inference.sh MCP · inference.sh

Auth required

Unclaimed — claim this pageinfrastructure Streamable HTTP2025-06-18 Auth expectations unknown

https://api.inference.sh/mcp

Badge

Authentication requiredReachable; initialization requires authentication.

Since Sep 9, 2026 — 9:36 AM (54 d ago)

An authentication challenge is availability, not an outage — the endpoint is reachable and answering. Passive observation records the challenge and any OAuth discovery metadata without ever authenticating. OAuth-authenticated contract monitoring is planned.

Recorded auth metadata

authMeta — as observed

{
  "httpStatus": 401,
  "wwwAuthenticate": "Bearer resource_metadata=\"https://api.inference.sh/.well-known/oauth-protected-resource\", scope=\"agents:read apps:read conversations:read files:read flows:read datastores:read projects:read teams:read secrets:read credentials:read knowledge:read artifacts:read remotes:read sandboxes:read settings:read bounties:read agents:execute apps:execute flows:execute forms:execute agents:write apps:write conversations:write files:write flows:write datastores:write projects:write secrets:write credentials:write knowledge:write artifacts:write remotes:write sandboxes:write settings:write forms:write billing:read\"",
  "discovery": {
    "resource": "https://api.inference.sh",
    "authorization_servers": [
      "https://api.inference.sh"
    ],
    "scopes_supported": [
      "agents:read",
      "apps:read",
      "conversations:read",
      "files:read",
      "flows:read",
      "datastores:read",
      "projects:read",
      "teams:read",
      "secrets:read",
      "credentials:read",
      "knowledge:read",
      "artifacts:read",
      "remotes:read",
      "sandboxes:read",
      "settings:read",
      "bounties:read",
      "agents:execute",
      "apps:execute",
      "flows:execute",
      "forms:execute",
      "agents:write",
      "apps:write",
      "conversations:write",
      "files:write",
      "flows:write",
      "datastores:write",
      "projects:write",
      "secrets:write",
      "credentials:write",
      "knowledge:write",
      "artifacts:write",
      "remotes:write",
      "sandboxes:write",
      "settings:write",
      "forms:write",
      "billing:read"
    ]
  }
}

100%

Availability · 30 days · 350 checks

606 ms

Latency (last observation)

rev 1

Contract

87days

Schema stable

Incidents · 30 days

Aug 6, 2026

Observed since

Availability — last 30 days

No failures Some failures Mostly failing Auth required No observations

Last observed 40 min ago by MCP Tools Edge Scanner · scheduled every 120 min

Authentication is now required Breaking Sep 9, 2026 — 9:36 AM

The endpoint stopped accepting unauthenticated initialization.

Verifiedinitialize returned HTTP 401.

InterpretationUnauthenticated clients can no longer connect and may require credentials or an OAuth flow.

Raw event details

{
  "httpStatus": 401,
  "wwwAuthenticate": "Bearer resource_metadata=\"https://api.inference.sh/.well-known/oauth-protected-resource\"",
  "discovery": {
    "resource": "https://api.inference.sh",
    "authorization_servers": [
      "https://api.inference.sh"
    ],
    "scopes_supported": [
      "apps:read",
      "apps:execute"
    ]
  }
}

Observed by MCP Tools Edge Scanner

Latency recovered below 1,000 ms Informational Aug 6, 2026 — 10:20 PM

Latest observation: 221 ms.

VerifiedObserved initialization latency: 221 ms.

Observed by MCP Tools Edge Scanner

Latency crossed above 1,000 ms Informational Aug 6, 2026 — 8:20 PM

Three consecutive observations exceeded 1,000 ms (latest: 1126 ms).

VerifiedObserved initialization latency: 1126 ms.

InterpretationClients may experience slow tool discovery and responses.

Observed by MCP Tools Edge Scanner

Baseline captured Aug 6, 2026 — 5:20 AM

25 tools, 0 resources, 0 prompts observed. Future observations will identify outages, recoveries, protocol changes, and contract drift from this state.

VerifiedCanonical contract hash sha256:0fe4606b21a0a98c… computed from the normalized capability inventory.

Raw event details

{
  "contractHash": "sha256:0fe4606b21a0a98c29b4711a61b44575fcb0101d98fc49f29d04d73a5977a54d"
}

Observed by MCP Tools Edge Scanner

Advertised capabilities

Tools · 25 Resources Prompts Logging Completions Experimental

Tools 25

app_get 1 param · 1 required Get detailed app info including input/output schemas and version history

Get detailed app info including input/output schemas and version history

Input schema

Parameter	Type	Description & constraints
app*	string	App ref: namespace/name or namespace/name@version

Raw schema JSON

app_get — raw

{
  "name": "app_get",
  "description": "Get detailed app info including input/output schemas and version history",
  "inputSchema": {
    "properties": {
      "app": {
        "description": "App ref: namespace/name or namespace/name@version",
        "type": "string"
      }
    },
    "required": [
      "app"
    ],
    "type": "object"
  }
}

app_list 4 params Search and filter available apps on inference.sh

Search and filter available apps on inference.sh

Input schema

Parameter	Type	Description & constraints
category	enum(7)	— one of: "image", "video", "audio", "text", "chat", "3d", "other"
cursor	string	—
limit	integer	— max: 100 · default: 20
query	string	Search by name or description

Raw schema JSON

app_list — raw

{
  "name": "app_list",
  "description": "Search and filter available apps on inference.sh",
  "inputSchema": {
    "properties": {
      "category": {
        "enum": [
          "image",
          "video",
          "audio",
          "text",
          "chat",
          "3d",
          "other"
        ],
        "type": "string"
      },
      "cursor": {
        "type": "string"
      },
      "limit": {
        "default": 20,
        "maximum": 100,
        "type": "integer"
      },
      "query": {
        "description": "Search by name or description",
        "type": "string"
      }
    },
    "type": "object"
  }
}

app_run 4 params · 2 required Run 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.

Input schema

Parameter	Type	Description & constraints
app*	string	App ref: namespace/name or namespace/name@version
function	string	Function name for multi-function apps
infrastructure	enum(3)	— one of: "cloud", "private", "private_first" · default: "cloud"
input*	object	App input matching the app's input schema

Raw schema JSON

app_run — raw

{
  "name": "app_run",
  "description": "Run an app on inference.sh. Creates a task that executes the app with the given input.",
  "inputSchema": {
    "properties": {
      "app": {
        "description": "App ref: namespace/name or namespace/name@version",
        "type": "string"
      },
      "function": {
        "description": "Function name for multi-function apps",
        "type": "string"
      },
      "infrastructure": {
        "default": "cloud",
        "enum": [
          "cloud",
          "private",
          "private_first"
        ],
        "type": "string"
      },
      "input": {
        "description": "App input matching the app&#39;s input schema",
        "type": "object"
      }
    },
    "required": [
      "app",
      "input"
    ],
    "type": "object"
  }
}

knowledge_create 4 params · 2 required Create a new knowledge entry (concept, observation, preference, reference, etc.)

Create a new knowledge entry (concept, observation, preference, reference, etc.)

Input schema

Parameter	Type	Description & constraints
content*	string	Entry content (markdown)
description	string	Short description
name*	string	Entry name
type	enum(6)	— one of: "concept", "observation", "preference", "reference", "person", "project" · default: "observation"

Raw schema JSON

knowledge_create — raw

{
  "name": "knowledge_create",
  "description": "Create a new knowledge entry (concept, observation, preference, reference, etc.)",
  "inputSchema": {
    "properties": {
      "content": {
        "description": "Entry content (markdown)",
        "type": "string"
      },
      "description": {
        "description": "Short description",
        "type": "string"
      },
      "name": {
        "description": "Entry name",
        "type": "string"
      },
      "type": {
        "default": "observation",
        "enum": [
          "concept",
          "observation",
          "preference",
          "reference",
          "person",
          "project"
        ],
        "type": "string"
      }
    },
    "required": [
      "name",
      "content"
    ],
    "type": "object"
  }
}

knowledge_delete 1 param · 1 required Delete a knowledge entry by ID

Delete a knowledge entry by ID

Input schema

Parameter	Type	Description & constraints
id*	string	Entry ID

Raw schema JSON

knowledge_delete — raw

{
  "name": "knowledge_delete",
  "description": "Delete a knowledge entry by ID",
  "inputSchema": {
    "properties": {
      "id": {
        "description": "Entry ID",
        "type": "string"
      }
    },
    "required": [
      "id"
    ],
    "type": "object"
  }
}

knowledge_get 1 param · 1 required Get detailed information about a knowledge entry by namespace/name or ID

Get detailed information about a knowledge entry by namespace/name or ID

Input schema

Parameter	Type	Description & constraints
ref*	string	Entry ref: namespace/name or ID

Raw schema JSON

knowledge_get — raw

{
  "name": "knowledge_get",
  "description": "Get detailed information about a knowledge entry by namespace/name or ID",
  "inputSchema": {
    "properties": {
      "ref": {
        "description": "Entry ref: namespace/name or ID",
        "type": "string"
      }
    },
    "required": [
      "ref"
    ],
    "type": "object"
  }
}

knowledge_list 3 params List your knowledge entries, optionally filtered by type

List your knowledge entries, optionally filtered by type

Input schema

Parameter	Type	Description & constraints
cursor	string	—
limit	integer	— max: 100 · default: 20
type	enum(7)	Filter by knowledge type one of: "skill", "concept", "observation", "preference", "reference", "person", "project"

Raw schema JSON

knowledge_list — raw

{
  "name": "knowledge_list",
  "description": "List your knowledge entries, optionally filtered by type",
  "inputSchema": {
    "properties": {
      "cursor": {
        "type": "string"
      },
      "limit": {
        "default": 20,
        "maximum": 100,
        "type": "integer"
      },
      "type": {
        "description": "Filter by knowledge type",
        "enum": [
          "skill",
          "concept",
          "observation",
          "preference",
          "reference",
          "person",
          "project"
        ],
        "type": "string"
      }
    },
    "type": "object"
  }
}

knowledge_search 4 params · 1 required Search your knowledge entries by query

Search your knowledge entries by query

Input schema

Parameter	Type	Description & constraints
cursor	string	—
limit	integer	— max: 100 · default: 20
query*	string	Search query
type	enum(7)	Filter by type one of: "skill", "concept", "observation", "preference", "reference", "person", "project"

Raw schema JSON

knowledge_search — raw

{
  "name": "knowledge_search",
  "description": "Search your knowledge entries by query",
  "inputSchema": {
    "properties": {
      "cursor": {
        "type": "string"
      },
      "limit": {
        "default": 20,
        "maximum": 100,
        "type": "integer"
      },
      "query": {
        "description": "Search query",
        "type": "string"
      },
      "type": {
        "description": "Filter by type",
        "enum": [
          "skill",
          "concept",
          "observation",
          "preference",
          "reference",
          "person",
          "project"
        ],
        "type": "string"
      }
    },
    "required": [
      "query"
    ],
    "type": "object"
  }
}

mcp_connect 1 param · 1 required Initiate 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.

Input schema

Parameter	Type	Description & constraints
slug*	string	Server slug

Raw schema JSON

mcp_connect — raw

{
  "name": "mcp_connect",
  "description": "Initiate a connection to an MCP server. For OAuth servers, returns an authorization URL to open in a browser.",
  "inputSchema": {
    "properties": {
      "slug": {
        "description": "Server slug",
        "type": "string"
      }
    },
    "required": [
      "slug"
    ],
    "type": "object"
  }
}

mcp_disconnect 1 param · 1 required Remove connection to an MCP server

Remove connection to an MCP server

Input schema

Parameter	Type	Description & constraints
slug*	string	Server slug

Raw schema JSON

mcp_disconnect — raw

{
  "name": "mcp_disconnect",
  "description": "Remove connection to an MCP server",
  "inputSchema": {
    "properties": {
      "slug": {
        "description": "Server slug",
        "type": "string"
      }
    },
    "required": [
      "slug"
    ],
    "type": "object"
  }
}

mcp_get 1 param · 1 required Get details about an MCP server including connection status

Get details about an MCP server including connection status

Input schema

Parameter	Type	Description & constraints
slug*	string	Server slug

Raw schema JSON

mcp_get — raw

{
  "name": "mcp_get",
  "description": "Get details about an MCP server including connection status",
  "inputSchema": {
    "properties": {
      "slug": {
        "description": "Server slug",
        "type": "string"
      }
    },
    "required": [
      "slug"
    ],
    "type": "object"
  }
}

mcp_list 4 params Browse available MCP servers that can be connected to

Browse available MCP servers that can be connected to

Input schema

Parameter	Type	Description & constraints
category	enum(5)	Filter by category one of: "developer", "productivity", "data", "communication", "ai"
cursor	string	—
featured	boolean	Show only featured servers
limit	integer	— max: 100 · default: 20

Raw schema JSON

mcp_list — raw

{
  "name": "mcp_list",
  "description": "Browse available MCP servers that can be connected to",
  "inputSchema": {
    "properties": {
      "category": {
        "description": "Filter by category",
        "enum": [
          "developer",
          "productivity",
          "data",
          "communication",
          "ai"
        ],
        "type": "string"
      },
      "cursor": {
        "type": "string"
      },
      "featured": {
        "description": "Show only featured servers",
        "type": "boolean"
      },
      "limit": {
        "default": 20,
        "maximum": 100,
        "type": "integer"
      }
    },
    "type": "object"
  }
}

mcp_run 2 params · 1 required Call 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.

Input schema

Parameter	Type	Description & constraints
input	object	Tool input arguments
slug*	string	slug/tool format (e.g. 'linear/list_issues')

Raw schema JSON

mcp_run — raw

{
  "name": "mcp_run",
  "description": "Call a tool on a connected MCP server. The server must be connected first via mcp_connect.",
  "inputSchema": {
    "properties": {
      "input": {
        "description": "Tool input arguments",
        "type": "object"
      },
      "slug": {
        "description": "slug/tool format (e.g. &#39;linear/list_issues&#39;)",
        "type": "string"
      }
    },
    "required": [
      "slug"
    ],
    "type": "object"
  }
}

mcp_search 3 params · 1 required Search available MCP servers by query

Search available MCP servers by query

Input schema

Parameter	Type	Description & constraints
cursor	string	—
limit	integer	— max: 100 · default: 20
query*	string	Search query

Raw schema JSON

mcp_search — raw

{
  "name": "mcp_search",
  "description": "Search available MCP servers by query",
  "inputSchema": {
    "properties": {
      "cursor": {
        "type": "string"
      },
      "limit": {
        "default": 20,
        "maximum": 100,
        "type": "integer"
      },
      "query": {
        "description": "Search query",
        "type": "string"
      }
    },
    "required": [
      "query"
    ],
    "type": "object"
  }
}

mcp_tools 1 param · 1 required List available tools on a connected MCP server, or get details for a specific tool

List available tools on a connected MCP server, or get details for a specific tool

Input schema

Parameter	Type	Description & constraints
slug*	string	Server slug (e.g. 'linear') or slug/tool (e.g. 'linear/list_issues')

Raw schema JSON

mcp_tools — raw

{
  "name": "mcp_tools",
  "description": "List available tools on a connected MCP server, or get details for a specific tool",
  "inputSchema": {
    "properties": {
      "slug": {
        "description": "Server slug (e.g. &#39;linear&#39;) or slug/tool (e.g. &#39;linear/list_issues&#39;)",
        "type": "string"
      }
    },
    "required": [
      "slug"
    ],
    "type": "object"
  }
}

skill_files 1 param · 1 required List supplementary files for a skill (references, scripts, etc.)

List supplementary files for a skill (references, scripts, etc.)

Input schema

Parameter	Type	Description & constraints
ref*	string	Skill ref: namespace/name

Raw schema JSON

skill_files — raw

{
  "name": "skill_files",
  "description": "List supplementary files for a skill (references, scripts, etc.)",
  "inputSchema": {
    "properties": {
      "ref": {
        "description": "Skill ref: namespace/name",
        "type": "string"
      }
    },
    "required": [
      "ref"
    ],
    "type": "object"
  }
}

skill_search 4 params · 1 required Search the public skill store

Search the public skill store

Input schema

Parameter	Type	Description & constraints
category	string	Filter by category
cursor	string	—
limit	integer	— max: 100 · default: 20
query*	string	Search query

Raw schema JSON

skill_search — raw

{
  "name": "skill_search",
  "description": "Search the public skill store",
  "inputSchema": {
    "properties": {
      "category": {
        "description": "Filter by category",
        "type": "string"
      },
      "cursor": {
        "type": "string"
      },
      "limit": {
        "default": 20,
        "maximum": 100,
        "type": "integer"
      },
      "query": {
        "description": "Search query",
        "type": "string"
      }
    },
    "required": [
      "query"
    ],
    "type": "object"
  }
}

skill_store 4 params Browse approved skills in the public skill store

Browse approved skills in the public skill store

Input schema

Parameter	Type	Description & constraints
category	string	Filter by category
cursor	string	—
featured	boolean	Show only featured skills
limit	integer	— max: 100 · default: 20

Raw schema JSON

skill_store — raw

{
  "name": "skill_store",
  "description": "Browse approved skills in the public skill store",
  "inputSchema": {
    "properties": {
      "category": {
        "description": "Filter by category",
        "type": "string"
      },
      "cursor": {
        "type": "string"
      },
      "featured": {
        "description": "Show only featured skills",
        "type": "boolean"
      },
      "limit": {
        "default": 20,
        "maximum": 100,
        "type": "integer"
      }
    },
    "type": "object"
  }
}

skill_upload 5 params · 2 required Create or update a skill with SKILL.md content and optional supporting files

Create or update a skill with SKILL.md content and optional supporting files

Input schema

Parameter	Type	Description & constraints
allowed_tools	string	Comma-separated list of allowed tools
content*	string	SKILL.md body content (markdown)
description	string	Short description
files	array<object>	Supporting files (references, scripts)
files[].content*	string	—
files[].path*	string	—
name*	string	Skill name

Raw schema JSON

skill_upload — raw

{
  "name": "skill_upload",
  "description": "Create or update a skill with SKILL.md content and optional supporting files",
  "inputSchema": {
    "properties": {
      "allowed_tools": {
        "description": "Comma-separated list of allowed tools",
        "type": "string"
      },
      "content": {
        "description": "SKILL.md body content (markdown)",
        "type": "string"
      },
      "description": {
        "description": "Short description",
        "type": "string"
      },
      "files": {
        "description": "Supporting files (references, scripts)",
        "items": {
          "properties": {
            "content": {
              "type": "string"
            },
            "path": {
              "type": "string"
            }
          },
          "required": [
            "path",
            "content"
          ],
          "type": "object"
        },
        "type": "array"
      },
      "name": {
        "description": "Skill name",
        "type": "string"
      }
    },
    "required": [
      "name",
      "content"
    ],
    "type": "object"
  }
}

skill_use 1 param · 1 required Fetch a skill's assembled SKILL.md content. Tries the inference.sh store first, falls back to GitHub. Returns …

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.

Input schema

Parameter	Type	Description & constraints
ref*	string	Skill ref: namespace/name, or github.com/user/repo URL

Raw schema JSON

skill_use — raw

{
  "name": "skill_use",
  "description": "Fetch a skill&#39;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.",
  "inputSchema": {
    "properties": {
      "ref": {
        "description": "Skill ref: namespace/name, or github.com/user/repo URL",
        "type": "string"
      }
    },
    "required": [
      "ref"
    ],
    "type": "object"
  }
}

skill_view 2 params · 2 required View a specific supplementary file from a skill's manifest

View a specific supplementary file from a skill's manifest

Input schema

Parameter	Type	Description & constraints
path*	string	File path within the skill
ref*	string	Skill ref: namespace/name

Raw schema JSON

skill_view — raw

{
  "name": "skill_view",
  "description": "View a specific supplementary file from a skill&#39;s manifest",
  "inputSchema": {
    "properties": {
      "path": {
        "description": "File path within the skill",
        "type": "string"
      },
      "ref": {
        "description": "Skill ref: namespace/name",
        "type": "string"
      }
    },
    "required": [
      "ref",
      "path"
    ],
    "type": "object"
  }
}

task_cancel 2 params · 1 required Cancel a running or queued task

Cancel a running or queued task

Input schema

Parameter	Type	Description & constraints
force	boolean	Force kill immediately instead of graceful shutdown default: false
task_id*	string	Task ID

Raw schema JSON

task_cancel — raw

{
  "name": "task_cancel",
  "description": "Cancel a running or queued task",
  "inputSchema": {
    "properties": {
      "force": {
        "default": false,
        "description": "Force kill immediately instead of graceful shutdown",
        "type": "boolean"
      },
      "task_id": {
        "description": "Task ID",
        "type": "string"
      }
    },
    "required": [
      "task_id"
    ],
    "type": "object"
  }
}

task_get 1 param · 1 required Get status and output of a task

Get status and output of a task

Input schema

Parameter	Type	Description & constraints
task_id*	string	Task ID

Raw schema JSON

task_get — raw

{
  "name": "task_get",
  "description": "Get status and output of a task",
  "inputSchema": {
    "properties": {
      "task_id": {
        "description": "Task ID",
        "type": "string"
      }
    },
    "required": [
      "task_id"
    ],
    "type": "object"
  }
}

task_list 3 params List your tasks on inference.sh

List your tasks on inference.sh

Input schema

Parameter	Type	Description & constraints
cursor	string	—
limit	integer	— max: 100 · default: 20
status	enum(6)	— one of: "received", "queued", "running", "completed", "failed", "cancelled"

Raw schema JSON

task_list — raw

{
  "name": "task_list",
  "description": "List your tasks on inference.sh",
  "inputSchema": {
    "properties": {
      "cursor": {
        "type": "string"
      },
      "limit": {
        "default": 20,
        "maximum": 100,
        "type": "integer"
      },
      "status": {
        "enum": [
          "received",
          "queued",
          "running",
          "completed",
          "failed",
          "cancelled"
        ],
        "type": "string"
      }
    },
    "type": "object"
  }
}

task_logs 2 params · 1 required Get execution logs for a task

Get execution logs for a task

Input schema

Parameter	Type	Description & constraints
log_type	enum(5)	— one of: "build", "run", "setup", "serve", "task" · default: "run"
task_id*	string	Task ID

Raw schema JSON

task_logs — raw

{
  "name": "task_logs",
  "description": "Get execution logs for a task",
  "inputSchema": {
    "properties": {
      "log_type": {
        "default": "run",
        "enum": [
          "build",
          "run",
          "setup",
          "serve",
          "task"
        ],
        "type": "string"
      },
      "task_id": {
        "description": "Task ID",
        "type": "string"
      }
    },
    "required": [
      "task_id"
    ],
    "type": "object"
  }
}

Resources 0

No resources advertised.

Prompts 0

No prompts advertised.

Inventory recorded Aug 6, 2026 — 5:20 AM as rev 1. Listing calls only — tools are never invoked.

Canonical contract hash

contract hash — rev 1

sha256:0fe4606b21a0a98c29b4711a61b44575fcb0101d98fc49f29d04d73a5977a54d

Computed centrally from the normalized capability inventory (normalizer v1). Scanners submit raw observations; the control plane normalizes and hashes, so every scanner agrees on the same value.

Revisions 1

Rev	Observed	Hash
rev 1 baseline	Aug 6, 2026 — 5:20 AM (88 d ago)

Contract changes 0

No drift observed — every successful observation since Aug 6, 2026 has matched the baseline hash. Boring, in the best way.

Full snapshots are stored only when the canonical hash changes — unchanged observations update freshness without duplicating the contract.

Recent observations latest 30

Observed	Result	Latency
Nov 2, 2026 — 1:45 AM (40 min ago)	Authentication required	606 ms
Nov 1, 2026 — 11:40 PM (3 h ago)	Authentication required	579 ms
Nov 1, 2026 — 9:40 PM (5 h ago)	Authentication required	724 ms
Nov 1, 2026 — 7:35 PM (7 h ago)	Authentication required	573 ms
Nov 1, 2026 — 5:30 PM (9 h ago)	Authentication required	605 ms
Nov 1, 2026 — 3:25 PM (11 h ago)	Authentication required	565 ms
Nov 1, 2026 — 1:20 PM (13 h ago)	Authentication required	555 ms
Nov 1, 2026 — 11:15 AM (15 h ago)	Authentication required	574 ms
Nov 1, 2026 — 9:10 AM (17 h ago)	Authentication required	583 ms
Nov 1, 2026 — 7:05 AM (19 h ago)	Authentication required	599 ms
Nov 1, 2026 — 5:00 AM (21 h ago)	Authentication required	574 ms
Nov 1, 2026 — 2:55 AM (23 h ago)	Authentication required	583 ms
Nov 1, 2026 — 12:50 AM (1 d ago)	Authentication required	566 ms
Oct 31, 2026 — 10:45 PM (1 d ago)	Authentication required	561 ms
Oct 31, 2026 — 8:40 PM (1 d ago)	Authentication required	563 ms
Oct 31, 2026 — 6:35 PM (1 d ago)	Authentication required	579 ms
Oct 31, 2026 — 4:30 PM (1 d ago)	Authentication required	696 ms
Oct 31, 2026 — 2:25 PM (1 d ago)	Authentication required	586 ms
Oct 31, 2026 — 12:20 PM (2 d ago)	Authentication required	662 ms
Oct 31, 2026 — 10:15 AM (2 d ago)	Authentication required	587 ms
Oct 31, 2026 — 8:10 AM (2 d ago)	Authentication required	555 ms
Oct 31, 2026 — 6:05 AM (2 d ago)	Authentication required	534 ms
Oct 31, 2026 — 4:00 AM (2 d ago)	Authentication required	616 ms
Oct 31, 2026 — 1:55 AM (2 d ago)	Authentication required	682 ms
Oct 30, 2026 — 11:50 PM (2 d ago)	Authentication required	206 ms
Oct 30, 2026 — 9:45 PM (2 d ago)	Authentication required	630 ms
Oct 30, 2026 — 7:40 PM (2 d ago)	Authentication required	741 ms
Oct 30, 2026 — 5:35 PM (2 d ago)	Authentication required	596 ms
Oct 30, 2026 — 3:30 PM (2 d ago)	Authentication required	653 ms
Oct 30, 2026 — 1:25 PM (3 d ago)	Authentication required	318 ms

Latest check — evidence & validation Nov 2, 2026 — 1:45 AM

Authentication required MCP Tools Edge Scanner ScheduledHTTP 401606 ms

response headers (as observed)

{
  "server": "cloudflare",
  "content-type": "application/json",
  "www-authenticate": "Bearer resource_metadata=\"https://api.inference.sh/.well-known/oauth-protected-resource\", scope=\"agents:read apps:read conversations:read files:read flows:read datastores:read projects:read teams:read secrets:read credentials:read knowledge:read artifacts:read remotes:read sandboxes:read settings:re"
}

auth metadata

{
  "httpStatus": 401,
  "wwwAuthenticate": "Bearer resource_metadata=\"https://api.inference.sh/.well-known/oauth-protected-resource\", scope=\"agents:read apps:read conversations:read files:read flows:read datastores:read projects:read teams:read secrets:read credentials:read knowledge:read artifacts:read remotes:read sandboxes:read settings:read bounties:read agents:execute apps:execute flows:execute forms:execute agents:write apps:write conversations:write files:write flows:write datastores:write projects:write secrets:write credentials:write knowledge:write artifacts:write remotes:write sandboxes:write settings:write forms:write billing:read\"",
  "discovery": {
    "resource": "https://api.inference.sh",
    "authorization_servers": [
      "https://api.inference.sh"
    ],
    "scopes_supported": [
      "agents:read",
      "apps:read",
      "conversations:read",
      "files:read",
      "flows:read",
      "datastores:read",
      "projects:read",
      "teams:read",
      "secrets:read",
      "credentials:read",
      "knowledge:read",
      "artifacts:read",
      "remotes:read",
      "sandboxes:read",
      "settings:read",
      "bounties:read",
      "agents:execute",
      "apps:execute",
      "flows:execute",
      "forms:execute",
      "agents:write",
      "apps:write",
      "conversations:write",
      "files:write",
      "flows:write",
      "datastores:write",
      "projects:write",
      "secrets:write",
      "credentials:write",
      "knowledge:write",
      "artifacts:write",
      "remotes:write",
      "sandboxes:write",
      "settings:write",
      "forms:write",
      "billing:read"
    ]
  }
}

Baseline capturedThe current contract is rev 1 — the reference state for this endpoint. Future observations will identify outages, recoveries, protocol changes, and contract drift from this state.

Server name	`inference.sh`
Server version	`2.0.0`
Transport	Streamable HTTP
Protocol version	`2025-06-18`
First observed	Aug 6, 2026
Last observed	40 min ago
Last successful	40 min ago
Origin	Registry seed

inference.sh MCP · inference.sh

Availability — last 30 days

Advertised capabilities

Tools 25

Input schema

Input schema

Input schema

Input schema

Input schema

Input schema

Input schema

Input schema

Input schema

Input schema

Input schema

Input schema

Input schema

Input schema

Input schema

Input schema

Input schema

Input schema

Input schema

Input schema

Input schema

Input schema

Input schema

Input schema

Input schema

Resources 0

Prompts 0

Canonical contract hash

Revisions 1

Contract changes 0

Recent observations latest 30

Publisher supplied

Independently observed

Name	inference.sh MCP
Vendor	inference.sh
Category	infrastructure
Docs	—
Repository	—
Auth expected	Auth expectations unknown