A
licenseA
qualityB
maintenanceEnables researching, verifying, comparing, and composing open-source AI projects with transparent evidence and uncertainty boundaries through read-only tools.
9
3
Apache 2.0
DiscoverIA
Server Details
Read-only registry of AI-assisted scientific claims and where their evaluation stands (fr/en)
If you are the author of this connector, you can claim ownership by verifying the domain or GitHub account it belongs to. Claimed connector authors can inspect health checks, view analytics, and manage their listing.
- Status
- Healthy
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
TDQS
Score is being calculated.
Available Tools
6 toolsget_announcementGet one registry entryRead-onlyIdempotentInspect
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.
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | Entry id (slug), e.g. 'gauss-sphere-packing-dim8', as returned by search_announcements. | |
| lang | No | Language of titles, labels and texts: 'fr' (French) or 'en' (English). Default 'en'. Use the user's language. | en |
get_citationCite a registry entryRead-onlyIdempotentInspect
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.
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | Entry id (slug), e.g. 'gauss-sphere-packing-dim8', as returned by search_announcements. | |
| lang | No | Language of titles, labels and texts: 'fr' (French) or 'en' (English). Default 'en'. Use the user's language. | en |
| style | No | 'apa', 'bibtex' or 'both'. Default 'both'. | both |
get_frontierGet a frontier and its current recordRead-onlyIdempotentInspect
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.
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| id | No | Frontier id, e.g. 'kissing-d11'. Omit to list all frontiers. | |
| lang | No | Language of titles, labels and texts: 'fr' (French) or 'en' (English). Default 'en'. Use the user's language. | en |
list_statusesList the statuses and their countsRead-onlyIdempotentInspect
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.
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| lang | No | Language of titles, labels and texts: 'fr' (French) or 'en' (English). Default 'en'. Use the user's language. | en |
recent_changesRecent status changes and news feedRead-onlyIdempotentInspect
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).
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| kind | No | 'status' for status changes only, 'feed' for feed items only, 'all' for both. Default 'all'. | all |
| lang | No | Language of titles, labels and texts: 'fr' (French) or 'en' (English). Default 'en'. Use the user's language. | en |
| limit | No | Maximum items per list, 1 to 50. Default 20. |
search_announcementsSearch the DiscoverIA registryRead-onlyIdempotentInspect
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.
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| lab | No | 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 Erdős-wiki archive is not attributed to labs. | |
| lang | No | Language of titles, labels and texts: 'fr' (French) or 'en' (English). Default 'en'. Use the user's language. | en |
| page | No | Page number, from 1. | |
| query | No | Free text matched against title, claimant, id, discipline and nature. All words must match; accents and case are ignored. Omit to list everything. | |
| status | No | Keep only entries with this status (see list_statuses). | |
| page_size | No | Results per page, 1 to 50. Default 10. | |
| discipline | No | Discipline slug, e.g. 'mathematiques', 'informatique-theorique', 'biologie-medecine', 'physique'. | |
| announced_to | No | YYYY, YYYY-MM or YYYY-MM-DD. Keeps entries whose announcement period starts on or before this date. | |
| announced_from | No | 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'). | |
| include_archive | No | Include the frozen archive of T. Tao's AI-Erdős wiki (about 520 entries). Default true. |
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
6 tool updates
- First observed
get_announcement - First observed
get_citation - First observed
get_frontier - First observed
list_statuses - First observed
recent_changes - First observed
search_announcements
Related MCP Connectors
Cite the claim, not the paper: 5,033 assertions, each hash-verifiable against its source PDF
Sourced register of open-weight AI model releases and AI news. Every field cites its source.
Signed, independent scores and claim checks for decentralised AI projects. Read-only, no auth.
Traceable scientific novelty and evidence assessment with source-linked results and a human gate.
Related MCP Servers
- FlicenseNot gradedqualityBmaintenanceAuditable AGI-2027 evidence: eight graded Situational Awareness predictions with pre-registered flip conditions, a 0-100 Thesis Tracker with full score history, and a public market-call ledger where misses stay published. Free, no auth, CC BY 4.0.-
- AlicenseNot gradedqualityAmaintenanceEnables an AI coding agent to take a research paper from arXiv, record its claims, build and run an implementation, measure the results, and receive a verdict for each claim. Every action is kept in a hash-chained evidence log, so the generated code folder and reproduction report can be checked without trusting the agent.MIT
- AlicenseAqualityBmaintenanceEnables scientific due diligence by grading claims against public literature, clinical trials, and filings, with explicit citations and optional attestation.4MIT
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd
Glama MCP Gateway
Add one secure layer between your agents and this server.