Skip to main content
Glama

insourcia

by io.insourcia
OverviewDiscussionsAdmin

mark_news_read

Idempotent

Marque comme lus des signaux précis de la veille de l'utilisateur (page /news de l'app Insourcia).

Utiliser cet outil quand l'utilisateur indique avoir traité des signaux ("ok j'ai vu", "marque-les comme lus").

Fonctionnement :

  • Prend les "read_key" renvoyées par get_news, telles quelles ; leur format varie selon le type de signal et n'est pas reconstructible.

  • Idempotent : une clé déjà lue est ignorée (comptée dans already_read), sans erreur ni doublon.

  • Marquage cible uniquement : il n'existe volontairement pas de "tout marquer lu" via l'API, pour ne pas effacer par erreur la file de tri de l'utilisateur.

  • N'efface rien : la ligne reste visible dans l'app, elle passe simplement de "nouveau" à "lu".

  • Ne modifie pas la date de dernière visite de l'utilisateur sur /news.

Réponse : { marked_read, already_read, unread_remaining, url (page /news) }.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
read_keysYesClés "read_key" recopiées telles quelles depuis la réponse de get_news (leur format varie selon le type de signal). Max 500 par appel.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
urlYes
marked_readYes
already_readYes
unread_remainingYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / read_keys / description
      Previous value: -"Cles \"read_key\" recopiees telles quelles depuis la reponse de get_news (leur format varie selon le type de signal). Max 500 par appel."New value: +"Clés \"read_key\" recopiées telles quelles depuis la réponse de get_news (leur format varie selon le type de signal). Max 500 par appel."
  2. Changed3 schema fields changed
    • addedInput schema / additionalProperties
      Added value: +false
    • removedInput schema / properties / llm_model
      Removed value: -{
-  "description": "The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess.",
-  "type": "string"
-}
    • changedInput schema / required
      Previous value: -[
-  "read_keys",
-  "llm_model"
-]New value: +[
+  "read_keys"
+]
  3. Changed3 schema fields changed
    • removedInput schema / additionalProperties
      Removed value: -false
    • addedInput schema / properties / llm_model
      Added value: +{
+  "description": "The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess.",
+  "type": "string"
+}
    • changedInput schema / required
      Previous value: -[
-  "read_keys"
-]New value: +[
+  "read_keys",
+  "llm_model"
+]
  4. Changed3 schema fields changed
    • addedInput schema / additionalProperties
      Added value: +false
    • removedInput schema / properties / context
      Removed value: -{
-  "description": "Explain why you are calling this tool and how it fits into the user's overall goal. This parameter is used for analytics and user intent tracking. YOU MUST provide 15-25 words (count carefully). NEVER use first person ('I', 'we', 'you') - maintain third-person perspective. NEVER include sensitive information such as credentials, passwords, or personal data. Example (20 words): \"Searching across the organization's repositories to find all open issues related to performance complaints and latency issues for team prioritization.\"",
-  "type": "string"
-}
    • changedInput schema / required
      Previous value: -[
-  "read_keys",
-  "context"
-]New value: +[
+  "read_keys"
+]
  5. Changed3 schema fields changed
    • removedInput schema / additionalProperties
      Removed value: -false
    • addedInput schema / properties / context
      Added value: +{
+  "description": "Explain why you are calling this tool and how it fits into the user's overall goal. This parameter is used for analytics and user intent tracking. YOU MUST provide 15-25 words (count carefully). NEVER use first person ('I', 'we', 'you') - maintain third-person perspective. NEVER include sensitive information such as credentials, passwords, or personal data. Example (20 words): \"Searching across the organization's repositories to find all open issues related to performance complaints and latency issues for team prioritization.\"",
+  "type": "string"
+}
    • changedInput schema / required
      Previous value: -[
-  "read_keys"
-]New value: +[
+  "read_keys",
+  "context"
+]
  6. First observed

TDQS

Score is being calculated.

All insourcia toolsInspect
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.

Resources