Skip to content

alirezarezvani/claude-skills / engineering/skills/coding-agent-rollout

coding-agent-rollout

Flagged

Roll out Claude Code to a team: shared or managed settings, MCP and plugin approval, layered CLAUDE.md, adoption. Use whenever the user sets up Claude Code for their team or org, or asks if a rollout or settings file is right.

references/mcp_and_plugin_governance.md

View on GitHub
# MCP servers, plugins and marketplaces

Every MCP server is code that runs with an engineer's credentials, and every
plugin can bring hooks, agents and its own MCP servers. This is what
`mcp_plugin_inventory.py` reads and why each check exists.

Confidence key: 🟒 verified on code.claude.com/docs or the cited source Β· πŸ”΄ recommendation.

## 1. Where MCP servers come from

| Scope | Location | Committed? |
|---|---|---|
| Local (default for `claude mcp add`) | `~/.claude.json` β†’ `projects["<path>"].mcpServers` | no |
| Project | `.mcp.json` at the repo root, key `mcpServers` | yes |
| User | `~/.claude.json` β†’ `mcpServers` | no |
| Managed | `managedMcpServers`, or `managed-mcp.json` beside `managed-settings.json` | IT |

Precedence: managed > local > project > user > plugin > claude.ai connectors;
same-name entries are not merged. 🟒 [mcp] `.mcp.json` expands `${VAR}` and
`${VAR:-default}`, so a committed file never needs a literal secret. 🟒 [mcp]
`managed-mcp.json` takes exclusive control; `{"mcpServers": {}}` disables MCP. 🟒 [managed-mcp]

## 2. Approval

- Project servers need approval. `enabledMcpjsonServers` / `disabledMcpjsonServers`
  approve by name; `enableAllProjectMcpServers: true` approves **everything**
  in `.mcp.json`, including the server a teammate adds next week. A committed
  `enable*` value is ignored in an untrusted folder. 🟒 [settings-reference]
- `allowedMcpServers` / `deniedMcpServers` entries take exactly one of
  `serverUrl` (supports `*`), `serverCommand` (exact array) or `serverName`
  (exact; the docs note a name alone is not a security control). Unset allowlist
  = everything allowed; `[]` = nothing. Deny always wins and merges from every
  scope; allowlists also merge unless `allowManagedMcpServersOnly: true`. 🟒 [managed-mcp]

**Recommendation:** approve by `serverUrl` or `serverCommand` in managed
settings, and keep the human-readable allowlist file (`approved-components.json`)
for the inventory diff. πŸ”΄

## 3. Pinning

An `npx -y some-mcp-server` entry runs whatever version the registry serves
that day. OWASP lists supply-chain compromise and excessive agency among the
top risks for LLM applications; an unpinned server with broad tool access is
both. 🟒 [OWASP] Pin the package (`pkg@1.4.2`, `pkg==0.6.2`) and update it on
purpose. πŸ”΄

## 4. Plugins and marketplaces

- `enabledPlugins` maps `"name@marketplace"` to a boolean; a managed `false`
  blocks the plugin everywhere. 🟒 [settings-reference]
- `extraKnownMarketplaces` (alias `additionalMarketplaces`) registers sources;
  from a repo file it applies only after trust. 🟒 [settings-reference]
- `strictKnownMarketplaces` (managed) is the source allowlist; `[]` blocks every
  marketplace, the official one included. `blockedMarketplaces` (managed) takes
  the same source objects, including `"owner/*"`. 🟒 [settings-reference]
- `strictPluginOnlyCustomization` locks skills, agents, hooks and/or MCP to
  plugin and managed sources, so customization ships only through reviewed
  plugins. 🟒 [managed-settings]

Pin a git or GitHub marketplace with `ref` so its contents cannot change between
review and install. πŸ”΄

## 5. Review checklist for a new server or plugin

1. Who maintains it, and is the source readable? (Open source or internal.)
2. What credentials does it receive? Scope them to read-only where possible.
3. Which tools does it expose? Deny the destructive ones with `mcp__server__tool` rules.
4. Is it pinned?
5. Does it send data off the machine, and is that allowed by your data policy? <!-- noqa: SEC-AUDITOR (governance review question) -->
6. Who owns it on your side, and when is it re-reviewed?

A plugin or server that fails 5 is a data-protection question before it is an
engineering one. πŸ”΄

## Sources

1. Claude Code docs β€” MCP. https://code.claude.com/docs/en/mcp
2. Claude Code docs β€” Managed MCP. https://code.claude.com/docs/en/managed-mcp
3. Claude Code docs β€” Settings reference. https://code.claude.com/docs/en/settings-reference
4. Claude Code docs β€” Managed settings. https://code.claude.com/docs/en/managed-settings
5. Claude Code docs β€” Permissions (MCP rule forms). https://code.claude.com/docs/en/permissions
6. OWASP Top 10 for LLM Applications. https://genai.owasp.org/llm-top-10/
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why β€” repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" β€” or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself β€” your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall