ZBS Index What actually exists in applied AI, with the source next to it

mcp server

inference.sh

run any ai model. compose agents, stack knowledge, connect tools. one api, pay per run.

Description as published by the maintainer. Source

  • version 2.0.1
  • active

active — Registry entry last updated 2026-07-27.

What this server can do

25 functions, named and described by the server itself. Parameter names are shown because they say more about what a function does than its name usually does.

app_get(app)
Get detailed app info including input/output schemas and version history Required: app.
app_list(limit, query, cursor, category)
Search and filter available apps on inference.sh
app_run(app, input, function, infrastructure)
Run an app on inference.sh. Creates a task that executes the app with the given input. Required: app, input.
knowledge_create(name, type, content, description)
Create a new knowledge entry (concept, observation, preference, reference, etc.) Required: name, content.
knowledge_delete(id)
Delete a knowledge entry by ID Required: id.
knowledge_get(ref)
Get detailed information about a knowledge entry by namespace/name or ID Required: ref.
knowledge_list(type, limit, cursor)
List your knowledge entries, optionally filtered by type
knowledge_search(type, limit, query, cursor)
Search your knowledge entries by query Required: query.
mcp_connect(slug)
Initiate a connection to an MCP server. For OAuth servers, returns an authorization URL to open in a browser. Required: slug.
mcp_disconnect(slug)
Remove connection to an MCP server Required: slug.
mcp_get(slug)
Get details about an MCP server including connection status Required: slug.
mcp_list(limit, cursor, category, featured)
Browse available MCP servers that can be connected to
mcp_run(slug, input)
Call a tool on a connected MCP server. The server must be connected first via mcp_connect. Required: slug.
mcp_search(limit, query, cursor)
Search available MCP servers by query Required: query.
mcp_tools(slug)
List available tools on a connected MCP server, or get details for a specific tool Required: slug.
skill_files(ref)
List supplementary files for a skill (references, scripts, etc.) Required: ref.
skill_search(limit, query, cursor, category)
Search the public skill store Required: query.
skill_store(limit, cursor, category, featured)
Browse approved skills in the public skill store
skill_upload(name, files, content, description, allowed_tools)
Create or update a skill with SKILL.md content and optional supporting files Required: name, content.
skill_use(ref)
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. Required: ref.
skill_view(ref, path)
View a specific supplementary file from a skill's manifest Required: ref, path.
task_cancel(force, task_id)
Cancel a running or queued task Required: task_id.
task_get(task_id)
Get status and output of a task Required: task_id.
task_list(limit, cursor, status)
List your tasks on inference.sh
task_logs(task_id, log_type)
Get execution logs for a task Required: task_id.

Last successful function declaration observed on . Source: https://api.inference.sh/mcp. We list what the server declared; we do not call any of these functions.

Endpoint status observed on . Source: https://api.inference.sh/mcp.

Signals

These are separate measurements of different things. They are deliberately not combined into one score, because a popularity number that mixes website traffic with saves and stars cannot be checked or acted on.

Signal Value What it measures Window Observed Source
Latest published version 2.0.1 Latest version string the maintainer published to the registry. as of fetch Model Context Protocol
Registry record last updated 2026-07-27 When the registry record was last updated by its maintainer. point in time Model Context Protocol
First listed in the MCP Registry 2026-07-27 Date this server was first published to the official MCP Registry. Not a usage or quality measure. point in time Model Context Protocol
mcp tools declared 25 tools Number of functions the server itself declared when asked to list them. This is what the server offers an agent, not a measure of how well any of them work. as of probe api.inference.sh
mcp endpoint status ok The server listed 25 functions when asked. as of probe api.inference.sh

Where to get it

This record as data

Every field on this page, with its source and observation date, is in the catalog JSON. Fetch the whole kind at once instead of parsing this HTML.

GET /api/v1/entries/mcp_server.json

Sources

  1. Tools declared by the MCP server at https://api.inference.sh/mcp — api.inference.sh, observed , trust tier 1.
  2. Official MCP Registry — Model Context Protocol, observed , trust tier 1.