Directory / Work & productivity
CleanApp
Search public reports, submit approved physical or digital observations, and track analysis decisions and recorded actions; related observations retain their own evidence and attribution. No account or API key; publication and notices depend on approved handling and eligibility checks.
Live Answered an MCP handshake without credentials and listed 5 tools.
- Category
- Work & productivity
- Transport
http- Source
- https://www.cleanapp.io/agents
- Endpoint
https://live.cleanapp.io/openai/mcp- MCP Registry
io.github.cleanappio/cleanapp- Reports itself as
- CleanApp 1.1.0
- Protocol
- 2025-06-18
- Tools
- 5
- Context cost
- about 1,840 tokens for the tool definitions (estimated at four characters per token)
- Tool definitions last changed
- 2026-11-19
- Handshake time
- 175 ms
- Last checked
- 2026-11-22 11:27:28 UTC
- Listed since
- 2026-11-18
Health and compatibility
| Endpoint reachable | Verified | Responded in 175 ms |
|---|---|---|
| MCP handshake (initialize) | Verified | Completed without credentials |
| Tool discovery (tools/list) | Verified | 5 tools listed |
| Authentication | Verified | None needed to connect |
| Protocol version | Verified | 2025-06-18 |
| Transport | Verified | Streamable HTTP |
| Capabilities declared | Verified | resources, tools |
Last checked . Verified means the check saw it happen; it says nothing about whether the server is safe.
Recent history
5 daily checks so far; median response 175 ms. Green answered, violet asked for auth, red did not answer.
Set up in your client
Claude Code
Run this in a terminal:
claude mcp add --transport http cleanapp https://live.cleanapp.io/openai/mcpClaude Desktop
Open Settings → Connectors → Add custom connector and paste this URL:
https://live.cleanapp.io/openai/mcpOr bridge it through mcp-remote in claude_desktop_config.json (needs Node.js):
{
"mcpServers": {
"cleanapp": {
"command": "npx",
"args": [
"-y",
"mcp-remote",
"https://live.cleanapp.io/openai/mcp"
]
}
}
}Cursor
Or add it to ~/.cursor/mcp.json (or .cursor/mcp.json in a project):
{
"mcpServers": {
"cleanapp": {
"url": "https://live.cleanapp.io/openai/mcp"
}
}
}VS Code
Or add it to .vscode/mcp.json:
{
"servers": {
"cleanapp": {
"type": "http",
"url": "https://live.cleanapp.io/openai/mcp"
}
}
}Or from a terminal:
code --add-mcp '{"name": "cleanapp", "type": "http", "url": "https://live.cleanapp.io/openai/mcp"}'Windsurf
Add it to ~/.codeium/windsurf/mcp_config.json:
{
"mcpServers": {
"cleanapp": {
"serverUrl": "https://live.cleanapp.io/openai/mcp"
}
}
}Other clients
Most clients accept this shape. The endpoint is:
https://live.cleanapp.io/openai/mcp{
"mcpServers": {
"cleanapp": {
"type": "http",
"url": "https://live.cleanapp.io/openai/mcp"
}
}
}If it does not connect
- Restart the client after editing a config file, and keep keys out of files you commit.
- If the tools do not appear, open the client's MCP log: a 401 means the credentials were not accepted, and a timeout means the server did not answer.
Tools 5
Names, descriptions and input schemas exactly as the server returned them on 2026-11-22. This is the server author's own text. Nothing is run from this page. Labels such as read-only are declared by the server and are not verified. Raw JSON
cleanapp_openread-onlyexternal accessOpens CleanApp’s interactive home panel for observed physical and digital problems, public reports, and …
Opens CleanApp’s interactive home panel for observed physical and digital problems, public reports, and private receipt tracking.
Takes no parameters.
Example call (required arguments only, placeholder values):
{
"method": "tools/call",
"params": {
"name": "cleanapp_open",
"arguments": {}
}
}cleanapp_prepare_reportread-onlyexternal accessCreates a draft preview of an observed physical or digital problem using supplied details. The preview …
Creates a draft preview of an observed physical or digital problem using supplied details. The preview includes supplied source context and the proposed publication and notice permissions. Report intake requires separate approval and submission.
| Parameter | Type | Description | |
|---|---|---|---|
domain | string | required | Physical place/infrastructure/environment issue, or digital product/service issue. One of: physical, digital |
problem_type | string | required | The observed problem category. One of: litter, illegal_dumping, pothole, accessibility, infrastructure, pollution, safety, software_bug … |
title | string | required | A factual short title, without personal identifiers. |
description | string | required | What the user observed, when and impact. Do not include secrets, private contact details or unrelated chat. |
location_text | string | optional | User-provided place, street, landmark, or area for a physical issue. Do not infer user location. |
latitude | number | optional | Optional coordinates explicitly supplied or approved by the user. |
longitude | number | optional | |
product_or_site | string | optional | Name of the affected product, app, website, or service for a digital issue. |
source_platform | string | optional | Explicitly supplied platform of the original observation, e.g. X or GitHub. Separate from the affected product and the submitting AI client; leave unknown when not provided. |
source_url | string | optional | Caller-provided public reference for the original observation. Do not copy a private chat URL, token or unrelated conversation. No URL is fetched during preparation. |
observed_at | string | optional | When the problem was observed, only if explicitly provided, as RFC3339 with a timezone. Never substitute submission time or source publication time. |
source_published_at | string | optional | Publication time of the referenced source, only if explicitly provided, as RFC3339 with a timezone. This is separate from when the problem was observed. |
reporter_context | string | optional | Caller-provided relationship to the observation. This is a claim, not verified authorship or CleanApp evidence classification. One of: firsthand, relayed, unknown |
submission_client | string | optional | Explicitly supplied submitting AI client. This label is caller-claimed, not a verified account identity; do not infer it from the affected product or source platform. One of: grok, chatgpt, claude, codex, other |
language | string | optional | Language of the report; preserve the user’s language. |
handling | object | optional | Include the requested publication and notice permissions in the exact preview. Obtain explicit user approval for those permissions before submitting; private review remains available. |
requires_redaction | boolean | optional | Set true when the user requests redaction or declares private information. Omitting this does not bypass CleanApp privacy checks. |
Example call (required arguments only, placeholder values):
{
"method": "tools/call",
"params": {
"name": "cleanapp_prepare_report",
"arguments": {
"domain": "physical",
"problem_type": "litter",
"title": "...",
"description": "..."
}
}
}cleanapp_report_statusread-onlyexternal accessLooks up a report using its private tracking token and returns recorded intake, analysis, decision and …
Looks up a report using its private tracking token and returns recorded intake, analysis, decision and reason, publication and notice status, and the next action. Results can include verified public links and related-report candidates.
| Parameter | Type | Description | |
|---|---|---|---|
tracking_token | string | required | Private tracking token returned when the report was prepared or submitted. Never guess report IDs. |
Example call (required arguments only, placeholder values):
{
"method": "tools/call",
"params": {
"name": "cleanapp_report_status",
"arguments": {
"tracking_token": "..."
}
}
}cleanapp_search_reportsread-onlyexternal accessSearches historical public reports about potholes, litter, illegal dumping, accessibility barriers, …
Searches historical public reports about potholes, litter, illegal dumping, accessibility barriers, infrastructure damage, pollution, software bugs, scams, and service failures. Coverage is limited to existing public reports.
| Parameter | Type | Description | |
|---|---|---|---|
query | string | required | Specific words describing the issue, place, or product, e.g. pothole or broken elevator. Search requires all words. |
domain | string | optional | One of: physical, digital, all |
language | string | optional | |
limit | integer | optional |
Example call (required arguments only, placeholder values):
{
"method": "tools/call",
"params": {
"name": "cleanapp_search_reports",
"arguments": {
"query": "..."
}
}
}cleanapp_submit_reportcan modifydestructiveexternal accessSends an approved draft to CleanApp’s private quarantine for review and returns a private tracking receipt. …
Sends an approved draft to CleanApp’s private quarantine for review and returns a private tracking receipt. The draft retains its approved publication and notice permissions. In the recorded result, held means received but blocked.
| Parameter | Type | Description | |
|---|---|---|---|
draft_token | string | required | |
confirmed | boolean | required | True only after the user approves the exact report preview, its disclosed publication and notice permissions, and sending it to CleanApp. |
Example call (required arguments only, placeholder values):
{
"method": "tools/call",
"params": {
"name": "cleanapp_submit_report",
"arguments": {
"draft_token": "...",
"confirmed": false
}
}
}Resources 1
cleanapp-app
Badge
Maintain this server? Put its live status in your README:
[](https://mcp.aianytime.net/s/cleanapp/)Edit this entry · Report a problem
More in Work & productivity
Checks record what a server answered, not whether it is safe. A listing is not a security audit; read a server's source and permissions before you connect it. Add a server · JSON · llms.txt · llms-full.txt
Browse: Agents, IDEs & developer tools · Search & discovery · Knowledge, memory & context · Media & generation · Security · Finance & markets · Marketing, content & social · Cloud, ops & data · Commerce, travel & logistics · Work & productivity · No account needed · Local servers