In-depth architectural comparison of the Proximo and Managed Agent Control MCP MCP servers. Compare execution transports, security boundaries, tool capabilities, quality scores, and ready-to-paste client installation snippets for Claude, Cursor, Windsurf, and VS Code.
At a Glance & Executive Verdict
Proximo
Cloud Platforms · Local stdio
Quality: 63/100 (Good) | Auth: API Key required
Managed Agent Control MCP
Cloud Platforms · Local stdio
Quality: 56/100 (Good) | Auth: API Key required
Verdict Summary: Choose Proximo if you need specialized Cloud Platforms tools running via a local process. Choose Managed Agent Control MCP if your workspace requires Cloud Platforms integration with local subprocess execution. Both servers can be configured concurrently in your client's mcpServers manifest.
Which MCP Server Should You Choose?
Choose Proximo when:
You need dedicated capabilities in the Cloud Platforms domain.
You prefer local stdio subprocess transport architecture.
Your security boundary fits: API Key required (Free / Open Source).
You have access to required keys: PROXIMO_API_BASE_URL, PROXIMO_NODE, PROXIMO_TOKEN_PATH.
All four Proxmox surfaces — VE, Backup Server, Mail Gateway, Datacenter Manager — plus in-container exec on one audited control plane. Every mutation dry-runs to a PLAN with its blast radius named, snapshots first where the platform can, and lands in a hash-chained tamper-evident audit ledger. 365 tools, read-only by default. uvx proximo-proxmox
Start, observe, and interact with Claude Managed Agents from any MCP client — launch an agent, poll its events to watch it work, reply, approve the tools it wants to run, and stop it. Runs over stdio, an HTTP container, or AWS Lambda, with pluggable inbound auth (bearer/OIDC/Cognito).
Tools & Capabilities Breakdown
Proximo Tools (7)
audit_entries
READ-ONLY: WHO changed WHAT and WHEN — guest configuration changes and every other
audited action, read back from the PROVE ledger.
Newest first. This is how you answer "who changed this guest" or "what has this caller
done". `matched` counts entries passing your filters, `total` counts the whole ledger,
and `truncated` says so when `limit` cut rows. An entry with no principal returns null
plus a note: the ledger not capturing an identity is a fact about the log, never a claim
that nobody was responsible. This READS the chain; `audit_verify` PROVES it is intact.
audit_verify
Verify the tamper-evident audit ledger's hash chain — PROVE the log is intact.
Pass `expected_head` (the head() value you pinned off-box) to also catch tail
truncation, a forged tail-append, or a full file replacement — a forward walk
alone can't see those. Falls back to PROXIMO_AUDIT_EXPECTED_HEAD when omitted.
proximo_call
Call any Proximo tool by exact name, including ones not in this server's listed tools.
Get the argument shape from proximo_tool_schema first. Same gates as calling it directly:
dry-run PLAN, ledger entry, token ACL. A smaller doorway, not a looser one.
proximo_recall
Ready-to-Paste Client Configurations
Paste either (or both) of these JSON server blocks into your client config file (e.g. claude_desktop_config.json or ~/.cursor/mcp.json).
Proximo is categorized under Cloud Platforms and uses a local stdio subprocess. In contrast, Managed Agent Control MCP belongs to Cloud Platforms using local stdio subprocess. Select Proximo when you need capabilities focused on cloud platforms and Managed Agent Control MCP when you require tools for cloud platforms.
READ-ONLY: the estate map from local Tier-1 memory — NOT a live PVE read. Returns
total/by_kind/by_status/guest_summary counts (trust guest_summary for guest-count questions;
all counting is server-side) plus lean entity rows, stamped {source:'memory', as_of,
age_seconds}: the data is as old as the stamp says. With `since`, also diffs: appeared,
status_changed, and not_seen_since (last observed before the window — a fact, not a claim
the entity is gone). journal=N adds the newest N diagnosis digests ("when did this last
happen") — findings summaries only, never raw diagnostic output. Memory is on by default
(PROXIMO_MEMORY=0 opts out), fed opportunistically by list reads and diagnose/doctor runs,
derived and rebuildable. For live state use pve_list_guests / pve_cluster_resources.
proximo_find_tools
Search Proximo's full tool catalog by keyword.
ESTATE QUESTIONS FIRST: if the question is what exists, how many, what changed, or when something last happened, call proximo_recall instead — it answers from local memory in one call, with no search and no schema lookup, and it stamps how old the answer is. Come here for everything else.
The facade is resident; 924 more tools on this server are searchable but not. Search for what you want ("guest power", "ceph pool", "firewall"), then call proximo_tool_schema on a result to get its arguments, then proximo_read (read-only tools) or proximo_call to run it. All terms must match.
proximo_tool_schema
Full description + JSON input schema for one tool found via proximo_find_tools.
proximo_read
READ-ONLY: run a read-only Proximo tool by exact name; refuses anything that can
mutate (use proximo_call for those). Same flow: get the shape from proximo_tool_schema
first.
Managed Agent Control MCP Tools (6)
Discover agents, environments, vaults, and memory stores
Start and manage Claude Managed Agent sessions
Poll session events and inspect token usage
Send messages, interrupt runs, and handle tool approvals
Run over stdio, HTTP containers, or AWS Lambda
Support bearer, OIDC, and Cognito inbound authentication