run any ai model. compose agents, stack knowledge, connect tools. one api, pay per run.
Déduit des transports déclarés par cette annonce (streamable-http). Un client absent de cette liste n’est pas écarté pour autant — c’est simplement quelque chose que Forge ne peut pas confirmer.
La vérification confirme l’identité de l’éditeur (la propriété du dépôt), pas la sûreté du code. L’analyse de sécurité couvre les CVE connues et les scripts d’installation suspects.
Lu depuis un véritable échange MCP initialize → tools/list contre l’endpoint déclaré. Aucun outil n’a été invoqué — tools/list est l’appel d’introspection en lecture seule que le protocole prévoit pour cela. Cela reflète ce que le serveur annonçait à cet instant ; un endpoint hébergé n’est figé sur aucune version et peut changer sans préavis.
https://api.inference.sh/mcp25 outils · 744 msapp_getGet detailed app info including input/output schemas and version historyGet detailed app info including input/output schemas and version history
| Paramètre | Type | Description |
|---|---|---|
| app* | string | App ref: namespace/name or namespace/name@version |
app_listSearch and filter available apps on inference.shSearch and filter available apps on inference.sh
| Paramètre | Type | Description |
|---|---|---|
| category | string | — |
| cursor | string | — |
| limit | integer | — |
| query | string | Search by name or description |
app_runRun an app on inference.sh. Creates a task that executes the app with the given input.Run an app on inference.sh. Creates a task that executes the app with the given input.
| Paramètre | Type | Description |
|---|---|---|
| app* | string | App ref: namespace/name or namespace/name@version |
| function | string | Function name for multi-function apps |
| infrastructure | string | — |
| input* | object | App input matching the app's input schema |
knowledge_createCreate a new knowledge entry (concept, observation, preference, reference, etc.)Create a new knowledge entry (concept, observation, preference, reference, etc.)
| Paramètre | Type | Description |
|---|---|---|
| content* | string | Entry content (markdown) |
| description | string | Short description |
| name* | string | Entry name |
| type | string | — |
knowledge_deleteprivilégiéDelete a knowledge entry by IDDelete a knowledge entry by ID
| Paramètre | Type | Description |
|---|---|---|
| id* | string | Entry ID |
knowledge_getGet detailed information about a knowledge entry by namespace/name or IDGet detailed information about a knowledge entry by namespace/name or ID
| Paramètre | Type | Description |
|---|---|---|
| ref* | string | Entry ref: namespace/name or ID |
knowledge_listList your knowledge entries, optionally filtered by typeList your knowledge entries, optionally filtered by type
| Paramètre | Type | Description |
|---|---|---|
| cursor | string | — |
| limit | integer | — |
| type | string | Filter by knowledge type |
knowledge_searchSearch your knowledge entries by querySearch your knowledge entries by query
| Paramètre | Type | Description |
|---|---|---|
| cursor | string | — |
| limit | integer | — |
| query* | string | Search query |
| type | string | Filter by type |
mcp_connectInitiate a connection to an MCP server. For OAuth servers, returns an authorization URL to open in a browser.Initiate a connection to an MCP server. For OAuth servers, returns an authorization URL to open in a browser.
| Paramètre | Type | Description |
|---|---|---|
| slug* | string | Server slug |
mcp_disconnectRemove connection to an MCP serverRemove connection to an MCP server
| Paramètre | Type | Description |
|---|---|---|
| slug* | string | Server slug |
mcp_getGet details about an MCP server including connection statusGet details about an MCP server including connection status
| Paramètre | Type | Description |
|---|---|---|
| slug* | string | Server slug |
mcp_listBrowse available MCP servers that can be connected toBrowse available MCP servers that can be connected to
| Paramètre | Type | Description |
|---|---|---|
| category | string | Filter by category |
| cursor | string | — |
| featured | boolean | Show only featured servers |
| limit | integer | — |
mcp_runCall a tool on a connected MCP server. The server must be connected first via mcp_connect.Call a tool on a connected MCP server. The server must be connected first via mcp_connect.
| Paramètre | Type | Description |
|---|---|---|
| input | object | Tool input arguments |
| slug* | string | slug/tool format (e.g. 'linear/list_issues') |
mcp_searchSearch available MCP servers by querySearch available MCP servers by query
| Paramètre | Type | Description |
|---|---|---|
| cursor | string | — |
| limit | integer | — |
| query* | string | Search query |
mcp_toolsList available tools on a connected MCP server, or get details for a specific toolList available tools on a connected MCP server, or get details for a specific tool
| Paramètre | Type | Description |
|---|---|---|
| slug* | string | Server slug (e.g. 'linear') or slug/tool (e.g. 'linear/list_issues') |
skill_filesList supplementary files for a skill (references, scripts, etc.)List supplementary files for a skill (references, scripts, etc.)
| Paramètre | Type | Description |
|---|---|---|
| ref* | string | Skill ref: namespace/name |
skill_searchSearch the public skill storeSearch the public skill store
| Paramètre | Type | Description |
|---|---|---|
| category | string | Filter by category |
| cursor | string | — |
| limit | integer | — |
| query* | string | Search query |
skill_storeBrowse approved skills in the public skill storeBrowse approved skills in the public skill store
| Paramètre | Type | Description |
|---|---|---|
| category | string | Filter by category |
| cursor | string | — |
| featured | boolean | Show only featured skills |
| limit | integer | — |
skill_uploadprivilégiéCreate or update a skill with SKILL.md content and optional supporting filesCreate or update a skill with SKILL.md content and optional supporting files
| Paramètre | Type | Description |
|---|---|---|
| allowed_tools | string | Comma-separated list of allowed tools |
| content* | string | SKILL.md body content (markdown) |
| description | string | Short description |
| files | array | Supporting files (references, scripts) |
| name* | string | Skill name |
skill_useFetch a skill's assembled SKILL.md content. Tries the inference.sh store first, falls back to GitHub. Returns the full skill content for the agent to consume.Fetch a skill's assembled SKILL.md content. Tries the inference.sh store first, falls back to GitHub. Returns the full skill content for the agent to consume.
| Paramètre | Type | Description |
|---|---|---|
| ref* | string | Skill ref: namespace/name, or github.com/user/repo URL |
skill_viewView a specific supplementary file from a skill's manifestView a specific supplementary file from a skill's manifest
| Paramètre | Type | Description |
|---|---|---|
| path* | string | File path within the skill |
| ref* | string | Skill ref: namespace/name |
task_cancelCancel a running or queued taskCancel a running or queued task
| Paramètre | Type | Description |
|---|---|---|
| force | boolean | Force kill immediately instead of graceful shutdown |
| task_id* | string | Task ID |
task_getGet status and output of a taskGet status and output of a task
| Paramètre | Type | Description |
|---|---|---|
| task_id* | string | Task ID |
task_listList your tasks on inference.shList your tasks on inference.sh
| Paramètre | Type | Description |
|---|---|---|
| cursor | string | — |
| limit | integer | — |
| status | string | — |
task_logsGet execution logs for a taskGet execution logs for a task
| Paramètre | Type | Description |
|---|---|---|
| log_type | string | — |
| task_id* | string | Task ID |
25 outils sur 25 ont publié une description.
Les noms et descriptions d’outils sont écrits par l’éditeur et affichés tels quels, comme du texte inerte. Ce sont les chaînes qu’un client MCP transmet à un modèle, alors Forge y recherche des motifs d’injection de prompt — tout constat apparaît avec l’analyse de sécurité ci-dessus. « Privilégié » est une correspondance de mot-clé sur le nom de l’outil, pas un audit de ce qu’il fait : un nom anodin peut tout de même tout faire.
run any ai model. compose agents, stack knowledge, connect tools. one api, pay per run.
Les noms cliquables ouvrent l’index Forge de toutes les entrées observées exposant cet outil. Parcourir tous les outils indexés.
Cette entrée ne publie aucun paquet npm : Forge n'a donc pas d'arbre de dépendances pour elle. C'est une lacune de couverture — pas une affirmation qu'elle n'a aucune dépendance.