# Agent Data Hub (remote · api.agentdatahub.de)

Official statistics and economic data for agents, with source and licence per answer. No key.

- Trust score: 80/100 (high trust)
- Change this week: +2
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- remote · `api.agentdatahub.de`: 80/100 (this document), [markdown](https://verifymcp.io/servers/jona1245-agentdatahub/api.md), [page](https://verifymcp.io/servers/jona1245-agentdatahub/api)

## Channel facts

- Endpoint: `https://api.agentdatahub.de/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.6.2`

## 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**: 80/100
  - 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.
  - The HSTS (Strict-Transport-Security) header is present.
  - 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**: 71/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (fair).
  - Tool/resource definitions use about 908 tokens (~100/item across 9 items; 9 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 83/100
  - Stability observed for 25 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 67/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 0% 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 9 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 10 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 60/100
  - Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28.

## Install

### How do I install the Agent Data Hub MCP server?

Agent Data Hub is a hosted endpoint at https://api.agentdatahub.de/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 jona1245-agentdatahub 'https://api.agentdatahub.de/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "jona1245-agentdatahub": {
      "url": "https://api.agentdatahub.de/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "jona1245-agentdatahub": {
      "type": "http",
      "url": "https://api.agentdatahub.de/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.jona1245-agentdatahub]
url = "https://api.agentdatahub.de/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "jona1245-agentdatahub": {
      "type": "remote",
      "url": "https://api.agentdatahub.de/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add jona1245-agentdatahub --url 'https://api.agentdatahub.de/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  jona1245-agentdatahub:
    url: "https://api.agentdatahub.de/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "jona1245-agentdatahub": {
      "Transport": "http",
      "Url": "https://api.agentdatahub.de/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add jona1245-agentdatahub -t streamable-http -u 'https://api.agentdatahub.de/mcp'
```

### Other

```json
{
  "mcpServers": {
    "jona1245-agentdatahub": {
      "type": "http",
      "url": "https://api.agentdatahub.de/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.

### 2026-11-21 (score 80, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “call_api” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 86 → 100

### 2026-11-19 (score 80, +1)

No change was recorded against any check on this day. Stability & Change Management went from 73 to 77. That category is still filling its 30-day observation window: 22 days of observed history at the previous scan, 23 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-18 (score 79, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “report_issue” rewrote its description, which is the text the model reads
- [security] Tool “ask_anything” rewrote its description, which is the text the model reads
- [security] Tool “call_api” rewrote its description, which is the text the model reads
- [security] Tool “find_data” rewrote its description, which is the text the model reads
- [security] Tool “get_history” rewrote its description, which is the text the model reads
- [security] Tool “get_series” rewrote its description, which is the text the model reads
- [security] Tool “search_apis” rewrote its description, which is the text the model reads
- [functional regression] Tool coverage: 100% → 0%
- [functional regression] “find_data” changed the type of “limit”: number → integer
- [functional regression] “search_apis” changed the type of “limit”: number → integer
- [functional improvement] Schema quality: fail → pass
- [functional] The server now declares the “prompts” capability
- [functional] First check of Schema quality: 100
- [functional] Schema quality: excellent → fair
- [functional] New prompt “cite_number”
- [functional] New prompt “compare_countries”
- [functional] New prompt “fx_on_date”
- [functional] New prompt “group_table”
- [functional] New prompt “series_summary”
- [functional] Server version: 1.7.0 → 1.9.0
- [functional] New tool “get_holidays”
- [functional] New tool “get_table”
- [cosmetic] “ask_anything” reworded the description of “query”
- [cosmetic] “ask_anything” reworded the description of “questions”
- [cosmetic] “call_api” reworded the description of “apiId”
- [cosmetic] “call_api” reworded the description of “fields”
- [cosmetic] “call_api” reworded the description of “params”
- [cosmetic] “find_data” reworded the description of “limit”
- [cosmetic] “find_data” reworded the description of “measure”
- [cosmetic] “find_data” reworded the description of “period”
- [cosmetic] “find_data” reworded the description of “place”
- [cosmetic] “find_data” reworded the description of “query”
- [cosmetic] “get_history” reworded the description of “apiId”
- [cosmetic] “get_history” reworded the description of “from”
- [cosmetic] “get_history” reworded the description of “params”
- [cosmetic] “get_series” reworded the description of “agg”
- [cosmetic] “get_series” reworded the description of “from”
- [cosmetic] “get_series” reworded the description of “id”
- [cosmetic] “get_series” reworded the description of “limit”
- [cosmetic] “get_series” reworded the description of “q”
- [cosmetic] “get_series” reworded the description of “resample”
- [cosmetic] “get_series” reworded the description of “to”
- [cosmetic] “report_issue” reworded the description of “apiId”
- [cosmetic] “report_issue” reworded the description of “kind”
- [cosmetic] “report_issue” reworded the description of “params”
- [cosmetic] “report_issue” reworded the description of “series”
- [cosmetic] “report_issue” reworded the description of “text”
- [cosmetic] “search_apis” reworded the description of “limit”
- [cosmetic] “search_apis” reworded the description of “search”
- [cosmetic] “ask_anything” dropped the optional parameter “full”
- [cosmetic] “ask_anything” dropped the optional parameter “mode”
- [cosmetic] “call_api” dropped the optional parameter “full”
- [cosmetic] “call_api” dropped the optional parameter “verbose”
- [cosmetic] “get_history” dropped the optional parameter “fields”
- [cosmetic] “get_history” dropped the optional parameter “limit”
- [cosmetic] “search_apis” dropped the optional parameter “category”
- [cosmetic] Tool “find_data” changed its title: Find candidate data series → Find data series
- [cosmetic] Tool “get_history” changed its title: Get recorded endpoint history → Get recorded history
- [cosmetic] Tool “get_series” changed its title: Get a full time series → Get a time series
- [cosmetic] Tool “search_apis” changed its title: Search the endpoint catalog → Search endpoints

### 2026-11-17 (score 79, 0)

- [security] Tool “get_series” rewrote its description, which is the text the model reads
- [cosmetic] “get_series” added an optional parameter “limit”

### 2026-11-16 (score 79, +1)

- [security] Tool “find_data” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 1988 → 2287
- [functional] Server version: 1.6.2 → 1.7.0
- [functional] New tool “report_issue”

### 2026-11-13 (score 78, +1)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “ask_anything” rewrote its description, which is the text the model reads
- [security] Tool “find_data” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 289 → 331
- [cosmetic] “ask_anything” added an optional parameter “mode”
- [cosmetic] “ask_anything” added an optional parameter “full”

### 2026-11-12 (score 77, 0)

- [security] Tool “ask_anything” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 1439 → 1739
- [functional] New tool “find_data”

### 2026-11-10 (score 77, +1)

No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes.

## MCP tools (9)

### `get_series` (~155 tokens)

Get a time series

Full history of one number as CSV: FX since 1999 (fx.EUR.USD), World Bank since 1960 (wb.{code}.{country}), ECB yields (ecb.yield10y.IT), Eurostat, power prices (smard.price.day), sunspots (noaa.sunspot-number). Example: {"id":"wb.FP.CPI.TOTL.ZG.DE","from":"2000"}; {"q":"inflation germany"} finds ids.

Input parameters:

- `agg` (string)
- `from` (string)
- `id` (string)
- `limit` (integer)
- `q` (string)
- `resample` (string)
- `to` (string)

### `find_data` (~92 tokens)

Find data series

Lists up to 10 series that may answer a data question, each with its call_api arguments; pick the one whose measure, place and time fit, else this service does not have it. Example: {"query":"inflation chile"}.

Input parameters:

- `limit` (integer)
- `measure` (string)
- `period` (string)
- `place` (string)
- `query` (string)

### `get_table` (~127 tokens)

Get a country group table

Newest value of one World Bank indicator for every member of a country group, highest first. period "common" puts every row on one period (members without it in missing). top (1-50) ranks the members and returns the first N, each row with its rank (order desc or asc). Example: {"indicator":"SP.POP.TOTL","group":"G20","period":"common"}.

Input parameters:

- `group` (string, required)
- `indicator` (string, required)
- `order` (string)
- `period` (string)
- `top` (integer)

### `get_holidays` (~63 tokens)

Get public holidays

Public holidays of a country, or one of its regions, in one year. Example: {"country":"DE","year":2027,"region":"BY"}.

Input parameters:

- `country` (string, required)
- `region` (string)
- `year` (integer, required)

### `ask_anything` (~40 tokens)

Answer a data question

Answers a data question in words. Example: {"query":"population of pakistan"}.

Input parameters:

- `query` (string)
- `questions` (array)

### `search_apis` (~39 tokens)

Search endpoints

Searches the endpoint catalog. Example: {"search":"electricity price germany"}.

Input parameters:

- `limit` (integer)
- `search` (string)

### `call_api` (~109 tokens)

Call an endpoint

Runs one endpoint or tool by id. Tools: fx-rate-on-day, purchasing-power, vat-rates, minimum-wage, software-end-of-life, ai-model-facts, publisher-licence, package-version, bot-lookup. Example: {"apiId":"fx-rate-on-day","params":{"from":"EUR","to":"USD","date":"2024-01-15"}}.

Input parameters:

- `apiId` (string, required)
- `fields` (string)
- `params` (object)

### `get_history` (~57 tokens)

Get recorded history

Values recorded from a live endpoint over time. Example: {"apiId":"bundle-location-brief","params":{"place":"Berlin"}}.

Input parameters:

- `apiId` (string, required)
- `from` (string)
- `params` (object)

### `report_issue` (~77 tokens)

Report a wrong value

Stores a report of a wrong value for a manual check; changes no data. Example: {"series":"fx.EUR.USD","kind":"wrong_value"}.

Input parameters:

- `apiId` (string)
- `kind` (string, required)
- `params` (object)
- `series` (string)
- `text` (string)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/jona1245-agentdatahub/api#diagnostics

## Score history

- 2026-11-21: 80
- 2026-11-20: 80
- 2026-11-19: 80
- 2026-11-18: 79
- 2026-11-17: 79
- 2026-11-16: 79
- 2026-11-15: 78
- 2026-11-14: 78
- 2026-11-13: 78
- 2026-11-12: 77
- 2026-11-11: 77
- 2026-11-10: 77
- 2026-11-09: 76
- 2026-11-08: 76
- 2026-11-07: 75
- 2026-11-06: 75
- 2026-11-05: 74
- 2026-11-04: 74
- 2026-11-03: 73
- 2026-11-02: 73
- 2026-11-01: 72
- 2026-10-31: 72
- 2026-10-30: 72
- 2026-10-29: 71
- 2026-10-28: 63
- 2026-10-27: 63

## Common questions

### What is the Agent Data Hub MCP server?

Agent Data Hub is an MCP server listed in the public MCP registry as io.github.Jona1245/agentdatahub. Official statistics and economic data for agents, with source and licence per answer. No key. This page covers its hosted endpoint (https://api.agentdatahub.de/mcp).

### Is the Agent Data Hub MCP server safe to use?

Agent Data Hub scores 80 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 Agent Data Hub MCP server expose?

Agent Data Hub exposes 9 tools: get_series, find_data, get_table, get_holidays, ask_anything, and 4 more. Their descriptions and schemas cost roughly 759 tokens of context every time the server is loaded.

### Does the Agent Data Hub MCP server require authentication?

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

### Is the Agent Data Hub MCP server still maintained?

Agent Data Hub 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 Agent Data Hub MCP server?

VerifyMCP ran 13 checks on Agent Data Hub, 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://api.agentdatahub.de/mcp
- Website: https://api.agentdatahub.de/
- Changelog RSS feed: https://verifymcp.io/servers/jona1245-agentdatahub/api.xml
- Changelog JSON feed: https://verifymcp.io/servers/jona1245-agentdatahub/api/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/jona1245-agentdatahub/api.json
- HTML version of this page: https://verifymcp.io/servers/jona1245-agentdatahub/api
