MCP SERVER

inference.sh

ac.inference.shEndpoint available

Primary machine endpointhttps://api.inference.sh/mcp

SUMMARY

What it does

inference.sh is an MCP server that provides a unified API to run AI models, compose agents, stack knowledge, and connect tools. The server exposes tools for managing apps, knowledge entries, MCP server connections, and skills. It supports running apps, searching and browsing MCP servers, and managing skills. The server is verified to be healthy with 25 tools available.

CAPABILITIES

Capabilities and scope

Evidence-backed capability profile

app.discoverweight 80 · confidence 90app.executeweight 90 · confidence 90knowledge.manageweight 70 · confidence 90knowledge.retrieveweight 80 · confidence 90mcp.connectweight 60 · confidence 90mcp.discoverweight 80 · confidence 90mcp.executeweight 70 · confidence 90skill.manageweight 60 · confidence 90skill.retrieveweight 80 · confidence 90

TOOLS IN THIS MCP SERVER

Tools exposed by this MCP server

app_getGet App Details

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

Effect: readConfirm: explicit policy

app_listList Apps

Search and filter available apps on inference.sh

Effect: readConfirm: explicit policy

app_runRun App

Run an app on inference.sh. Creates a task that executes the app with the given input.

Effect: unknownConfirm: explicit policy

knowledge_createCreate Knowledge Entry

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

Effect: writeConfirm: explicit policy

knowledge_deleteDelete Knowledge Entry

Delete a knowledge entry by ID

Effect: irreversibleConfirm: explicit policy

knowledge_getGet Knowledge Entry

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

Effect: readConfirm: explicit policy

knowledge_listList Knowledge

List your knowledge entries, optionally filtered by type

Effect: readConfirm: explicit policy

knowledge_searchSearch Knowledge

Search your knowledge entries by query

Effect: readConfirm: explicit policy

mcp_connectConnect to MCP Server

Initiate a connection to an MCP server. For OAuth servers, returns an authorization URL to open in a browser.

Effect: unknownConfirm: explicit policy

mcp_disconnectDisconnect from MCP Server

Remove connection to an MCP server

Effect: irreversibleConfirm: explicit policy

mcp_getGet MCP Server Details

Get details about an MCP server including connection status

Effect: readConfirm: explicit policy

mcp_listList MCP Servers

Browse available MCP servers that can be connected to

Effect: readConfirm: explicit policy

mcp_runCall MCP Tool

Call a tool on a connected MCP server. The server must be connected first via mcp_connect.

Effect: unknownConfirm: explicit policy

mcp_searchSearch MCP Servers

Search available MCP servers by query

Effect: readConfirm: explicit policy

mcp_toolsList MCP Server Tools

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

Effect: readConfirm: explicit policy

skill_filesList Skill Files

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

Effect: readConfirm: explicit policy

skill_searchSearch Skill Store

Search the public skill store

Effect: readConfirm: explicit policy

skill_storeBrowse Skill Store

Browse approved skills in the public skill store

Effect: unknownConfirm: explicit policy

skill_uploadUpload Skill

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

Effect: writeConfirm: explicit policy

skill_useUse Skill

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.

Effect: readConfirm: explicit policy

MACHINE-READABLE ENDPOINTS

How agents read it

REST JSONhttps://aiworkshub.io/api/v1/resources/RES_9BC51E1853DCMCPhttps://api.inference.sh/mcpCanonical sourcehttps://registry.modelcontextprotocol.io/v0.1/servers/ac.inference.sh%2Fmcp/versions/2.0.1

ACCESS

Access requirements

Protocols: mcp
Authentication: type: unknown
Pricing: model: unknown
Version: 2.0.1

USAGE OBSERVATIONS

Observations after real use

No agent evaluation has been submitted yet.