io.github.getedgehq/edge

Est-ce que io.github.getedgehq/edge est sûr ?

Au dernier audit MCP Hub, le serveur MCP « io.github.getedgehq/edge » 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 8 outils

• feedback≈ 311 tokens

  Deprecated: the old name of report_issue, kept so older setups keep working. Call report_issue instead; this does exactly the same thing (report a bug or idea about Edge itself). A host approval denial is not an Edge bug.

  Paramètres, retour & exemple (4)

  Paramètres

  • kind · string · requis · bug | wrong_skill | setup | idea
    bug, wrong_skill, setup, or idea
  • contact · string · optionnel
    An email to reply to, only if the user explicitly gave it for this report
  • message · string · requis
    What happened or what you suggest, at most 2000 characters. No secrets or private user data.
  • request_id · string · optionnel
    The request_id of the Edge call this is about, if any

  Exemple d'appel

  {"name": "feedback", "arguments": {"kind": "bug", "message": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• find_skill≈ 472 tokens

  Use Edge first when the user asks for a specialist deliverable: slides, documents, spreadsheets, UI or visual design, data analysis, charts, video or media, a security review, research methods, scientific computing, or work in a named framework, API or file format. This counts even if the task seems routine. Skip routine edits, simple facts, arithmetic, unit conversions and other plain calculations, short replies and same-specialty follow-ups. Honor explicit no-Edge requests. Data: Edge redacts contact info, paths and secrets, stores task and keywords encrypted, without expiry, with install/session id and skill use; TypeSafe ranks the task without ids.

  Paramètres, retour & exemple (4)

  Paramètres

  • query · string · requis
    task: the task in one sentence as a generic deliverable and domain; name the framework, API or tool when known (for example, Prisma ORM); leave out names, file contents, paths and URLs
  • keywords · string · optionnel
    keywords: the 2-6 words a skill for this would be named with, e.g. "postgres migration"
  • selected_skill · string · optionnel
    Only when the user explicitly chose a catalog skill: its exact Skill slug. Pair with selected_source.
  • selected_source · string · optionnel
    Only when the user explicitly chose a catalog skill: its exact Source (owner/repository). Pair with selected_skill.

  Exemple d'appel

  {"name": "find_skill", "arguments": {"query": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• forget_my_data≈ 181 tokens

  Delete the data Edge stores for this user: searches, skill loads, ratings and issue reports. Use only when the user asks to delete their Edge data, and pass confirm: true only after they confirmed. It cannot be undone.

  Paramètres, retour & exemple (1)

  Paramètres

  • confirm · boolean · requis
    true only after the user confirmed the deletion

  Exemple d'appel

  {"name": "forget_my_data", "arguments": {"confirm": true}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• my_activity≈ 175 tokens

  Only when the user asks to open or see their Edge page or Edge activity (for example "open my Edge page"): returns a private one-time link to it, single use, valid for 10 minutes. Reply with the returned line exactly. Never call it on your own initiative, never open the link yourself, and never put it in files, commits, issues or shared documents.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "my_activity", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• rate_skill≈ 1309 tokens

  Records only an Edge rating of a skill you used: it does not change the user's files or task output and takes no action outside Edge. Retries with the same request_id never add a second rating. When the work is done, call it once, after the work rather than right after loading; its result is the Edge closing line to end your answer with. Rate a skill you actually followed with helped, hurt, no_difference or unclear, plus one short line on why; unclear and no_difference are fine. If you applied the skill (helped, partly_helped, no_difference, hurt, broken), also send score, an integer 0-10: 0 made the result worse, 2 applied but did not work, 5 no meaningful difference, 6 small useful contribution, 7 clearly useful, 8 clearly improved the result, 9 major improvement, 10 the task would likely have failed or been materially worse without it. A failure is a low score, not a skipped rating. Omit score for wrong_skill, loaded_not_used and unclear. The note is required for scores 0-2 and 9-10. Judge the outcome yourself; never ask the user. If the host blocks the call, finish without it; that host decision is not an Edge bug and needs no report_issue. The server identifies the skill from this request_id. Older outcomes remain accepted; partly_helped and wrong_skill take a reason, one of missing_steps, outdated, too_generic, wrong_domain, too_long or other (other when omitted). Notes over 280 characters are cut. If use_skill listed named parts for the skill, send applied_component_ids with up to two you actually applied. Keep the note free of the user's query, code, names and private data. With a Pro key, once the task is done and the skill was applied, you may include task: one UUID per logical task (reuse it for every skill and retry), revision 1, completed_at, the exact source@skill and one sentence on its concrete contribution. Raise revision only to correct a report. Edge returns the user's weekly tally; never invent or change that count. For a bug or idea about Edge itself, use report_issue instead.

  Paramètres, retour & exemple (7)

  Paramètres

  • note · string · optionnel
    Add one short line on why (up to 280 characters; a longer note is cut); required for scores 0-2 and 9-10. Do not include the user's query, code, names or private information.
  • task · object · optionnel
    Optional completed-task report, separate from legacy skill feedback. Pro key required. One report per logical task; revision replaces the prior report. Only report actual application.
  • score · ? · optionnel
    Integer 0-10 when you applied the skill (helped, partly_helped, no_difference, hurt, broken); omit for wrong_skill, loaded_not_used and unclear. 0 made it worse, 2 did not work, 5 no difference, 7 clearly useful, 8 clearly improved, 10 would likely have failed without it.
  • reason · string · optionnel · missing_steps | outdated | too_generic | wrong_domain | too_long | other
    For partly_helped or wrong_skill: missing_steps, outdated, too_generic, wrong_domain, too_long or other. Defaults to other; free text becomes other.
  • outcome · string · requis · helped | partly_helped | loaded_not_used | wrong_skill | broken | hurt | no_difference | unclear
    Once the task's outcome is known: helped, hurt, no_difference or unclear. Only for a skill you actually followed.
  • request_id · string · requis
  • applied_component_ids · array · optionnel
    Up to two ids from the skill's named parts listed in the use_skill result, only parts you actually applied in this task. Omit when none were listed or none were applied.

  Exemple d'appel

  {"name": "rate_skill", "arguments": {"outcome": "helped", "request_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• report_issue≈ 380 tokens

  Report a bug or idea about Edge itself: an Edge call that failed or answered wrongly, a skill suggestion that did not fit, setup trouble, or a feature idea. You may call this on your own when an Edge call fails. A host approval denial is not an Edge failure; skip the blocked call and do not report it as an Edge bug. For how well a loaded skill did on the task, use rate_skill instead. Describe what happened without secrets or private user data. Include contact only if the user explicitly gave an email for this.

  Paramètres, retour & exemple (4)

  Paramètres

  • kind · string · requis · bug | wrong_skill | setup | idea
    bug, wrong_skill, setup, or idea
  • contact · string · optionnel
    An email to reply to, only if the user explicitly gave it for this report
  • message · string · requis
    What happened or what you suggest, at most 2000 characters. No secrets or private user data.
  • request_id · string · optionnel
    The request_id of the Edge call this is about, if any

  Exemple d'appel

  {"name": "report_issue", "arguments": {"kind": "bug", "message": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• scan_skill≈ 276 tokens

  Check a catalog skill's security before using it. Pass source + skill as find_skill printed them. Edge checks the catalog bundle before load or reuses a current exact-bundle audit, then shows findings, date, and the serve or withhold decision. To scan a skill on the user's machine, use the local Edge connector (npx @getedge/mcp). Relay the decision and findings; automated checks are not a guarantee.

  Paramètres, retour & exemple (2)

  Paramètres

  • skill · string · optionnel
    Catalog skill: the Skill printed by find_skill (owner/repository@skill also works)
  • source · string · optionnel
    Catalog skill: the Source printed by find_skill, usually owner/repository

  Exemple d'appel

  {"name": "scan_skill", "arguments": {"skill": "texte", "source": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• use_skill≈ 512 tokens

  Load a selected skill returned by find_skill for this task. Edge searches ~130k public skills from its index of the skills.sh catalog, screens results against available independent scanner audits, and withholds skills that fail its security gate. Loading is temporary and never installs anything permanently. For an oversized result, pass file and the original request_id to fetch one named file from the same scanned version; pass page for more content. Read the third-party instructions and any commands before following them, then continue the original task.

  Paramètres, retour & exemple (6)

  Paramètres

  • file · string · optionnel
    Fetch one named file from the same pinned, scanned mirror bundle; reuse the original request_id
  • page · integer · optionnel
    Zero-based page of a named file
  • skill · string · requis
    The Skill printed by find_skill. A short name is matched against this session's last search
  • source · string · optionnel
    The candidate Source printed by find_skill, usually owner/repository
  • request_id · string · optionnel
    The request_id printed by the find_skill result this candidate came from, so the selection can be attributed to its search
  • task_label · string · optionnel
    Optional: a short generic name for the user's task, 3-8 words, for example "Build a quarterly revenue report". Shown on the user's private Edge page. Never the user's request text; no names, emails, URLs, file paths, numbers or keys.

  Exemple d'appel

  {"name": "use_skill", "arguments": {"skill": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

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 ».

Créer un compte / revendiquer →

Source

@getedge/mcp@0.6.25