microsoft · Nikolasgs · Jul 3, 2026
@@ -2,7 +2,7 @@
   "name": "dataverse-skills",
   "metadata": {
     "description": "Official Dataverse plugin marketplace for agent-guided development",
-    "version": "1.6.0"
+    "version": "1.7.0"
   },
   "owner": {
     "name": "Microsoft",
@@ -13,7 +13,7 @@
       "name": "dataverse",
       "description": "Microsoft Dataverse plugin for coding agents — powering CRUD, bulk data operations, advanced queries, schema lifecycle, and environment management through intelligent skills that unify MCP, CLI, and SDK workflows.",
       "source": "./.github/plugins/dataverse",
-      "version": "1.6.0",
+      "version": "1.7.0",
       "homepage": "https://github.com/microsoft/Dataverse-skills"
     }
   ]

@@ -1,7 +1,7 @@
 {
   "name": "dataverse",
   "description": "Microsoft Dataverse plugin for coding agents — powering CRUD, bulk data operations, advanced queries, schema lifecycle, and environment management through intelligent skills that unify MCP, CLI, and SDK workflows.",
-  "version": "1.6.0",
+  "version": "1.7.0",
   "author": {
     "name": "Microsoft",
     "url": "https://www.microsoft.com"

@@ -1,7 +1,7 @@
 {
   "name": "dataverse",
   "description": "Microsoft Dataverse plugin for coding agents — powering CRUD, bulk data operations, advanced queries, schema lifecycle, and environment management through intelligent skills that unify MCP, CLI, and SDK workflows.",
-  "version": "1.6.0",
+  "version": "1.7.0",
   "author": {
     "name": "Microsoft",
     "url": "https://www.microsoft.com"

@@ -2,7 +2,7 @@
   "name": "dataverse",
   "displayName": "Microsoft Dataverse",
   "description": "Microsoft Dataverse plugin for coding agents — powering CRUD, bulk data operations, advanced queries, schema lifecycle, and environment management through intelligent skills that unify MCP, CLI, and SDK workflows.",
-  "version": "1.6.0",
+  "version": "1.7.0",
   "author": {
     "name": "Microsoft",
     "url": "https://www.microsoft.com"

@@ -1,7 +1,7 @@
 {
   "name": "dataverse",
   "description": "Microsoft Dataverse plugin for coding agents — powering CRUD, bulk data operations, advanced queries, schema lifecycle, and environment management through intelligent skills that unify MCP, CLI, and SDK workflows.",
-  "version": "1.6.0",
+  "version": "1.7.0",
   "author": {
     "name": "Microsoft",
     "url": "https://www.microsoft.com"

@@ -330,7 +330,7 @@ def get_token(scope=None):
     "unknown",
 })
 _ALLOWED_AGENTS = frozenset({
-    "claude-code", "copilot", "cursor", "codex", "unknown",
+    "claude-code", "copilot", "cursor", "codex", "opencode", "unknown",
 })
 # Strict format: key=value pairs, semicolon-separated. No spaces, no PII.
 _CONTEXT_RE = re.compile(

@@ -0,0 +1,140 @@
+"""
+install-opencode.py — Install Dataverse skills into an opencode-compatible location.
+
+opencode has no plugin marketplace for skill bundles (unlike Claude Code, GitHub
+Copilot, Cursor, and Codex, which install this plugin via their own marketplace
+commands). opencode instead auto-discovers skills from these locations:
+
+  - .claude/skills/<name>/SKILL.md   (project, Claude Code compatibility layer)
+  - ~/.claude/skills/<name>/SKILL.md (global, Claude Code compatibility layer)
+
+This script copies the plugin's skill folders (and scripts/auth.py) from this
+repo into one of those locations inside a target project, so opencode picks
+them up automatically on its next session. It is idempotent — re-running it
+only overwrites files whose content actually changed.
+
+Usage:
+    # From a clone of microsoft/Dataverse-skills, targeting the current directory:
+    python .github/plugins/dataverse/scripts/install-opencode.py --target /path/to/your/project
+
+    # Install into the global location instead (available in all projects):
+    python .github/plugins/dataverse/scripts/install-opencode.py --global
+
+    # Default target is the current working directory:
+    python .github/plugins/dataverse/scripts/install-opencode.py
+
+After running, restart (or start a new) opencode session in the target
+project — skills are discovered at session startup.
+"""
+
+import argparse
+import filecmp
+import shutil
+import sys
+from pathlib import Path
+
+_PLUGIN_ROOT = Path(__file__).resolve().parent.parent
+_SKILLS_SRC = _PLUGIN_ROOT / "skills"
+_AUTH_SRC = _PLUGIN_ROOT / "scripts" / "auth.py"
+
+
+def _copy_tree_if_changed(src: Path, dst: Path) -> list[str]:
+    """Copy src into dst recursively, skipping files whose content is unchanged.
+
+    Returns a list of human-readable change descriptions (created/updated).
+    """
+    changes = []
+    dst.mkdir(parents=True, exist_ok=True)
+    for item in sorted(src.iterdir()):
+        target = dst / item.name
+        if item.is_dir():
+            changes.extend(_copy_tree_if_changed(item, target))
+            continue
+        if target.exists() and filecmp.cmp(item, target, shallow=False):
+            continue
+        action = "updated" if target.exists() else "created"
+        shutil.copy2(item, target)
+        changes.append(f"{action}: {target}")
+    return changes
+
+
+def install_skills(dest_skills_dir: Path) -> list[str]:
+    """Copy every skills/dv-* folder into dest_skills_dir. Returns change log."""
+    changes = []
+    for skill_dir in sorted(_SKILLS_SRC.glob("dv-*")):
+        if not skill_dir.is_dir():
+            continue
+        changes.extend(_copy_tree_if_changed(skill_dir, dest_skills_dir / skill_dir.name))
+    return changes
+
+
+def install_auth_script(target: Path) -> list[str]:
+    """Copy scripts/auth.py into <target>/scripts/auth.py if missing or changed."""
+    if not _AUTH_SRC.exists():
+        return []
+    dest_dir = target / "scripts"
+    dest_dir.mkdir(parents=True, exist_ok=True)
+    dest = dest_dir / "auth.py"
+    if dest.exists() and filecmp.cmp(_AUTH_SRC, dest, shallow=False):
+        return []
+    action = "updated" if dest.exists() else "created"
+    shutil.copy2(_AUTH_SRC, dest)
+    return [f"{action}: {dest}"]
+
+
+def main():
+    parser = argparse.ArgumentParser(
+        description="Install Dataverse skills into an opencode-compatible .claude/skills/ location."
+    )
+    parser.add_argument(
+        "--target",
+        default=".",
+        help="Target project directory (default: current directory). Ignored with --global.",
+    )
+    parser.add_argument(
+        "--global",
+        dest="use_global",
+        action="store_true",
+        help="Install into ~/.claude/skills/ instead of a project's .claude/skills/.",
+    )
+    args = parser.parse_args()
+
+    if not _SKILLS_SRC.exists():
+        print(f"ERROR: skills source directory not found: {_SKILLS_SRC}", file=sys.stderr)
+        sys.exit(2)
+
+    if args.use_global:
+        target = Path.home()
+        dest_skills_dir = target / ".claude" / "skills"
+    else:
+        target = Path(args.target).resolve()
+        dest_skills_dir = target / ".claude" / "skills"
+
+    print(f"Installing Dataverse skills into: {dest_skills_dir}")
+    skill_changes = install_skills(dest_skills_dir)
+
+    auth_changes = []
+    if not args.use_global:
+        auth_changes = install_auth_script(target)
+
+    all_changes = skill_changes + auth_changes
+    if not all_changes:
+        print("Nothing to do — all files already up to date.")
+    else:
+        for line in all_changes:
+            print(f"  {line}")
+        print(f"\n{len(all_changes)} file(s) installed/updated.")
+
+    print(
+        "\nDone. Restart (or start a new) opencode session in the target project — "
+        "skills are discovered at session startup via .claude/skills/."
+    )
+    if not args.use_global:
+        print(
+            "Next: describe what you want in plain English (e.g. \"Connect to Dataverse\") "
+            "and the dv-connect skill will handle MCP registration for opencode."
+        )
+
+
+if __name__ == "__main__":
+    main()
@@ -20,7 +20,7 @@ Before touching anything, check whether this workspace is already connected to a
 Run these checks in order. If **all four pass**, skip straight to Step 7 (final verification) and stop there.
 
 1. **`.env` is present and complete** — file exists at the workspace root and contains non-empty values for `DATAVERSE_URL`, `TENANT_ID`, and `MCP_CLIENT_ID`
-2. **MCP is registered** — `.mcp.json` (Claude Code) or the equivalent Copilot / Cursor config file has a `dataverse-*` server entry pointing at the `DATAVERSE_URL` from `.env`
+2. **MCP is registered** — `.mcp.json` (Claude Code) or the equivalent Copilot / Cursor / Codex / opencode config file has a `dataverse-*` server entry pointing at the `DATAVERSE_URL` from `.env`
 3. **Both auth surfaces match `.env`** — `dataverse auth who` shows a profile whose `Environment Url` matches `DATAVERSE_URL`, AND `pac org who` against a PAC profile for the same URL succeeds. (DV CLI auth covers Connect / Data / Query / Metadata / MCP / Python; PAC auth covers `dv-solution` and `dv-admin`. Both are front-loaded at connect time so neither prompts later.)
 4. **Python SDK is importable and current** — `python -c "from PowerPlatform.Dataverse.client import DataverseClient; import pandas; from importlib.metadata import version; v=version('PowerPlatform-Dataverse-Client'); assert v>='0.1.0b9', f'SDK {v} is outdated, need >=0.1.0b9'"` exits 0
 
@@ -151,20 +151,18 @@ Present authentication options:
 
 Write `.env` directly — do not instruct the user to create it:
 
-Detect the current tool (Claude or Copilot) from context and set `MCP_CLIENT_ID` automatically:
-- Claude (CLI or VSCode extension): `0c412cc3-0dd6-449b-987f-05b053db9457`
-- GitHub Copilot: `aebc6443-996d-45c2-90f0-388ff96faa56`
+Detect the current tool from context and set `MCP_CLIENT_ID` automatically — see [mcp-configuration.md](references/mcp-configuration.md) Step 0 for the full agent → client-ID mapping.
 
 Also set plugin attribution variables for User-Agent tagging. **Fill in the two literals below from your own context** — you (the agent) loaded this plugin, so you already know both values:
 
 - `PLUGIN_VERSION` — the `version` field of your loaded plugin manifest (e.g. `"1.5.0"`). At runtime, `auth.py` re-reads this from the live manifest via host env vars; this `.env` entry is a fallback for offline cases.
-- `AGENT` — your host identity, one of: `claude-code`, `copilot`, `cursor`, `codex`, or `unknown`. Must match an entry in `_ALLOWED_AGENTS` in `auth.py` — if you don't recognize your host, use `unknown`.
+- `AGENT` — your host identity, one of: `claude-code`, `copilot`, `cursor`, `codex`, `opencode`, or `unknown`. Must match an entry in `_ALLOWED_AGENTS` in `auth.py` — if you don't recognize your host, use `unknown`.
 
 ```python
 # Substitute these two literals from your loaded plugin context.
 # Do NOT leave the angle-bracket placeholders — replace with real values.
 plugin_version = "<plugin manifest version, e.g. 1.5.0>"
-agent_host = "<your host name: claude-code | copilot | cursor | codex | unknown>"
+agent_host = "<your host name: claude-code | copilot | cursor | codex | opencode | unknown>"
 
 with open(".env", "w") as f:
     f.write(f"DATAVERSE_URL={dataverse_url}\n")
@@ -244,12 +242,12 @@ All three must resolve the same user/environment. They prove the DV CLI cache, t
 ## Step 6: Configure MCP server
 
 **Skip this step** if MCP is already configured:
-- `.mcp.json` or `~/.copilot/mcp-config.json` or `~/.cursor/mcp.json` or `~/.codex/config.toml` contains a Dataverse server entry
+- `.mcp.json` or `~/.copilot/mcp-config.json` or `~/.cursor/mcp.json` or `~/.codex/config.toml` or `opencode.json` / `~/.config/opencode/opencode.json` contains a Dataverse server entry
 - `claude mcp list` shows a `dataverse-*` server registered
 
 If MCP is not configured, follow [mcp-configuration.md](references/mcp-configuration.md):
 
-1. Detect which tool the user is running (Copilot, Claude, Cursor, or Codex) from context
+1. Detect which tool the user is running (Copilot, Claude, Cursor, Codex, or opencode) from context
 2. Set `MCP_CLIENT_ID` based on tool choice
 3. Get environment URL from `.env`
 4. Default to GA endpoint (`/api/mcp`)
@@ -262,26 +260,7 @@ If MCP is not configured, follow [mcp-configuration.md](references/mcp-configura
 DATAVERSE_OPERATION_CONTEXT=app=dataverse-skills/{DATAVERSE_PLUGIN_VERSION};skill=mcp-direct;agent={DATAVERSE_PLUGIN_AGENT}
 ```
 
-For Claude Code (`claude mcp add -t stdio`), pass it via `-e DATAVERSE_OPERATION_CONTEXT=...`. For Copilot/Cursor JSON configs, add it to the `"env"` object in the stdio server entry; for Codex, add it to its `[mcp_servers.<name>.env]` table.
-
-**Important:** MCP configuration requires an editor/CLI restart.
-
-**For Copilot:** Write the JSON config, then:
-> ✅ Dataverse MCP server configured. **Restart your editor** for changes to take effect.
-
-**For Claude:** Run the `claude mcp add` command, then warn the user about the auth popup that will appear on next launch:
-> ✅ Dataverse MCP server registered. Restart Claude Code to enable MCP tools.
-> Remember to **use `claude --continue` to resume the session** without losing context.
->
-> **On restart, a browser window will open** asking you to sign in to your Dataverse environment. This is the MCP proxy authenticating on your behalf — sign in with the same account you used for `dataverse auth create` (or your active DV CLI profile, e.g., `{username}`). This only happens once; the token is cached for future sessions, and `dataverse auth create` populates the same cache so the popup is skipped if you've already run it.
-
-**For Cursor:** Write the JSON config, then:
-> ✅ Dataverse MCP server `dataverse-{orgid}` configured in `~/.cursor/mcp.json`. **Reload the Cursor window** (Ctrl+Shift+P → "Developer: Reload Window") for the new MCP server to appear under Settings → Tools & MCPs.
->
-> On first use, the `npx @microsoft/dataverse` proxy starts a device-code sign-in in your browser. Sign in with the same account you used for `dataverse auth create`; the token is cached in your OS credential store for future sessions. If you've already run `dataverse auth create`, the proxy reuses that cache silently — no device code.
-
-**For Codex:** Write the TOML config to `~/.codex/config.toml`. Codex loads MCP tools only at startup, so don't claim they're callable until the user restarts. Tell the user:
-> ✅ Dataverse MCP server `dataverse-{orgid}` configured in `~/.codex/config.toml`. **Restart Codex** (CLI) or reload the Codex IDE to load the MCP tools.
+**Important:** MCP configuration requires an editor/CLI restart (or opencode session restart) for every host. Register the server and deliver the exact per-host confirmation message from [mcp-configuration.md](references/mcp-configuration.md) Step 8 — do not improvise the wording, it carries host-specific restart and auth-popup guidance.
 
 ---
 
@@ -354,6 +333,4 @@ After verifying MCP works, tell the user:
 
 ## Supported Agents
 
-This plugin's skill files are natively loaded by both **GitHub Copilot CLI** and **Claude Code CLI** when installed as a plugin. No manual context-loading is needed — both agents discover and invoke skills automatically.
-
-The PAC CLI commands, Python scripts, and XML templates work identically in both environments.
+This plugin's skills are natively discovered by GitHub Copilot, Claude Code, Cursor, and Codex when installed as a plugin, and by opencode via its built-in `.claude/skills` compatibility layer (see the README for the opencode install path). No manual context-loading is needed. PAC CLI commands, Python scripts, and XML templates work identically across all five.