Jungle Cleaner MCP Server

by junglecleaner Your server? Claim it

not responding

Jungle Cleaner is listed as active in the registry but did not answer our last check. It exposes 7 tools.

Lowers your AWS bill by helping you clean up and optimize your setup

Uptime history 91 days of history · worst day 0%

91 days agonow

58.7%

Uptime 24h

54 of 92 checks

Tools

read from the server

472 ms

Response time

average over 24h

open, no key

Access

streamable-http

Jungle Cleaner does not always answer

Over the last week it answered 31.4% of our checks. We check every 15 minutes, so you hear about the next outage within the hour — not from your users.

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 6 min ago.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add mcp --transport http https://junglecleaner.com/api/mcp

Settings → Connectors → Add custom connector, then paste this address

https://junglecleaner.com/api/mcp

~/.codex/config.toml

[mcp_servers.mcp]
url = "https://junglecleaner.com/api/mcp"

.cursor/mcp.json

{
  "mcpServers": {
    "mcp": {
      "url": "https://junglecleaner.com/api/mcp"
    }
  }
}

.vscode/mcp.json

{
  "servers": {
    "mcp": {
      "type": "http",
      "url": "https://junglecleaner.com/api/mcp"
    }
  }
}

Available tools 7

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

accounts

list_accounts

List all AWS accounts connected to Jungle Cleaner for the current user.

clean

clean

Get a step-by-step cleanup guide for your latest scan findings. Automatically checks whether idle resources are still in use before recommending deletion. Detects IaC tools (Terraform, CloudFormation, OpenTofu, Pulumi) and shows IaC-first remediation guidance. Returns a ready-to-act guidance prompt — you follow the steps, Jungle Cleaner verifies the savings.

connect

connect_aws

Connect an AWS account so it can be scanned for unused resources and wasted spend. Returns a guided setup page. If you are not yet signed in to Jungle Cleaner, this will return a sign-in URL first.

results

get_results

Retrieve the latest scan results without triggering a new scan. Useful if you want to re-read results from a previous run.

scan

scan

Scan your connected AWS account for unused resources and wasted spend. Returns findings with estimated monthly cost in plain English. Pass progressToken to receive live progress updates during the scan. If multiple accounts are connected, pass the account name or account ID to target a specific one.

usage

check_usage

Check whether a specific resource is currently idle or in active use. Uses live CloudWatch metrics and API state checks. Returns a verdict (confirmed_inactive / possibly_active / unknown) with supporting evidence.

verify

verify_savings

Check which findings from the latest scan have been remediated — resources deleted, configs changed, policies set. Confirms each remediation via the AWS API and records the estimated monthly saving so your total captured savings accumulate over time. Returns newly confirmed remediations and your running captured savings total.

Endpoints

URL	Transport	State	Latency	Checked
https://junglecleaner.com/api/mcp	streamable-http	answering	70 ms	6 min ago

Alternatives to Jungle Cleaner

same job, measured the same way

PySpark MCP

by annasmazhar

SQL migration, AWS Glue job generation, and PySpark optimization as an MCP server.

161 installs/wk local only

Infrly

by getinfrly

Read-only access to your Infrly services, deploys, logs, metrics and billing.

answering

AWS MCP Connector

by ferhatdundar

MCP server for the AWS CLI. Read-only by default; single Go binary.

local only

Servonaut

by servonaut

Manage AWS, Hetzner, OVH and SSH servers: status, logs, CloudWatch, IP bans, safe command exec.

4 700 installs/wk local only

cloudcostwise

by cloudwise-app

Find AWS waste with your own read-only credentials. Runs locally. Nothing is sent unless you opt in.

1 906 installs/wk local only

Connections

by lunarwerx

AWS, GitHub and connected services from your agent, no keys to paste, plus local shell and browser.

98 installs/wk local only

Computegpu

by jyswee

Rent cloud GPUs from your agent: live catalogue, deploy, stop, destroy. Per-second billing.

78 installs/wk 2 tools answering

elmah.io

by elmah

Search logs, investigate errors, check deployments, and monitor uptime for your elmah.io org.

answering

Jungle Cleaner — questions

Answers built from our own checks of this server.

What can Jungle Cleaner do?

It exposes 7 tools, read directly from the server on our last check. Among them: check_usage, clean, connect_aws, get_results, list_accounts, scan and 1 more. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →

Is Jungle Cleaner working right now?

We send a real MCP handshake every 15 minutes. Over the last 24 hours 54 of 92 checks got a reply (58.7%), average response time 472 ms. The bar chart above shows every period we have measured.

The registry lists Jungle Cleaner as active — why does it not respond?

The official MCP registry stores what the author submitted; it does not verify that the server still runs. We check the endpoint ourselves, and this one does not answer. Catalogues that copy the registry without checking will show it as working.

How do I connect Jungle Cleaner?

Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.

Does Jungle Cleaner need an API key?

No. Jungle Cleaner completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 7 of them are readable on this page. This is what we observed, not what the docs claim.

How fast is Jungle Cleaner?

It answers our handshake in 472 ms on average, which is faster than 25% of all working MCP servers we measure. That is on the slow side — worth knowing if the tool sits inside an interactive loop. The comparison comes from our own checks across the whole registry, every 15 minutes.