Skip to content
External endpointresponds

inference.sh

Run 150+ AI apps — image, video, audio, LLMs, 3D and more. Browse, execute, stream results.

Endpoint URL
https://api.inference.sh/mcp
Current status
responds
Last checked
Aug 17, 2026, 04:59 AM UTC
Check
MCP initialize · 8s limit
Latency
889 ms
Response record
4 of 4 rounds
Transport
streamable-http
Source
mcp_registry
Registry name
ac.inference.sh/mcp

Current observation

This endpoint answered at its latest recorded check.

What this server reports about itself

Self-reported at initialize. Not verified by Licium.

Server name
inference.sh
Version
2.0.0
Capability keys
logging, prompts, resources, tools
Tool names
app_get, app_list, app_run, knowledge_create, knowledge_delete, knowledge_get, knowledge_list, knowledge_search, mcp_connect, mcp_disconnect, mcp_get, mcp_list, mcp_run, mcp_search, mcp_tools, skill_files, skill_search, skill_store, skill_upload, skill_use, skill_view, task_cancel, task_get, task_list, task_logs
Instructions excerpt

inference.sh lets you run AI apps, manage knowledge and skills, and connect to other MCP servers. Apps: app_list, app_get, app_run, task_get, task_list, task_logs, task_cancel. Knowledge: knowledge_list, knowledge_search, knowledge_get, knowledge_create, knowledge_delete. Skills: skill_use (with GitHub fallback), skill_files, skill_view, skill_upload, skill_store, skill_search. MCP proxy: mcp_list, mcp_search, mcp_get, mcp_tools, mcp_run, mcp_connect, mcp_disconnect.

Reported Aug 17, 2026, 04:59 AM UTC.

Check history

Oldest to newest. Each row is one recorded check.

  1. responds
    MCP initialize · 8s limit · HTTP 200 · 756ms
  2. responds
    MCP initialize · 8s limit · HTTP 200 · 815ms
  3. responds
    MCP initialize · 8s limit · HTTP 200 · 795ms
  4. responds
    MCP initialize · 8s limit · HTTP 200 · 889ms
Back to MCP directory