Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

Agent Data Hub

REMOTE · API.AGENTDATAHUB.DE

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

+2 this week 80 Trust /100

Last scanned (18 hours ago)

Scores higher than 77% of remote servers

Reachable. Last reached 21 Nov 2026.

Category Data and Analytics

Trust breakdown (7 categories)

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. How we score → Why this is hard to score →

Endpoint Security80
  • The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
  • 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. See how to fix → View diagnostics → Partial
  • HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
  • The HSTS (Strict-Transport-Security) header is present. View diagnostics → Pass
  • DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
Transport & Reachability100
Schema Quality & AI Usability71
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (fair).Partial
  • Tool/resource definitions use about 908 tokens (~100/item across 9 items; 9 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management83
  • Stability observed for 25 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage67
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 0% of tool parameters carry a description.Fail
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 9 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 10 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities60
  • Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28. See how to fix → Fail
What we tested

Checks we ran (13)

  • TLS certificate
  • Authorization
  • HTTPS
  • HSTS header
  • DNSSEC
  • Transport
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Does not apply to this hosted endpoint (2)

  • Supply Chain SecurityScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
  • Provenance & TransparencyScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.

The score does not measure everything. What the score does not measure →

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 21 Nov 26 0
    • 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 security
    • Schema quality: 86 → 100 ▼ functional
  • 19 Nov 26 +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.

  • 18 Nov 26 0
    • 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 security
    • Tool coverage: 100% → 0% ▼ functional
    • “find_data” changed the type of “limit”: number → integer ▼ functional
    • “search_apis” changed the type of “limit”: number → integer ▼ functional
    • 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” functional
    • “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 cosmetic
  • 17 Nov 26 0
    • Tool “get_series” rewrote its description, which is the text the model reads security
    • “get_series” added an optional parameter “limit” cosmetic
  • 16 Nov 26 +1
    • Tool “find_data” rewrote its description, which is the text the model reads security
    • Schema quality: 1988 → 2287 ▼ functional
    • Server version: 1.6.2 → 1.7.0 functional
    • New tool “report_issue” functional
  • 13 Nov 26 +1
    • 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 security
    • Schema quality: 289 → 331 ▼ functional
    • “ask_anything” added an optional parameter “mode” cosmetic
    • “ask_anything” added an optional parameter “full” cosmetic
  • 12 Nov 26 0
    • Tool “ask_anything” rewrote its description, which is the text the model reads security
    • Schema quality: 1439 → 1739 ▼ functional
    • New tool “find_data” functional
  • 10 Nov 26 +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.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 21 Nov 2026 · Probed https://api.agentdatahub.de/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=api.agentdatahub.de CN=YE1,O=Let's Encrypt,C=US 27 Oct 2026 25 Jan 2027 ECDSA 256 ECDSA-SHA384 6cb7b0b2e888066d880506f8c6e7834542e
SANs: api.agentdatahub.de
CN=YE1,O=Let's Encrypt,C=US (CA) CN=Root YE,O=ISRG,C=US 3 Sept 2025 2 Sept 2028 ECDSA 384 ECDSA-SHA384 5ddd70dd31f801c85c186a7a04b80afe
CN=Root YE,O=ISRG,C=US (CA) CN=ISRG Root X2,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 ECDSA 384 ECDSA-SHA384 872165fc34b6e5fba8add5b3705fb53a
CN=ISRG Root X2,O=Internet Security Research Group,C=US (CA) CN=ISRG Root X1,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 ECDSA 384 SHA256-RSA 6c8f1dc727c7117f7baf853ac980f9cd

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of api.agentdatahub.de. — Not signed

Zone DS Keys Algorithms Outcome
. Trust anchor 20326, 38696 8, 8 Verified
de. DS published 26755 8 Verified
agentdatahub.de. No DS Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 200
Header Value
strict-transport-security max-age=31536000; includeSubDomains
x-content-type-options nosniff
x-frame-options DENY
referrer-policy strict-origin-when-cross-origin
permissions-policy camera=(), microphone=(), geolocation=()

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://api.agentdatahub.de/mcp Verified 200
http (plaintext) http://api.agentdatahub.de/mcp HTTPS enforced 308 https://api.agentdatahub.de/mcp
MCP tools · 9 exposed · ~759 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
ask_anything ~40

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

NameTypeReqDescription
querystring––
questionsarray––

No output schema declared.

No examples provided.

call_api ~109

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"}}.

NameTypeReqDescription
apiIdstringyes–
fieldsstring––
paramsobject––

No output schema declared.

No examples provided.

find_data ~92

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"}.

NameTypeReqDescription
limitinteger––
measurestring––
periodstring––
placestring––
querystring––

No output schema declared.

No examples provided.

get_history ~57

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

NameTypeReqDescription
apiIdstringyes–
fromstring––
paramsobject––

No output schema declared.

No examples provided.

get_holidays ~63

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

NameTypeReqDescription
countrystringyes–
regionstring––
yearintegeryes–

No output schema declared.

No examples provided.

get_series ~155

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.

NameTypeReqDescription
aggstring––
fromstring––
idstring––
limitinteger––
qstring––
resamplestring––
tostring––

No output schema declared.

No examples provided.

get_table ~127

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"}.

NameTypeReqDescription
groupstringyes–
indicatorstringyes–
orderstring––
periodstring––
topinteger––

No output schema declared.

No examples provided.

report_issue ~77

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

NameTypeReqDescription
apiIdstring––
kindstringyes–
paramsobject––
seriesstring––
textstring––

No output schema declared.

No examples provided.

search_apis ~39

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

NameTypeReqDescription
limitinteger––
searchstring––

No output schema declared.

No examples provided.

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.

remote · api.agentdatahub.de

# add to Claude Code
claude mcp add --transport http jona1245-agentdatahub 'https://api.agentdatahub.de/mcp'
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.