# AgentDataAPI (remote · agentdataapi.com)

Grid power prices and carbon, open sensors, weather alerts and forecasts, news and social signals.

- Trust score: 75/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- remote · `agentdataapi.com`: 75/100 (this document), [markdown](https://verifymcp.io/servers/com-agentdataapi-agentdata/agentdataapi.md), [page](https://verifymcp.io/servers/com-agentdataapi-agentdata/agentdataapi)

## Channel facts

- Endpoint: `https://agentdataapi.com/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.1.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-21.

- **Endpoint Security**: 74/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Nothing on it is marked destructive, but we can't show that an anonymous caller can only read: full credit needs the server to list at least one tool and every tool to be verifiably read-only. We use a best-effort check of tool names and descriptions to tell read-only tools from tools that change things, so some genuinely read-only tools may not get full credit. Names that start with a read verb (get, list, read, search and similar) and accurate readOnlyHint annotations help. Meet that to earn full credit, or require authorisation.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 72/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 3508 tokens (~85/item across 41 items; 41 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 33/100
  - Stability observed for 10 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 41 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 42 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the AgentDataAPI MCP server?

AgentDataAPI is a hosted endpoint at https://agentdataapi.com/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http com-agentdataapi-agentdata 'https://agentdataapi.com/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "com-agentdataapi-agentdata": {
      "url": "https://agentdataapi.com/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "com-agentdataapi-agentdata": {
      "type": "http",
      "url": "https://agentdataapi.com/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.com-agentdataapi-agentdata]
url = "https://agentdataapi.com/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-agentdataapi-agentdata": {
      "type": "remote",
      "url": "https://agentdataapi.com/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-agentdataapi-agentdata --url 'https://agentdataapi.com/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-agentdataapi-agentdata:
    url: "https://agentdataapi.com/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "com-agentdataapi-agentdata": {
      "Transport": "http",
      "Url": "https://agentdataapi.com/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-agentdataapi-agentdata -t streamable-http -u 'https://agentdataapi.com/mcp'
```

### Other

```json
{
  "mcpServers": {
    "com-agentdataapi-agentdata": {
      "type": "http",
      "url": "https://agentdataapi.com/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-20 (score 75, +1)

No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-18 (score 74, +1)

No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-16 (score 73, +1)

No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-14 (score 72, +2)

- [security] Tool “list_capabilities” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 75 → 85
- [functional improvement] Tool coverage: 63% → 100%
- [cosmetic] “hot_discussions” reworded the description of “limit”
- [cosmetic] “news_sentiment_history” reworded the description of “entity”
- [cosmetic] “news_sentiment_history” reworded the description of “limit”
- [cosmetic] “news_top_stories” reworded the description of “limit”
- [cosmetic] “news_trending” reworded the description of “limit”
- [cosmetic] “news_trending” reworded the description of “window”
- [cosmetic] “news_trending_people” reworded the description of “limit”
- [cosmetic] “news_trending_topics” reworded the description of “limit”
- [cosmetic] “sensors_air_near” reworded the description of “lat”
- [cosmetic] “sensors_air_near” reworded the description of “lon”
- [cosmetic] “sensors_air_near” reworded the description of “radius_km”
- [cosmetic] “sensors_quakes” reworded the description of “hours”
- [cosmetic] “sensors_quakes” reworded the description of “lat”
- [cosmetic] “sensors_quakes” reworded the description of “lon”
- [cosmetic] “sensors_quakes” reworded the description of “min_mag”
- [cosmetic] “sensors_quakes” reworded the description of “radius_km”
- [cosmetic] “sensors_stations_near” reworded the description of “lat”
- [cosmetic] “sensors_stations_near” reworded the description of “lon”
- [cosmetic] “sensors_stations_near” reworded the description of “radius_km”
- [cosmetic] “sensors_tide_predictions” reworded the description of “station”
- [cosmetic] “sensors_water_history” reworded the description of “limit”
- [cosmetic] “sensors_water_history” reworded the description of “site”
- [cosmetic] “social_history” reworded the description of “limit”
- [cosmetic] “social_top_mentions” reworded the description of “limit”
- [cosmetic] “social_trending_links” reworded the description of “limit”
- [cosmetic] “social_trending_topics” reworded the description of “limit”
- [cosmetic] “trending_github_repos” reworded the description of “limit”
- [cosmetic] “weather_alerts” reworded the description of “limit”
- [cosmetic] “weather_forecast” reworded the description of “hours”
- [cosmetic] “weather_forecast” reworded the description of “lat”
- [cosmetic] “weather_forecast” reworded the description of “lon”
- [cosmetic] “weather_forecast_daily” reworded the description of “days”
- [cosmetic] “weather_forecast_daily” reworded the description of “lat”
- [cosmetic] “weather_forecast_daily” reworded the description of “lon”
- [cosmetic] “weather_stations_near” reworded the description of “lat”
- [cosmetic] “weather_stations_near” reworded the description of “lon”
- [cosmetic] “weather_stations_near” reworded the description of “radius_km”

### 2026-11-13 (score 70, +1)

- [security] The server rewrote its instructions, which are the text every model session reads
- [functional regression] Schema quality: 2422 → 3097
- [functional] New tool “hot_discussions”
- [functional] New tool “social_history”
- [functional] New tool “social_network_stats”
- [functional] New tool “social_symbol_mentions”
- [functional] New tool “social_top_mentions”
- [functional] New tool “social_topic_trend”
- [functional] New tool “social_trending_links”
- [functional] New tool “social_trending_topics”
- [functional] New tool “trending_github_repos”

### 2026-11-12 (score 69, 0)

- [functional improvement] Stability: unverified → 0.03

### 2026-11-11 (score 69)

First indexed and scored.

## MCP tools (41)

### `list_capabilities` (~38 tokens)

What this server offers across energy, sensors, weather, news and social: endpoints, prices and the first calls to make. No key needed.

### `create_free_api_key` (~59 tokens)

Create a FREE AgentDataAPI key (no signup) valid for every slice. Returned once; add it to the server's X-API-Key header.

Input parameters:

- `email` (string, required): Your human's real email, else your own agent mailbox.

### `grid_regions` (~44 tokens)

Every power market region we serve: code, market, timezone, currency, source and price cadence.

Input parameters:

- `market`: nem, gb, eu or us; omit for all

### `grid_price` (~78 tokens)

Latest settled wholesale electricity price for a region (micro units of local currency, USD conversion, demand, negative-price flag).

Input parameters:

- `market` (string, required): nem (Australia), gb, eu or us
- `region` (string, required): Region code, e.g. NSW1, GB, DE_LU, CAISO. List them with grid_regions.

### `grid_day_ahead` (~102 tokens)

Day-ahead (EU) or pre-dispatch (NEM) prices per interval for a local day, with min, max, average and negative intervals.

Input parameters:

- `date`: Local calendar day YYYY-MM-DD, default tomorrow
- `market` (string, required): nem (Australia), gb, eu or us
- `region` (string, required): Region code, e.g. NSW1, GB, DE_LU, CAISO. List them with grid_regions.

### `grid_price_history` (~118 tokens)

Settled prices for the last 7 days (Pro), optionally averaged per 30 or 60 minutes.

Input parameters:

- `from`: ISO UTC start, default 7 days ago
- `interval` (string): native, 30m or 60m
- `market` (string, required): nem (Australia), gb, eu or us
- `region` (string, required): Region code, e.g. NSW1, GB, DE_LU, CAISO. List them with grid_regions.
- `to`: ISO UTC end, default now

### `grid_load` (~63 tokens)

Latest grid demand for a region in MW.

Input parameters:

- `market` (string, required): nem (Australia), gb, eu or us
- `region` (string, required): Region code, e.g. NSW1, GB, DE_LU, CAISO. List them with grid_regions.

### `grid_generation` (~74 tokens)

Latest generation mix for a region: MW per fuel, total and renewables share (basis points).

Input parameters:

- `market` (string, required): nem (Australia), gb, eu or us
- `region` (string, required): Region code, e.g. NSW1, GB, DE_LU, CAISO. List them with grid_regions.

### `grid_cheapest_window` (~109 tokens)

Cheapest contiguous window of N hours in the next horizon from day-ahead or pre-dispatch prices (GB: greenest window from the carbon forecast).

Input parameters:

- `horizon` (integer): Look-ahead in hours
- `hours` (integer): Window length in hours
- `market` (string, required): nem (Australia), gb, eu or us
- `region` (string, required): Region code, e.g. NSW1, GB, DE_LU, CAISO. List them with grid_regions.

### `grid_carbon` (~63 tokens)

GB grid carbon intensity in gCO2/kWh: actual and forecast now, the next 6 hours, and the regional generation mix.

Input parameters:

- `region` (string): GB for national, or a NESO region id 1 to 17 (13 = London)

### `petroleum_weekly` (~52 tokens)

Latest EIA weekly US petroleum inventory figure with the previous week and the change.

Input parameters:

- `series` (string): crude_stocks, gasoline_stocks, distillate_stocks, refinery_inputs or crude_imports

### `sensors_stations_near` (~134 tokens)

Stations of every open sensor network near a point, nearest first, with distance and parameters.

Input parameters:

- `lat` (number, required): Latitude in decimal degrees, e.g. -33.87
- `lon` (number, required): Longitude in decimal degrees, e.g. 151.21
- `network`: usgs, coops or openaq
- `parameter`: pm25, pm10, o3, no2, so2, co, gage_height, discharge, water_temp, water_level
- `radius_km` (number): Search radius in km, default 25, max 500

### `sensors_air` (~43 tokens)

Latest air quality readings and US EPA AQI at one monitor.

Input parameters:

- `station_id` (string, required): openaq_{location_id}, e.g. openaq_2178

### `sensors_air_near` (~105 tokens)

Air quality monitors near a point with latest readings (PM2.5, PM10, O3, NO2, SO2, CO) and AQI, nearest first.

Input parameters:

- `lat` (number, required): Latitude in decimal degrees, e.g. -33.87
- `lon` (number, required): Longitude in decimal degrees, e.g. 151.21
- `radius_km` (number): Search radius in km, default 25, max 500

### `sensors_water_gauge` (~57 tokens)

Latest river gauge height, discharge and water temperature at a USGS site, with NWS flood stage status.

Input parameters:

- `site` (string, required): USGS site number, e.g. 01646500 (Potomac at Little Falls)

### `sensors_water_history` (~86 tokens)

Gauge readings for the last 7 days at a USGS site, newest first (Pro).

Input parameters:

- `end`: ISO time, latest
- `limit` (integer): Max readings to return, default 500
- `site` (string, required): USGS site number, e.g. 01646500 (Potomac at Little Falls)
- `start`: ISO time, earliest

### `sensors_tides` (~58 tokens)

Latest observed water level (metres MLLW) at a NOAA tide station with the next high and low.

Input parameters:

- `station` (string, required): NOAA CO-OPS station id, e.g. 8518750 (The Battery, NY)

### `sensors_tide_predictions` (~64 tokens)

Predicted high and low tides for a day at a NOAA tide station.

Input parameters:

- `date`: YYYY-MM-DD (UTC), default today
- `station` (string, required): NOAA CO-OPS station id, e.g. 8518750 (The Battery, NY)

### `sensors_quakes` (~124 tokens)

Earthquakes in the last N hours from USGS, optionally above a magnitude and within a radius of a point.

Input parameters:

- `hours` (integer): Look-back window in hours, default 24, max 720
- `lat`: Centre latitude in decimal degrees; with lon and radius_km limits results to a circle
- `lon`: Centre longitude in decimal degrees
- `min_mag`: Minimum magnitude, e.g. 4.5; omit for all
- `radius_km`: Radius in km around lat/lon, max 20000

### `weather_alerts` (~98 tokens)

Active weather alerts for a region, severity first. US from the National Weather Service; Australia from the Bureau of Meteorology where licensed.

Input parameters:

- `limit` (integer): Max alerts to return, default 100
- `region` (string, required): US state (TX), NWS zone or county code (TXZ229), Australian state (NSW), or US / AU
- `severity`: Extreme, Severe, Moderate, Minor or Unknown

### `weather_current` (~60 tokens)

Current conditions at the nearest reporting station (within 150 km) in the United States or Australia.

Input parameters:

- `lat` (number, required): Latitude, e.g. -33.87
- `lon` (number, required): Longitude, e.g. 151.21

### `weather_forecast` (~94 tokens)

Hourly GFS forecast (temperature, humidity, wind, gust, precipitation, cloud) for a point in the contiguous US or Australia.

Input parameters:

- `hours` (integer): Forecast horizon in hours, default 48, max 120
- `lat` (number, required): Latitude in decimal degrees, e.g. -33.87
- `lon` (number, required): Longitude in decimal degrees, e.g. 151.21

### `weather_forecast_daily` (~92 tokens)

Daily forecast summary (min and max temperature, wind, gust, precipitation total) for a point in the contiguous US or Australia.

Input parameters:

- `days` (integer): Number of days, default 3, max 5
- `lat` (number, required): Latitude in decimal degrees, e.g. -33.87
- `lon` (number, required): Longitude in decimal degrees, e.g. 151.21

### `weather_stations_near` (~85 tokens)

Reporting stations near a point in the United States or Australia, nearest first.

Input parameters:

- `lat` (number, required): Latitude in decimal degrees, e.g. -33.87
- `lon` (number, required): Longitude in decimal degrees, e.g. 151.21
- `radius_km` (number): Search radius in km, default 50, max 500

### `news_search_entities` (~69 tokens)

Search the tracked entities (organisations, tickers, crypto assets, central banks, governments, topics) and get their ids.

Input parameters:

- `kind`: org, ticker, crypto, central_bank, government, topic
- `query`: Free text: 'nvidia', 'fed', 'bitcoin'

### `news_sentiment` (~75 tokens)

News tone (bps), mentions against the 30-day baseline, volume ratio, novelty and top themes for one entity.

Input parameters:

- `entity` (string, required): Entity id such as org_nvidia, cb_federal_reserve, asset_bitcoin
- `window` (string): 1h, 24h or 7d

### `news_ticker_score` (~67 tokens)

News score for a ticker: how unusual the coverage volume is and how its tone compares with normal.

Input parameters:

- `symbol` (string, required): Ticker or crypto symbol: NVDA, JPM, BTC
- `window` (string): 1h, 24h or 7d

### `news_trending` (~77 tokens)

Entities with the most unusual news volume in the window, ranked by novelty against their baseline.

Input parameters:

- `kind`: ticker, crypto, org, central_bank, government, topic
- `limit` (integer): Max entities to return, default 20
- `window` (string): 1h, 24h or 7d

### `news_sentiment_history` (~81 tokens)

Mentions and tone per window or per day for an entity (Pro), newest first.

Input parameters:

- `entity` (string, required): Entity id such as org_nvidia, cb_federal_reserve, asset_bitcoin
- `interval` (string): 15m or 1d
- `limit` (integer): Max points to return, default 60

### `news_trending_people` (~63 tokens)

Public figures with the biggest attention spike (Wikipedia pageviews and news coverage over their 30-day baseline), by category.

Input parameters:

- `category`: celebrity, politics, sport, business, other
- `limit` (integer): Max people to return, default 20

### `news_trending_topics` (~57 tokens)

Trending topics for a region: top daily searches with headlines, trending Mastodon tags and shared links.

Input parameters:

- `limit` (integer): Max topics to return, default 20
- `region` (string): US, AU or GB

### `news_top_stories` (~74 tokens)

The most-covered stories in the window (title, link, publisher, tone), never article text.

Input parameters:

- `entity`: Only stories naming this entity id
- `limit` (integer): Max stories to return, default 20
- `window` (string): 1h, 6h or 24h

### `social_trending_topics` (~89 tokens)

Trending hashtags across Bluesky, Mastodon and Nostr (mentions x spike against each tag's baseline), plus Bluesky's own trends list.

Input parameters:

- `limit` (integer): Max tags to return, default 25
- `network` (string): all, bluesky, mastodon or nostr
- `window` (string): 1h, 6h or 24h

### `social_topic_trend` (~75 tokens)

One hashtag across networks: mentions per network, expected count, spike, trend, first seen and the last 24 hours by hour.

Input parameters:

- `tag` (string, required): A hashtag without #: 'bitcoin', 'ai', 'f1'
- `window` (string): 1h, 6h or 24h

### `social_trending_links` (~84 tokens)

The most-shared URLs across networks with titles, shares per network and the Hacker News, Lobsters or Lemmy discussions about them.

Input parameters:

- `domain`: Only this domain, e.g. github.com
- `limit` (integer): Max links to return, default 25
- `window` (string): 1h, 6h or 24h

### `social_top_mentions` (~79 tokens)

Stocks and crypto assets ranked by social attention: mentions against a 30-day baseline, spike, lexicon tone, discussions.

Input parameters:

- `limit` (integer): Max symbols to return, default 20
- `type` (string): all, crypto or stock
- `window` (string): 1h, 6h or 24h

### `social_symbol_mentions` (~74 tokens)

Social volume and tone for one ticker or coin: mentions per network against its baseline, spike, trend and discussions naming it.

Input parameters:

- `symbol` (string, required): Ticker or crypto symbol: BTC, ETH, NVDA, TSLA
- `window` (string): 1h, 6h or 24h

### `hot_discussions` (~66 tokens)

Hot discussions merged from Hacker News, Lobsters and Lemmy: title, link, discussion URL, score, comments, heat.

Input parameters:

- `limit` (integer): Max discussions to return, default 30
- `source` (string): all, hn, lobsters or lemmy

### `trending_github_repos` (~74 tokens)

GitHub repositories gaining the most stars in the window, with language, topics and discussions linking them.

Input parameters:

- `language`: Primary language, e.g. Rust, Python
- `limit` (integer): Max repos to return, default 25
- `window` (string): 24h or 7d

### `social_network_stats` (~36 tokens)

Activity per network: Bluesky and Nostr posts per hour, fediverse size (FediDB), Hacker News items per hour.

### `social_history` (~95 tokens)

Stored hourly or daily history for a hashtag, a symbol (mentions and tone) or a GitHub repo (stars), newest first (Pro).

Input parameters:

- `key` (string, required): The tag, the symbol (BTC) or the repo (owner/name)
- `kind` (string, required): tag, symbol or repo
- `limit` (integer): Max points to return, default 60
- `resolution` (string): hour or day

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/com-agentdataapi-agentdata/agentdataapi#diagnostics

## Score history

- 2026-11-21: 75
- 2026-11-20: 75
- 2026-11-19: 74
- 2026-11-18: 74
- 2026-11-17: 73
- 2026-11-16: 73
- 2026-11-15: 72
- 2026-11-14: 72
- 2026-11-13: 70
- 2026-11-12: 69
- 2026-11-11: 69

## Common questions

### What is the AgentDataAPI MCP server?

AgentDataAPI is an MCP server listed in the public MCP registry as com.agentdataapi/agentdata. Grid power prices and carbon, open sensors, weather alerts and forecasts, news and social signals. This page covers its hosted endpoint (https://agentdataapi.com/mcp).

### Is the AgentDataAPI MCP server safe to use?

AgentDataAPI scores 75 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the AgentDataAPI MCP server expose?

AgentDataAPI exposes 41 tools: list_capabilities, create_free_api_key, grid_regions, grid_price, grid_day_ahead, and 36 more. Their descriptions and schemas cost roughly 3,135 tokens of context every time the server is loaded.

### Does the AgentDataAPI MCP server require authentication?

No. We connected to AgentDataAPI without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the AgentDataAPI MCP server still maintained?

AgentDataAPI is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What did VerifyMCP test on the AgentDataAPI MCP server?

VerifyMCP ran 13 checks on AgentDataAPI, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- Remote endpoint: https://agentdataapi.com/mcp
- Website: https://agentdataapi.com/mcp-server
- Changelog RSS feed: https://verifymcp.io/servers/com-agentdataapi-agentdata/agentdataapi.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-agentdataapi-agentdata/agentdataapi/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/com-agentdataapi-agentdata/agentdataapi.json
- HTML version of this page: https://verifymcp.io/servers/com-agentdataapi-agentdata/agentdataapi
