accueil / serveurs / Recherche & Web / ai.edgechat/edgepedia
ai.edgechat/edgepedia
serveur MCP (Model Context Protocol) · edgepedia 1.2.0
Référencé dans l'annuaire. Seul le pentest comportemental fait foi, et il n'a pas encore été exécuté sur ce serveur.
Est-ce que ai.edgechat/edgepedia est sûr ?
Au dernier audit MCP Hub, le serveur MCP « ai.edgechat/edgepedia » est classé « Non encore testé ». Référencé dans l'annuaire. Seul le pentest comportemental fait foi, et il n'a pas encore été exécuté sur ce serveur. Le verdict est réévalué en continu ; consultez la fiche pour l'état à jour.
Méthode : MCP Hub analyse la description de chaque outil (couche 1) et, pour le verdict fort, exécute le serveur dans une micro-VM isolée avec leurres et réseau bloqué (couche 2). On publie des noms et des compteurs, jamais le contenu brut renvoyé par un outil.
Les 5 outils
- connect≈ 331 tokens
Find the shortest chain of in-text links from one Edgepedia article to another (at most 6 hops), with the sentence that makes each hop; pass two ids as `search` returns them.
Paramètres, retour & exemple (2)
Paramètresto· string · requis
The target article, named the same ways.from· string · requis
The starting article's id (such as "koala"), its ep… id, or its title.
Exemple d'appel{"name": "connect", "arguments": {"to": "texte", "from": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}], "structuredContent": {"to": "texte", "from": "texte", "hops": 1, "path": [], "text": "texte", "found": true, "steps": [], "reason": "texte"}} - fetch≈ 944 tokens
Read an encyclopedia article in full: one Edgepedia article as Markdown with its citations, by a `search` result's id. Returns id, title, text, url, and metadata (topic path, license, credit). A `topic:` id lists that topic's parent, narrower topics, and articles, 120 a page; `topic:root` is the top of the tree, `topic:geo` the geography tree. `citations: false` gives [n] markers instead of inline source links. Show the `credit` line with any text you quote.
Paramètres, retour & exemple (17)
Paramètresid· string · requis
The id of a search result (the last part of the article's address, such as "mount-fuji", or a topic's "topic:…" id).ids· array · optionnel
More ids to fetch with `id` in one call, up to 10 in all.cite· string · optionnel · csl | bibtex | ris | apa | mla | chicago | harvard
Add a reference in this format (csl, bibtex, ris, apa, mla, chicago, harvard).page· integer · optionnel
A topic only: which page of its articles, from 1.links· string · optionnel · in | out | both
Add the articles linking here (in), the links it makes (out), or both.query· string · optionnel
Only the 3 passages that best match these words, each with a `cite_url`.quote· string · optionnel
A sentence from the article, or a chunk id: adds a `cite_url` that opens the page at it.chunks· boolean · optionnel
true = the text as paragraphs with stable ids, in `chunks`.cursor· string · optionnel
Where to continue, from a cut text's `next_cursor`.format· string · optionnel · text | html | jsonld | turtle
The text as plain text, HTML, JSON-LD, or Turtle instead of Markdown.length· string · optionnel · snippet | lead | full
snippet or lead for a short text; full (default) for the whole article.tables· boolean · optionnel
true = add the article's tables as JSON and CSV.outline· boolean · optionnel
true = add the list of the article's headings.section· string · optionnel
Only this section, by its heading ("Etymology", "History").citations· boolean · optionnel
Default true. false = [n] markers instead of inline source links; the numbered reference list stays.links_page· integer · optionnel
With links "in" or "both": which 30 articles linking here, from 1.max_tokens· integer · optionnel
Cut the text at a section boundary to about this many tokens; pass `next_cursor` as `cursor` for the rest.
Exemple d'appel{"name": "fetch", "arguments": {"id": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}], "structuredContent": {"id": "texte", "url": "texte", "text": "texte", "title": "texte", "results": [], "metadata": {}, "moved_from": "texte", "canonical_id": "texte"}} - related≈ 334 tokens
Find encyclopedia articles related to an Edgepedia article: its topic-mates, a few from each neighboring topic, and its geography neighbors. Pass its id, as for `fetch`. Returns groups of results; `fetch` a group's `topic` id for more.
Paramètres, retour & exemple (2)
Paramètresby· string · optionnel · links
"links" = articles cited together with it, and articles linking to what it links to.id· string · requis
An article's id, as `search` returns it (such as "mount-fuji").
Exemple d'appel{"name": "related", "arguments": {"id": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}], "structuredContent": {"by": "links", "id": "texte", "geo": [], "url": "texte", "title": "texte", "cocited": [], "coupled": [], "cousins": [], "siblings": {}}} - resolve≈ 542 tokens
Find which encyclopedia article a name means: Edgepedia's best match for a person, place, thing, or concept named in a text, with a confidence, whether the name is ambiguous, and the alternatives. Pass the name ("Mercury"), and optionally words from the text around it (`context`: "planet orbit") or a topic id the article must sit under (`type`). Returns `result` (id, title, url) and `alternatives`; pass an id to `fetch`.
Paramètres, retour & exemple (4)
Paramètresname· string · requis
The name as the text gives it.type· string · optionnel
Only articles under this topic id (as `fetch` topic:… names it, without "topic:").limit· integer · optionnel
Candidates to return, 1 to 10 (default 5).context· string · optionnel
Words from the text around the name, which favor the article they fit.
Exemple d'appel{"name": "resolve", "arguments": {"name": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}], "structuredContent": {"match": "exact", "query": "texte", "result": "texte", "ambiguous": true, "confidence": 1, "alternatives": []}} - search≈ 570 tokens
Search an encyclopedia for facts about a person, place, thing, event, or concept: Edgepedia, more than 400,000 articles with citations. Pass the subject's name ("Mount Fuji", "photosynthesis"), not a question; other names and misspellings match, and when no title matches, articles whose text does follow, marked `match: fulltext`. Returns results with id, title, url, and preview text, plus a `topic:` result when the query names a topic ("painters"); pass an id to `fetch`. `limit` and `page` reach further results.
Paramètres, retour & exemple (6)
Paramètrespage· integer · optionnel
Which page of results, from 1.sort· string · optionnel · relevance | central
central = the most-linked subjects first.first· boolean · optionnel
true = only the best match.limit· integer · optionnel
Results a page, 1 to 30 (default 10).query· string · requis
The name of a subject, or words from an article title.topic· string · optionnel
Only articles under this topic id (as `fetch` topic:… names it, without "topic:").
Exemple d'appel{"name": "search", "arguments": {"query": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}], "structuredContent": {"page": 1, "pages": 1, "results": [], "did_you_mean": "texte"}}
C'est votre serveur ?
Revendiquez-le sur l'espace créateur (preuve GitHub, domaine ou npm) pour afficher le badge « propriétaire vérifié » et lancer un pentest comportemental à la demande afin d'obtenir le badge « Vérifié ».