Update saiop-mcp-servers skill: docker-mcp widened to all tools (operator-approved), proxmox-mcp added (custom server + sshd ForceCommand hardening)

skills/saiop-infrastructure/saiop-mcp-servers/SKILL.md

@@ -1,16 +1,16 @@
 ---
 name: saiop-mcp-servers
-description: "MCP server setup for SAIOP (git, postgres read-only, docker read-only) — least-privilege patterns and what was deliberately NOT wired up."
+description: "MCP server setup for SAIOP (git, postgres read-only, docker, proxmox snapshot access) — least-privilege patterns, and what was operator-approved to widen beyond the initial conservative defaults."
-version: 1.0.0
+version: 2.0.0
 author: Claude Code (SAIOP ops session)
 license: MIT
 platforms: [linux]
 prerequisites:
   env_vars: [MCP_POSTGRES_READONLY_PASSWORD]
-  commands: [uvx]
+  commands: [uvx, uv, ssh]
 metadata:
   hermes:
-    tags: [SAIOP, MCP, security, least-privilege, postgres, docker, git]
+    tags: [SAIOP, MCP, security, least-privilege, postgres, docker, git, proxmox, ssh]
 ---
 
 # MCP servers on SAIOP (Phase 6.3)
@@ -32,27 +32,68 @@ Adding or auditing MCP tool access for Hermes (Deployment Guide §6.3).
   blocks non-SELECT statements at the app layer too. Connection string goes
   through the `DATABASE_URI` env var (checked the package source —
   `os.environ.get("DATABASE_URI", args.database_url)`), not a CLI arg,
-  since CLI args are visible to any local user via `ps aux`.
+  since CLI args are visible to any local user via `ps aux`. `postgresql`'s
-- **docker-mcp** (`uvx docker-mcp`) — **the npm/pip package itself has no
+  port is published to `127.0.0.1:5432` only (loopback) since Hermes runs
-  read-only mode.** It exposes `create-container` and `deploy-compose`
+  on the host, not in Docker, and can't resolve container names.
-  (full write/deploy) alongside `get-logs`/`list-containers`. Restricted via
+- **docker-mcp** (`uvx docker-mcp`) — **operator-approved widening:**
-  Hermes's own `tools: {include: [...]}` allow-list in `config.yaml` to
+  originally restricted to `get-logs`/`list-containers` only (the package
-  just the two read-only tools — same enforcement mechanism already
+  has no native read-only mode; `create-container`/`deploy-compose` are
-  field-verified for the Telegram platform-toolset restriction (a real
+  full write/deploy). After an explicit flag-and-confirm round, the
-  destructive command was confirmed blocked at the tool layer, not just
+  operator chose to enable all 4 tools. This is a real, deliberate widening
-  configured). **Do not change this to "all tools" without a deliberate
+  of what Hermes can do to the host via MCP — if revisiting this decision,
-  decision** — full Docker access would directly undermine the project's
+  remember the restriction mechanism is still available and field-proven
-  core containment design (the `hermes` Linux user is deliberately denied
+  (`tools: {include: [...]}` in `config.yaml`, same mechanism verified for
-  `docker compose`/restart-docker capability via scoped sudoers; an
+  the Telegram platform-toolset restriction) if you want to dial it back.
-  unrestricted docker-mcp would hand that back through a side door).
+- **proxmox-mcp** — a **custom-written, single-tool MCP server**
+  (`/opt/ai-stack/hermes/scripts/proxmox_mcp.py`, run via
+  `uv run --with mcp python3 ...`), not an off-the-shelf package. Exposes
+  exactly one tool, `proxmox_qm(command)`, which SSHes to the Proxmox host
+  as the existing scoped `claude` account using a **dedicated keypair**
+  generated specifically for Hermes (not reusing the operator's desktop
+  key — separate blast radius per principal, same pattern as every other
+  dedicated credential in this project).
+  - **All three off-the-shelf SSH MCP packages checked (`mcp-server-ssh`,
+    `ssh-mcp-server`, `ssh-mcp`) were rejected before writing a custom one:**
+    `mcp-server-ssh` exposes a sprawling toolkit (`execute_command`,
+    `file_operations`, `process_manager`, `sftp_upload`/`download`,
+    `system_monitor`) — far more surface than needed. `ssh-mcp` (the
+    `mcpssh` package) was the narrowest (2 tools) but depends on an
+    external "Passman" credential-management service to resolve
+    connection details — an unwanted new dependency just to satisfy one
+    fixed host/user/key. `ssh-mcp-server` didn't expose a usable interface
+    for this case either. Writing ~60 lines directly against the `mcp`
+    Python SDK (`FastMCP`) was less work than adapting any of them, and
+    means the *only* security-relevant logic in the whole path is the
+    server-side sshd restriction (see below) — the MCP server itself is a
+    deliberately thin, unopinionated pipe.
+  - **The real enforcement is server-side, not in the MCP tool.** An sshd
+    `ForceCommand` drop-in on the Proxmox host (`Match User claude` in
+    `/etc/ssh/sshd_config.d/claude-restricted.conf`) routes every SSH
+    session for that account through a wrapper script
+    (`/usr/local/bin/claude-ssh-wrapper.sh`) that only permits
+    `qm snapshot/listsnapshot/status` patterns — regardless of what the
+    SSH client (the MCP tool, or anything else) requests. Verified directly:
+    allowed commands work, arbitrary commands (`whoami`, `cat /etc/passwd`)
+    are rejected, and a command-injection attempt via the snapshot-name
+    argument (`qm snapshot 141 test; whoami`) is rejected too (the wrapper
+    splits on whitespace and validates each token, not just regex-matching
+    the whole string). `AllowAgentForwarding`/`AllowTcpForwarding`/
+    `PermitTTY` are all disabled in the same `Match` block.
+  - **Wrapper-script gotcha hit while building this:** a long `elif [[ ... =~
+    ... ]]` line got an actual newline inserted into it during copy/paste
+    into `nano`, breaking the regex syntax (manifested as a confusing
+    `unexpected argument 'newline' to conditional binary operator` error —
+    not obviously a paste problem from the error text alone). Rewritten to
+    avoid any long lines at all (`read -ra parts <<< "$cmd"` + per-token
+    validation instead of one big regex) specifically so there's nothing
+    left for a wrap/paste to corrupt.
+  - I don't have write access to `/etc/ssh` or reload `sshd` myself — only
+    the scoped `claude` account, which can't escalate to root. The operator
+    applied the sshd-side changes directly; I verified them afterward over
+    SSH from the VM side.
 
 ## What was deliberately NOT wired up
 
-- **SSH MCP** — no second system exists in this environment that needs SSH
-  access beyond the VM Hermes already runs on. The one genuinely sensitive
-  SSH target (the Proxmox hypervisor) is the project's hardest boundary —
-  don't wire SSH MCP access to it without the operator directly involved in
-  scoping exactly what it can reach.
 - **pfSense/MikroTik MCP** — no real device credentials exist in this
   environment to configure them safely. Needs the operator to provide
   scoped, read-only-by-default credentials first.
@@ -68,3 +109,12 @@ hermes mcp test <name>          # verify a server connects and discover its tool
 non-interactive path — for a scripted/repeatable setup, hand-edit
 `mcp_servers:` in `config.yaml` directly instead (schema:
 `{command, args, env, enabled, tools: {include: [...]}}`).
+
+## If revisiting the Docker or Proxmox scope later
+
+- To re-restrict docker-mcp: add back
+  `tools: {include: ["get-logs", "list-containers"]}` under its entry.
+- To extend proxmox-mcp's reach: the *only* place that matters is the sshd
+  wrapper on the Proxmox host, not this MCP server or Hermes's config — the
+  MCP tool will happily send any command, the wrapper decides what actually
+  runs.