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.

DiscoverIA

REMOTE · MCP.DISCOVERIA.AI

Read-only registry of AI-assisted scientific claims and where their evaluation stands (fr/en)

+3 this week 80 Trust /100

Last scanned (15 hours ago)

Scores higher than 77% of remote servers

Reachable. Last reached 21 Nov 2026.

Category Health and Science

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 Security66
  • 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 enforcement could not be verified: the plaintext port answered with HTTP 405, which proves neither a plaintext path nor enforcement. View diagnostics → Unverified
  • HSTS check failed: the Strict-Transport-Security header is absent. See how to fix → View diagnostics → Fail
  • DNSSEC is configured correctly; the domain's records validate against the full chain to the root. View diagnostics → Pass
Transport & Reachability100
Schema Quality & AI Usability67
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 1149 tokens (~191/item across 6 items; 6 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
  • No destabilizing schema changes in the last 30 days.Pass
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 6 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 7 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a current MCP spec version (2026-07-28).Pass
What we tested

Checks we ran (12)

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

Checks we could not complete (1)

These are gaps on our side, not findings about this hosted endpoint. We only credit what we can confirm, so a category made up entirely of them scores 0.

  • HTTPS in Endpoint SecurityHTTPS enforcement could not be verified: the plaintext port answered with HTTP 405, which proves neither a plaintext path nor enforcement.

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
    • Stability: 0.97 → pass security
  • 20 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.

  • 17 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.

  • 15 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 77 to 80. That category is still filling its 30-day observation window: 23 days of observed history at the previous scan, 24 at this one. The score rises as the window fills, whether or not the server changes.

  • 13 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 70 to 73. That category is still filling its 30-day observation window: 21 days of observed history at the previous scan, 22 at this one. The score rises as the window fills, whether or not the server changes.

  • 11 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 63 to 67. That category is still filling its 30-day observation window: 19 days of observed history at the previous scan, 20 at this one. The score rises as the window fills, whether or not the server changes.

  • 9 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 57 to 60. That category is still filling its 30-day observation window: 17 days of observed history at the previous scan, 18 at this one. The score rises as the window fills, whether or not the server changes.

  • 7 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 50 to 53. That category is still filling its 30-day observation window: 15 days of observed history at the previous scan, 16 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://mcp.discoveria.ai/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=discoveria.ai CN=WE1,O=Google Trust Services,C=US 22 Oct 2026 20 Jan 2027 ECDSA 256 ECDSA-SHA256 760566efe0187ea113a340d7db6767c6
SANs: discoveria.ai, mcp.discoveria.ai, *.mcp.discoveria.ai
CN=WE1,O=Google Trust Services,C=US (CA) CN=GTS Root R4,O=Google Trust Services LLC,C=US 13 Dec 2023 20 Feb 2029 ECDSA 256 ECDSA-SHA384 7ff31977972c224a76155d13b6d685e3
CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE 15 Nov 2023 28 Jan 2028 ECDSA 384 SHA256-RSA 7fe530bf331343bedd821610493d8a1b

Background: What to check on a remote MCP endpoint →

DNSSEC secure

Validation of mcp.discoveria.ai. — Secure

Zone DS Keys Algorithms Outcome
. Trust anchor 20326, 38696 8, 8 Verified
ai. DS published 1814 8 Verified
discoveria.ai. DS published 2371 13 Verified
mcp.discoveria.ai. Verified address RRset verified with the apex keys
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
x-content-type-options nosniff

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

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://mcp.discoveria.ai/mcp Verified 200
http (plaintext) http://mcp.discoveria.ai/mcp Inconclusive 405
MCP tools · 6 exposed · ~1,056 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
get_announcement ~138

Get one entry of the DiscoverIA registry by id: claim, claimant, current status with its rule, dated status history with sources, verifiers, links, statement fidelity, events, related frontiers and the plain-language summary. A status says where the evaluation stands, not whether the result is true.

NameTypeReqDescription
idstringyesEntry id (slug), e.g. 'gauss-sphere-packing-dim8', as returned by search_announcements.
langstring–Language of titles, labels and texts: 'fr' (French) or 'en' (English). Default 'en'. Use the user's language.

No output schema declared.

No examples provided.

get_citation ~137

Dated citation of a registry entry in APA and/or BibTeX, with its status and the date that status was observed. Data are CC BY 4.0, credit DiscoverIA.

NameTypeReqDescription
idstringyesEntry id (slug), e.g. 'gauss-sphere-packing-dim8', as returned by search_announcements.
langstring–Language of titles, labels and texts: 'fr' (French) or 'en' (English). Default 'en'. Use the user's language.
stylestring–'apa', 'bibtex' or 'both'. Default 'both'.

No output schema declared.

No examples provided.

get_frontier ~134

Frontiers track the best known bound of a quantity (e.g. a kissing number) and who moved it. With an id: the frontier, its current lower and upper records (exact values as strings, never rounded) and its series. Without an id: the list of frontiers with their current records.

NameTypeReqDescription
idstring–Frontier id, e.g. 'kissing-d11'. Omit to list all frontiers.
langstring–Language of titles, labels and texts: 'fr' (French) or 'en' (English). Default 'en'. Use the user's language.

No output schema declared.

No examples provided.

list_statuses ~88

List DiscoverIA's six evaluation statuses for scientific claims (and the provisional product statuses) with their definitions and the number of entries in each. A status says where the evaluation stands, not whether the result is true.

NameTypeReqDescription
langstring–Language of titles, labels and texts: 'fr' (French) or 'en' (English). Default 'en'. Use the user's language.

No output schema declared.

No examples provided.

recent_changes ~137

Latest status changes in the registry (last 90 days, with source) and the latest items of DiscoverIA's feed (last 30 days: sciences, models and labs, apps, devices).

NameTypeReqDescription
kindstring–'status' for status changes only, 'feed' for feed items only, 'all' for both. Default 'all'.
langstring–Language of titles, labels and texts: 'fr' (French) or 'en' (English). Default 'en'. Use the user's language.
limitinteger–Maximum items per list, 1 to 50. Default 20.

No output schema declared.

No examples provided.

search_announcements ~422

Search DiscoverIA's registry of AI-assisted scientific claims by free text, status, lab, discipline and announcement date. Returns paginated entries with their current status, the date that status was observed and a link to the entry's page. A status says where the evaluation of a claim stands, not whether the result is true. Entries from the frozen Erdős-wiki archive have statuses dated at the freeze.

NameTypeReqDescription
announced_fromstring–YYYY, YYYY-MM or YYYY-MM-DD. Keeps entries whose announcement period ends on or after this date (a claim dated '2026-02' matches announced_from '2026-02-15').
announced_tostring–YYYY, YYYY-MM or YYYY-MM-DD. Keeps entries whose announcement period starts on or before this date.
disciplinestring–Discipline slug, e.g. 'mathematiques', 'informatique-theorique', 'biologie-medecine', 'physique'.
include_archiveboolean–Include the frozen archive of T. Tao's AI-Erdős wiki (about 520 entries). Default true.
labstring–Lab slug from DiscoverIA's lab report, e.g. 'openai', 'google-deepmind', 'anthropic', 'harmonic', 'math-inc'. Matches claims announced by the lab and results obtained by others with its systems. The…
langstring–Language of titles, labels and texts: 'fr' (French) or 'en' (English). Default 'en'. Use the user's language.
pageinteger–Page number, from 1.
page_sizeinteger–Results per page, 1 to 50. Default 10.
querystring–Free text matched against title, claimant, id, discipline and nature. All words must match; accents and case are ignored. Omit to list everything.
statusstring–Keep only entries with this status (see list_statuses).

No output schema declared.

No examples provided.

Install

How do I install the DiscoverIA MCP server?

DiscoverIA is a hosted endpoint at https://mcp.discoveria.ai/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 · mcp.discoveria.ai

# add to Claude Code
claude mcp add --transport http ai-discoveria-discoveria 'https://mcp.discoveria.ai/mcp'
Common questions

What is the DiscoverIA MCP server?

DiscoverIA is an MCP server listed in the public MCP registry as ai.discoveria/discoveria. Read-only registry of AI-assisted scientific claims and where their evaluation stands (fr/en). This page covers its hosted endpoint (https://mcp.discoveria.ai/mcp).

Is the DiscoverIA MCP server safe to use?

DiscoverIA 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 DiscoverIA MCP server expose?

DiscoverIA exposes 6 tools: search_announcements, get_announcement, list_statuses, recent_changes, get_frontier, get_citation. Their descriptions and schemas cost roughly 1,056 tokens of context every time the server is loaded.

Does the DiscoverIA MCP server require authentication?

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

Is the DiscoverIA MCP server still maintained?

DiscoverIA 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 DiscoverIA MCP server?

VerifyMCP ran 12 checks on DiscoverIA, covering TLS certificate, Authorization, HSTS header, DNSSEC and 8 more. One item could not be completed, a gap on our side rather than a finding about DiscoverIA: HTTPS. 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.