Remote MCP server to run your Atako AI agents: chat, projects, files, integrations and channels.
- Passed: Handshake
- Passed: Tools listed
- Passed: Updated recently
Median latency 132 ms · Last checked
Explore
Evidence for your next connection.
Independent measurements of remote MCP servers. Every observation has a timestamp.
Read-only probesMCP server · Code & DevOps
PM2.5 air pollution by city: worst-first rankings, current air and daily history.
3 failed · 8 not measured
Median of successful probes over 7 days
Share of countable probes over 30 days, including daily rollups. Auth challenges are excluded.
Tool definitions returned by this server
Independent monitoring
Responded
The server completed its last measured handshake. This is an observation, not a guarantee.
Last checked| Test area | Passed | Failed | Unmeasured |
|---|---|---|---|
ConnectionCan a client connect and discover tools? | 5 | 0 | 0 |
Reliability & speedDoes it respond consistently and quickly? | 0 | 0 | 4 |
Access & authenticationWhat is required to use this server? | 1 | 0 | 2 |
Tool qualityAre the tool definitions usable by an agent? | 3 | 1 | 0 |
Publisher identityCan the publisher be traced to its source? | 2 | 2 | 2 |
Unmeasured means there is not enough evidence to decide. How these checks work
Start using SmogRank
Choose your client, copy the configuration, then enable the server in your client’s MCP settings.
Run this command in your terminal, then restart Claude Code.
Claude Code
claude mcp add --transport http smogrank https://smogrank.com/mcpCapabilities
PM2.5 now in a city: the latest hourly value, its 24-hour, 7-day, 30-day and year-to-date averages with its rank among all measured cities, the US EPA category, how it compares with the WHO guideline, and the "why it ranks here" notes (patterns in its own history and nearby fire, smoke and volcano evidence, named as likely causes, never confirmed), and the local hours its air was usually worst and cleanest over the last 30 days. Each measured city's trust says what stands behind it: checked (reference monitors at 2+ sites), one (a single reference site) or low (3+ low-cost sensors). Cities without a monitor get a model estimate, labelled as one, plus few_sensors when one or two low-cost sensors measure there (not ranked). No forecasts.
DiscoveredA measured city's daily mean PM2.5 (its local calendar days, µg/m³) and its daily rank, between two dates (up to 400 days; default the last 30), with monthly means. Also a city measured only in the past, or a day late (China's national network), with no rank.
DiscoveredSearch SmogRank's cities by name (local, old and short names too: "München", "Bombay", "NYC"), or find the nearest ones to a point. Returns each city's path for the other tools, whether it is measured by ground monitors (ranked) or only estimated from a model, and its page; a name search also returns the countries and regions it names, as places with their page.
DiscoveredThe ranking of measured cities by average PM2.5, worst first: a rolling window (24h, 7d, 30d, year to date) or a past period (a day 2026-09-30, a week 2026-W40, a month 2026-09, a year 2025). Optionally one country.
DiscoveredRecent measurements
| Checked | Result | Response | Tools |
|---|---|---|---|
| Connected | 74 ms | 4 |