# DiscoverIA (remote · mcp.discoveria.ai)

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

- Trust score: 80/100 (high trust)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- remote · `mcp.discoveria.ai`: 80/100 (this document), [markdown](https://verifymcp.io/servers/ai-discoveria-discoveria/mcp.md), [page](https://verifymcp.io/servers/ai-discoveria-discoveria/mcp)

## Channel facts

- Endpoint: `https://mcp.discoveria.ai/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.1.0`

## 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**: 66/100
  - 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 enforcement could not be verified: the plaintext port answered with HTTP 405, which proves neither a plaintext path nor enforcement.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC is configured correctly; the domain's records validate against the full chain to the root.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 67/100
  - AI-judged instruction clarity (excellent).
  - 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.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 100/100
  - No destabilizing schema changes in the last 30 days.
- **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 6 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 7 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## 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.

### Claude

```bash
claude mcp add --transport http ai-discoveria-discoveria 'https://mcp.discoveria.ai/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "ai-discoveria-discoveria": {
      "url": "https://mcp.discoveria.ai/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "ai-discoveria-discoveria": {
      "type": "http",
      "url": "https://mcp.discoveria.ai/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.ai-discoveria-discoveria]
url = "https://mcp.discoveria.ai/mcp"
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add ai-discoveria-discoveria --url 'https://mcp.discoveria.ai/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  ai-discoveria-discoveria:
    url: "https://mcp.discoveria.ai/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "ai-discoveria-discoveria": {
      "Transport": "http",
      "Url": "https://mcp.discoveria.ai/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add ai-discoveria-discoveria -t streamable-http -u 'https://mcp.discoveria.ai/mcp'
```

### Other

```json
{
  "mcpServers": {
    "ai-discoveria-discoveria": {
      "type": "http",
      "url": "https://mcp.discoveria.ai/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] Stability: 0.97 → pass

### 2026-11-20 (score 80, +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.

### 2026-11-17 (score 79, +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.

### 2026-11-15 (score 78, +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.

### 2026-11-13 (score 77, +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.

### 2026-11-11 (score 76, +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.

### 2026-11-09 (score 75, +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.

### 2026-11-07 (score 74, +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.

## MCP tools (6)

### `search_announcements` (~422 tokens)

Search the DiscoverIA registry

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.

Input parameters:

- `announced_from` (string): 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_to` (string): YYYY, YYYY-MM or YYYY-MM-DD. Keeps entries whose announcement period starts on or before this date.
- `discipline` (string): Discipline slug, e.g. 'mathematiques', 'informatique-theorique', 'biologie-medecine', 'physique'.
- `include_archive` (boolean): Include the frozen archive of T. Tao's AI-Erdős wiki (about 520 entries). Default true.
- `lab` (string): 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…
- `lang` (string): Language of titles, labels and texts: 'fr' (French) or 'en' (English). Default 'en'. Use the user's language.
- `page` (integer): Page number, from 1.
- `page_size` (integer): Results per page, 1 to 50. Default 10.
- `query` (string): Free text matched against title, claimant, id, discipline and nature. All words must match; accents and case are ignored. Omit to list everything.
- `status` (string): Keep only entries with this status (see list_statuses).

### `get_announcement` (~138 tokens)

Get one registry entry

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.

Input parameters:

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

### `list_statuses` (~88 tokens)

List the statuses and their counts

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.

Input parameters:

- `lang` (string): Language of titles, labels and texts: 'fr' (French) or 'en' (English). Default 'en'. Use the user's language.

### `recent_changes` (~137 tokens)

Recent status changes and news feed

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).

Input parameters:

- `kind` (string): 'status' for status changes only, 'feed' for feed items only, 'all' for both. Default 'all'.
- `lang` (string): Language of titles, labels and texts: 'fr' (French) or 'en' (English). Default 'en'. Use the user's language.
- `limit` (integer): Maximum items per list, 1 to 50. Default 20.

### `get_frontier` (~134 tokens)

Get a frontier and its current record

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.

Input parameters:

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

### `get_citation` (~137 tokens)

Cite a registry entry

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.

Input parameters:

- `id` (string, required): Entry id (slug), e.g. 'gauss-sphere-packing-dim8', as returned by search_announcements.
- `lang` (string): Language of titles, labels and texts: 'fr' (French) or 'en' (English). Default 'en'. Use the user's language.
- `style` (string): 'apa', 'bibtex' or 'both'. Default 'both'.

## Diagnostics

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

## Score history

- 2026-11-21: 80
- 2026-11-20: 80
- 2026-11-19: 79
- 2026-11-18: 79
- 2026-11-17: 79
- 2026-11-16: 78
- 2026-11-15: 78
- 2026-11-14: 77
- 2026-11-13: 77
- 2026-11-12: 76
- 2026-11-11: 76
- 2026-11-10: 75
- 2026-11-09: 75
- 2026-11-08: 74
- 2026-11-07: 74
- 2026-11-06: 73
- 2026-11-05: 73
- 2026-11-04: 72
- 2026-11-03: 72
- 2026-11-02: 72
- 2026-11-01: 71
- 2026-10-31: 71
- 2026-10-30: 70
- 2026-10-29: 70
- 2026-10-28: 69
- 2026-10-27: 69
- 2026-10-26: 68
- 2026-10-25: 68
- 2026-10-24: 67
- 2026-10-23: 67

## 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.

## Links

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