tools

Verify before release

Roadmap

Project principles

Contributing

License