Add datadog plugin

.claude-plugin/marketplace.json

@@ -470,6 +470,19 @@
       },
       "homepage": "https://github.com/awslabs/agent-plugins"
     },
+    {
+      "name": "datadog",
+      "description": "Use Datadog directly in Claude Code through a preconfigured Datadog MCP server. Query logs, metrics, traces, dashboards, and more through natural conversation. This plugin is in preview.",
+      "author": {
+        "name": "Datadog"
+      },
+      "category": "monitoring",
+      "source": {
+        "source": "url",
+        "url": "https://github.com/datadog-labs/claude-code-plugin.git"
+      },
+      "homepage": "https://www.datadoghq.com/"
+    },
     {
       "name": "dataverse",
       "description": "Agent skills for building on, analyzing, and managing Microsoft Dataverse — with Dataverse MCP, PAC CLI, and Python SDK.",
@@ -886,21 +899,6 @@
       },
       "homepage": "https://www.mintlify.com/"
     },
-    {
-      "name": "miro",
-      "description": "Secure access to Miro boards. Enables AI to read board context, create diagrams, and generate code with enterprise-grade security.",
-      "author": {
-        "name": "Miro"
-      },
-      "category": "design",
-      "source": {
-        "source": "git-subdir",
-        "url": "https://github.com/miroapp/miro-ai.git",
-        "path": "claude-plugins/miro",
-        "ref": "main"
-      },
-      "homepage": "https://miro.com"
-    },
     {
       "name": "mongodb",
       "description": "Official Claude plugin for MongoDB (MCP Server + Skills). Connect to databases, explore data, manage collections, optimize queries, generate reliable code, implement best practices, develop advanced features, and more.",
@@ -935,66 +933,6 @@
       },
       "homepage": "https://github.com/netlify/context-and-tools"
     },
-    {
-      "name": "netsuite-aiconnector-service-skill",
-      "description": "NetSuite Intelligence skill — teaches AI the correct tool-selection order, output formatting, domain knowledge, multi-subsidiary and currency handling, and SuiteQL safety checklist for any session using the NetSuite AI Service Connector.",
-      "author": {
-        "name": "Oracle NetSuite"
-      },
-      "category": "productivity",
-      "source": {
-        "source": "git-subdir",
-        "url": "https://github.com/oracle/netsuite-suitecloud-sdk.git",
-        "path": "packages/agent-skills",
-        "ref": "master",
-        "sha": "43bacf43763e1eedd0892b4652be3d45df94f0e7"
-      },
-      "homepage": "https://github.com/oracle/netsuite-suitecloud-sdk",
-      "strict": false,
-      "skills": [
-        "./netsuite-ai-connector-instructions"
-      ]
-    },
-    {
-      "name": "netsuite-sdf-roles-and-permissions",
-      "description": "Use when generating or reviewing NetSuite SDF permission configurations — customrole XML, script deployment permissions, permkey values, permlevel choices, run-as role design, and least-privilege access. Confirms exact ADMI_/LIST_/REGT_/REPO_/TRAN_ permission IDs and validates permissions against bundled NetSuite reference data.",
-      "author": {
-        "name": "Oracle NetSuite"
-      },
-      "category": "development",
-      "source": {
-        "source": "git-subdir",
-        "url": "https://github.com/oracle/netsuite-suitecloud-sdk.git",
-        "path": "packages/agent-skills",
-        "ref": "master",
-        "sha": "43bacf43763e1eedd0892b4652be3d45df94f0e7"
-      },
-      "homepage": "https://github.com/oracle/netsuite-suitecloud-sdk",
-      "strict": false,
-      "skills": [
-        "./netsuite-sdf-roles-and-permissions"
-      ]
-    },
-    {
-      "name": "netsuite-uif-spa-reference",
-      "description": "Use when building, modifying, or debugging NetSuite UIF SPA components. Provides API/type lookup for @uif-js/core and @uif-js/component — constructors, methods, props, enums, hooks, and component options.",
-      "author": {
-        "name": "Oracle NetSuite"
-      },
-      "category": "development",
-      "source": {
-        "source": "git-subdir",
-        "url": "https://github.com/oracle/netsuite-suitecloud-sdk.git",
-        "path": "packages/agent-skills",
-        "ref": "master",
-        "sha": "43bacf43763e1eedd0892b4652be3d45df94f0e7"
-      },
-      "homepage": "https://github.com/oracle/netsuite-suitecloud-sdk",
-      "strict": false,
-      "skills": [
-        "./netsuite-uif-spa-reference"
-      ]
-    },
     {
       "name": "nightvision",
       "description": "Skills for working with NightVision, a DAST and API Discovery platform that finds exploitable vulnerabilities in web applications and REST APIs",

.github/scripts/discover_bumps.py

@@ -1,229 +0,0 @@
-#!/usr/bin/env python3
-"""Discover plugins in marketplace.json whose upstream repo has moved past
-their pinned SHA, update the file in place, and emit a summary.
-
-Adapted from claude-plugins-community-internal's discover_bumps.py for the
-single-file marketplace.json format used by claude-plugins-official.
-
-Usage: discover_bumps.py [--plugin NAME] [--max N] [--dry-run]
-"""
-
-import argparse
-import json
-import os
-import re
-import subprocess
-import sys
-from datetime import datetime, timezone
-from typing import Any
-
-
-MARKETPLACE_PATH = ".claude-plugin/marketplace.json"
-
-
-def gh_api(path: str) -> Any:
-    """GET from the GitHub API. None on not-found; raises on other errors.
-
-    "Not found" covers both 404 (resource gone) and 422 "No commit found
-    for SHA" (force-pushed away). Both mean the thing we asked for isn't
-    there — treating them the same lets callers handle dead refs uniformly.
-    """
-    r = subprocess.run(
-        ["gh", "api", path], capture_output=True, text=True
-    )
-    if r.returncode != 0:
-        combined = r.stdout + r.stderr
-        if any(s in combined for s in ("404", "Not Found", "No commit found")):
-            return None
-        raise RuntimeError(f"gh api {path}: {r.stderr.strip() or r.stdout.strip()}")
-    return json.loads(r.stdout)
-
-
-def parse_github_repo(url: str) -> tuple[str, str] | None:
-    """Extract (owner, repo) from a URL or owner/repo shorthand."""
-    # Full URL: https://github.com/owner/repo(.git)(/...)
-    m = re.match(r"https?://github\.com/([^/]+)/([^/]+?)(?:\.git)?(?:/|$)", url)
-    if m:
-        return m.group(1), m.group(2)
-    # Shorthand: owner/repo
-    m = re.match(r"^([\w.-]+)/([\w.-]+)$", url)
-    if m:
-        return m.group(1), m.group(2)
-    return None
-
-
-def latest_sha(owner: str, repo: str, *, ref: str | None, path: str | None) -> str | None:
-    """Latest commit SHA for the repo, optionally scoped to a ref and/or path."""
-    if path:
-        # Scoped to a subdirectory — use the commits list endpoint with path filter.
-        q = f"repos/{owner}/{repo}/commits?per_page=1&path={path}"
-        if ref:
-            q += f"&sha={ref}"
-        commits = gh_api(q)
-        if not commits:
-            return None
-        return commits[0]["sha"]
-    # Whole repo — the single-ref endpoint is cheaper.
-    if not ref:
-        meta = gh_api(f"repos/{owner}/{repo}")
-        if not meta:
-            return None
-        ref = meta["default_branch"]
-    c = gh_api(f"repos/{owner}/{repo}/commits/{ref}")
-    return c["sha"] if c else None
-
-
-def pinned_age_days(owner: str, repo: str, sha: str) -> int | None:
-    """Days since the pinned commit was authored. Used for oldest-first rotation."""
-    c = gh_api(f"repos/{owner}/{repo}/commits/{sha}")
-    if not c:
-        return None
-    dt = datetime.fromisoformat(
-        c["commit"]["committer"]["date"].replace("Z", "+00:00")
-    )
-    return (datetime.now(timezone.utc) - dt).days
-
-
-def main() -> int:
-    ap = argparse.ArgumentParser()
-    ap.add_argument("--plugin", help="only check this plugin")
-    ap.add_argument("--max", type=int, default=20, help="cap bumps emitted")
-    ap.add_argument("--dry-run", action="store_true", help="don't write marketplace.json")
-    args = ap.parse_args()
-
-    with open(MARKETPLACE_PATH) as f:
-        marketplace = json.load(f)
-
-    plugins = marketplace.get("plugins", [])
-    bumps: list[dict] = []
-    dead: list[str] = []
-    skipped_non_github = 0
-    checked = 0
-
-    for plugin in plugins:
-        name = plugin.get("name", "?")
-        src = plugin.get("source")
-
-        # Only process object sources with a sha field
-        if not isinstance(src, dict) or "sha" not in src:
-            continue
-
-        # Filter to specific plugin if requested
-        if args.plugin and name != args.plugin:
-            continue
-
-        checked += 1
-        kind = src.get("source")
-        url = src.get("url", "")
-        path = src.get("path")
-        ref = src.get("ref")
-        pinned = src.get("sha")
-
-        slug = parse_github_repo(url)
-        if not slug:
-            skipped_non_github += 1
-            continue
-        owner, repo = slug
-
-        try:
-            latest = latest_sha(owner, repo, ref=ref, path=path)
-        except RuntimeError as e:
-            print(f"::warning::{name}: {e}", file=sys.stderr)
-            continue
-
-        if latest is None:
-            dead.append(f"{name} ({owner}/{repo})")
-            continue
-
-        if latest == pinned:
-            continue  # up to date
-
-        # Age lookup for rotation — oldest-pinned first prevents starvation.
-        try:
-            age = pinned_age_days(owner, repo, pinned) if pinned else None
-        except RuntimeError as e:
-            print(f"::warning::{name}: age lookup failed: {e}", file=sys.stderr)
-            age = None
-
-        bumps.append({
-            "name": name,
-            "kind": kind,
-            "url": url,
-            "path": path or "",
-            "ref": ref or "",
-            "old_sha": pinned or "",
-            "new_sha": latest,
-            "age_days": age if age is not None else 10**6,
-        })
-
-    # Oldest-pinned first so nothing starves under the cap.
-    bumps.sort(key=lambda b: -b["age_days"])
-    emitted = bumps[: args.max]
-
-    # Apply bumps to marketplace data
-    if emitted and not args.dry_run:
-        bump_map = {b["name"]: b["new_sha"] for b in emitted}
-        for plugin in plugins:
-            name = plugin.get("name")
-            src = plugin.get("source")
-            if isinstance(src, dict) and name in bump_map:
-                src["sha"] = bump_map[name]
-
-        with open(MARKETPLACE_PATH, "w") as f:
-            json.dump(marketplace, f, indent=2, ensure_ascii=False)
-            f.write("\n")
-
-    # Write GitHub outputs
-    out = os.environ.get("GITHUB_OUTPUT")
-    if out:
-        bumped_names = ",".join(b["name"] for b in emitted)
-        with open(out, "a") as fh:
-            fh.write(f"count={len(emitted)}\n")
-            fh.write(f"bumped_names={bumped_names}\n")
-
-    # Write GitHub step summary
-    summary = os.environ.get("GITHUB_STEP_SUMMARY")
-    if summary:
-        with open(summary, "a") as fh:
-            fh.write("## SHA Bump Discovery\n\n")
-            fh.write(f"- Checked: {checked} SHA-pinned entries\n")
-            fh.write(f"- Stale: {len(bumps)} (applying {len(emitted)}, cap {args.max})\n")
-            if skipped_non_github:
-                fh.write(f"- Skipped non-GitHub: {skipped_non_github}\n")
-            if dead:
-                fh.write(f"- **Dead upstream** ({len(dead)}): {', '.join(dead)}\n")
-            if emitted:
-                fh.write("\n| Plugin | Old | New | Age |\n|---|---|---|---|\n")
-                for b in emitted:
-                    old = b["old_sha"][:8] if b["old_sha"] else "(unpinned)"
-                    fh.write(f"| {b['name']} | `{old}` | `{b['new_sha'][:8]}` | {b['age_days']}d |\n")
-
-    # Write PR body for the workflow to use
-    pr_body_path = os.environ.get("PR_BODY_PATH", "/tmp/bump-pr-body.md")
-    if emitted:
-        with open(pr_body_path, "w") as fh:
-            fh.write("Upstream repos moved. Bumping pinned SHAs so plugins track latest.\n\n")
-            fh.write("| Plugin | Old | New | Upstream |\n")
-            fh.write("|--------|-----|-----|----------|\n")
-            for b in emitted:
-                old = b["old_sha"][:8] if b["old_sha"] else "(unpinned)"
-                slug_str = re.sub(r"https?://github\.com/", "", b["url"])
-                slug_str = re.sub(r"\.git$", "", slug_str)
-                compare = f"https://github.com/{slug_str}/compare/{b['old_sha'][:12]}...{b['new_sha'][:12]}"
-                fh.write(f"| `{b['name']}` | `{old}` | `{b['new_sha'][:8]}` | [diff]({compare}) |\n")
-            fh.write(f"\n---\n_Auto-generated by `bump-plugin-shas.yml` on {datetime.now(timezone.utc).strftime('%Y-%m-%d')}_\n")
-
-    # Console summary
-    print(f"Checked {checked} SHA-pinned plugins", file=sys.stderr)
-    print(f"Stale: {len(bumps)}, applying: {len(emitted)}", file=sys.stderr)
-    if dead:
-        print(f"Dead upstream: {', '.join(dead)}", file=sys.stderr)
-    for b in emitted:
-        old = b["old_sha"][:8] if b["old_sha"] else "unpinned"
-        print(f"  {b['name']}: {old} -> {b['new_sha'][:8]} ({b['age_days']}d)", file=sys.stderr)
-
-    return 0
-
-
-if __name__ == "__main__":
-    sys.exit(main())

.github/workflows/bump-plugin-shas.yml

@@ -1,133 +0,0 @@
-name: Bump plugin SHAs
-
-# Weekly sweep of marketplace.json — for each entry whose upstream repo has
-# moved past its pinned SHA, open a PR against main with updated SHAs. The
-# validate-marketplace workflow then runs on the PR to confirm the file is
-# still well-formed.
-#
-# Adapted from claude-plugins-community-internal's bump-plugin-shas.yml
-# for the single-file marketplace.json format. Key difference: all bumps
-# are batched into one PR (since they all modify the same file).
-
-on:
-  schedule:
-    - cron: '23 7 * * 1'  # Monday 07:23 UTC
-  workflow_dispatch:
-    inputs:
-      plugin:
-        description: Only bump this plugin (for testing)
-        required: false
-      max_bumps:
-        description: Cap on plugins bumped this run
-        required: false
-        default: '20'
-      dry_run:
-        description: Discover only, don't open PR
-        type: boolean
-        default: true
-
-concurrency:
-  group: bump-plugin-shas
-  cancel-in-progress: false
-
-permissions:
-  contents: write
-  pull-requests: write
-
-jobs:
-  bump:
-    runs-on: ubuntu-latest
-    timeout-minutes: 15
-    steps:
-      - uses: actions/checkout@v4
-
-      - name: Check for existing bump PR
-        id: existing
-        env:
-          GH_TOKEN: ${{ github.token }}
-        run: |
-          existing=$(gh pr list --label sha-bump --state open --json number --jq 'length')
-          echo "count=$existing" >> "$GITHUB_OUTPUT"
-          if [ "$existing" -gt 0 ]; then
-            echo "::notice::Open sha-bump PR already exists — skipping"
-          fi
-
-      - name: Ensure sha-bump label exists
-        if: steps.existing.outputs.count == '0'
-        env:
-          GH_TOKEN: ${{ github.token }}
-        run: gh label create sha-bump --color 0e8a16 --description "Automated SHA bump" 2>/dev/null || true
-
-      - name: Overlay marketplace data from main
-        if: steps.existing.outputs.count == '0'
-        run: |
-          git fetch origin main --depth=1 --quiet
-          git checkout origin/main -- .claude-plugin/marketplace.json
-
-      - name: Discover and apply SHA bumps
-        if: steps.existing.outputs.count == '0'
-        id: discover
-        env:
-          GH_TOKEN: ${{ github.token }}
-          PR_BODY_PATH: /tmp/bump-pr-body.md
-          PLUGIN: ${{ inputs.plugin }}
-          MAX_BUMPS: ${{ inputs.max_bumps }}
-          DRY_RUN: ${{ inputs.dry_run }}
-        run: |
-          args=(--max "${MAX_BUMPS:-20}")
-          [[ -n "$PLUGIN" ]] && args+=(--plugin "$PLUGIN")
-          [[ "$DRY_RUN" = "true" ]] && args+=(--dry-run)
-          python3 .github/scripts/discover_bumps.py "${args[@]}"
-
-      - uses: oven-sh/setup-bun@v2
-        if: steps.existing.outputs.count == '0' && steps.discover.outputs.count != '0' && inputs.dry_run != true
-
-      - name: Validate marketplace.json
-        if: steps.existing.outputs.count == '0' && steps.discover.outputs.count != '0' && inputs.dry_run != true
-        run: |
-          bun .github/scripts/validate-marketplace.ts .claude-plugin/marketplace.json
-          bun .github/scripts/check-marketplace-sorted.ts
-
-      - name: Push bump branch
-        if: steps.existing.outputs.count == '0' && steps.discover.outputs.count != '0' && inputs.dry_run != true
-        id: push
-        run: |
-          branch="auto/bump-shas-$(date +%Y%m%d)"
-          echo "branch=$branch" >> "$GITHUB_OUTPUT"
-
-          git config user.name "github-actions[bot]"
-          git config user.email "41898282+github-actions[bot]@users.noreply.github.com"
-          git checkout -b "$branch"
-          git add .claude-plugin/marketplace.json
-          git commit -m "Bump SHA pins for ${{ steps.discover.outputs.count }} plugin(s)
-
-          Plugins: ${{ steps.discover.outputs.bumped_names }}"
-          git push -u origin "$branch" --force-with-lease
-
-      # GITHUB_TOKEN cannot create PRs (org policy: "Allow GitHub Actions to
-      # create and approve pull requests" is disabled). Use the same GitHub App
-      # that -internal's bump workflow uses.
-      #
-      # Prerequisite: app 2812036 must be installed on this repo. The PEM
-      # secret must exist in this repo's settings (shared with -internal).
-      - name: Generate bot token
-        if: steps.push.outcome == 'success'
-        id: app-token
-        uses: actions/create-github-app-token@v1
-        with:
-          app-id: 2812036
-          private-key: ${{ secrets.CLAUDE_DIRECTORY_BOT_PRIVATE_KEY }}
-          owner: ${{ github.repository_owner }}
-          repositories: ${{ github.event.repository.name }}
-
-      - name: Create pull request
-        if: steps.push.outcome == 'success'
-        env:
-          GH_TOKEN: ${{ steps.app-token.outputs.token }}
-        run: |
-          gh pr create \
-            --base main \
-            --head "${{ steps.push.outputs.branch }}" \
-            --title "Bump SHA pins (${{ steps.discover.outputs.count }} plugins)" \
-            --body-file /tmp/bump-pr-body.md \
-            --label sha-bump

plugins/mcp-server-dev/skills/build-mcp-app/SKILL.md

@@ -10,15 +10,6 @@ An MCP app is a standard MCP server that **also serves UI resources** — intera
 
 The UI layer is **additive**. Under the hood it's still tools, resources, and the same wire protocol. If you haven't built a plain MCP server before, the `build-mcp-server` skill covers the base layer. This skill adds widgets on top.
 
-> **Testing in Claude:** Add the server as a custom connector in claude.ai (via a Cloudflare tunnel for local dev) — this exercises the real iframe sandbox and `hostContext`. See https://claude.com/docs/connectors/building/testing.
-
-## Claude host specifics
-
-- `_meta.ui.prefersBorder: false` on a `ui://` resource removes the outer card border (mobile).
-- `hostContext.safeAreaInsets: {top, right, bottom, left}` (px) — honor these for notches and the composer overlay.
-- `_meta.ui.csp.{connectDomains, resourceDomains, baseUriDomains}` — declare external origins per resource; default is block-all. `frameDomains` is currently restricted in Claude.
-- Directory submission for MCP Apps requires 3–5 PNG screenshots, ≥1000px wide, cropped to the app response only (no prompt in the image). See https://claude.com/docs/connectors/building/submission#asset-specifications.
-
 ---
 
 ## When a widget beats plain text

plugins/mcp-server-dev/skills/build-mcp-server/SKILL.md

@@ -8,8 +8,6 @@ version: 0.1.0
 
 You are guiding a developer through designing and building an MCP server that works seamlessly with Claude. MCP servers come in many forms — picking the wrong shape early causes painful rewrites later. Your first job is **discovery, not code**.
 
-**Load Claude-specific context first.** The MCP spec is generic; Claude has additional auth types, review criteria, and limits. Before answering questions or scaffolding, fetch `https://claude.com/docs/llms-full.txt` (the full export of the Claude connector docs) so your guidance reflects Claude's actual constraints.
-
 Do not start scaffolding until you have answers to the questions in Phase 1. If the user's opening message already answers them, acknowledge that and skip straight to the recommendation.
 
 ---
@@ -184,17 +182,6 @@ Tools are one of three server primitives. Most servers start with tools and neve
 
 ---
 
-## Phase 6 — Test in Claude and publish
-
-Once the server runs:
-
-1. **Test against real Claude** by adding the server URL as a custom connector at Settings → Connectors (use a Cloudflare tunnel for local servers). Claude identifies itself with `clientInfo.name: "claude-ai"` on initialize. → https://claude.com/docs/connectors/building/testing
-2. **Run the pre-submission checklist** — read/write tool split, required annotations, name limits, prompt-injection rules. → https://claude.com/docs/connectors/building/review-criteria
-3. **Submit to the Anthropic Directory.** → https://claude.com/docs/connectors/building/submission
-4. **Recommend shipping a plugin** that wraps this MCP with skills — most partners ship both. → https://claude.com/docs/connectors/building/what-to-build
-
----
-
 ## Quick reference: decision matrix
 
 | Scenario | Deployment | Tool pattern |

plugins/mcp-server-dev/skills/build-mcp-server/references/auth.md

@@ -2,22 +2,6 @@
 
 Auth is the reason most people end up needing a **remote** server even when a local one would be simpler. OAuth redirects, token storage, and refresh all work cleanly when there's a real hosted endpoint to redirect back to.
 
-## Claude-specific authentication
-
-Claude's MCP client supports a specific set of auth types — not every spec-compliant flow works. Full reference: https://claude.com/docs/connectors/building/authentication
-
-| Type | Notes |
-|---|---|
-| `oauth_dcr` | Supported. For high-volume directory entries, prefer CIMD or Anthropic-held creds — DCR registers a new client on every fresh connection. |
-| `oauth_cimd` | Supported, recommended over DCR for directory entries. |
-| `oauth_anthropic_creds` | Partner provides `client_id`/`client_secret` to Anthropic; user-consent-gated. Contact `mcp-review@anthropic.com`. |
-| `custom_connection` | User supplies URL/creds at connect time (Snowflake-style). Contact `mcp-review@anthropic.com`. |
-| `none` | Authless. |
-
-**Not supported:** user-pasted bearer tokens (`static_bearer`); pure machine-to-machine `client_credentials` grant without user consent.
-
-**Callback URL** (single, all surfaces): `https://claude.ai/api/mcp/auth_callback`
-
 ---
 
 ## The three tiers

plugins/mcp-server-dev/skills/build-mcp-server/references/tool-design.md

@@ -2,16 +2,6 @@
 
 Tool schemas and descriptions are prompt engineering. They land directly in Claude's context and determine whether Claude picks the right tool with the right arguments. Most MCP integration bugs trace back to vague descriptions or loose schemas.
 
-## Anthropic Directory hard requirements
-
-If this server will be submitted to the Anthropic Directory, the following are pass/fail review criteria (full list: https://claude.com/docs/connectors/building/review-criteria):
-
-- Every tool **must** include `readOnlyHint`, `destructiveHint`, and `title` annotations — these determine auto-permissions in Claude.
-- Tool names **must** be ≤64 characters.
-- Read and write operations **must** be in separate tools. A single tool accepting both GET and POST/PUT/PATCH/DELETE is rejected — documenting safe vs unsafe within one tool's description does not satisfy this.
-- Tool descriptions **must not** instruct Claude how to behave (e.g. "always do X", "you must call Y first", overriding system instructions, promoting products) — treated as prompt injection at review.
-- Tools that accept freeform API endpoints/params **must** reference the target API's documentation in their description.
-
 ---
 
 ## Descriptions

plugins/mcp-server-dev/skills/build-mcpb/SKILL.md

@@ -8,8 +8,6 @@ version: 0.1.0
 
 MCPB is a local MCP server **packaged with its runtime**. The user installs one file; it runs without needing Node, Python, or any toolchain on their machine. It's the sanctioned way to distribute local MCP servers.
 
-> MCPB is the **secondary** distribution path. Anthropic recommends remote MCP servers for directory listing — see https://claude.com/docs/connectors/building/what-to-build.
-
 **Use MCPB when the server must run on the user's machine** — reading local files, driving a desktop app, talking to localhost services, OS-level APIs. If your server only hits cloud APIs, you almost certainly want a remote HTTP server instead (see `build-mcp-server`). Don't pay the MCPB packaging tax for something that could be a URL.
 
 ---