mcpbeat Sign in

inference.sh MCP Server

by inference-sh Your server? Claim it
answering

inference.sh is answering right now. Last checked 14 min ago. It exposes 25 tools.

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

Uptime history 52 days of history · worst day 95%
52 days agonow
97.8%
Uptime 24h
89 of 91 checks
25
Tools
read from the server
114 ms
Response time
average over 24h
OAuth sign-in
Access
streamable-http

inference.sh does not always answer

Over the last week it answered 98.7% of our checks. We check every 15 minutes, so you hear about the next outage within the hour — not from your users.

Three servers free · no card

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 14 min ago.

run in your terminal
claude mcp add mcp --transport http https://api.inference.sh/mcp
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "mcp": {
      "url": "https://api.inference.sh/mcp"
    }
  }
}
~/.codex/config.toml
[mcp_servers.mcp]
url = "https://api.inference.sh/mcp"
.cursor/mcp.json
{
  "mcpServers": {
    "mcp": {
      "url": "https://api.inference.sh/mcp"
    }
  }
}
.vscode/mcp.json
{
  "mcpServers": {
    "mcp": {
      "url": "https://api.inference.sh/mcp"
    }
  }
}

This endpoint answered with an authorization challenge. The server is running, and it signs you in through your browser: there is no API key to paste.

Available tools 25

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

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

Endpoints

URLTransportStateLatencyChecked
https://api.inference.sh/mcp streamable-http sign-in 174 ms 14 min ago

Alternatives to inference.sh

same job, measured the same way
Nex
by nex-crm

Organizational context & memory for AI agents. Connect 100+ tools into one knowledge graph.

48 installs/wk local only
Forensic Deepdive
by dhevenddra

Persistent code knowledge graph + 9 composite MCP tools for AI coding agents.

147 installs/wk local only
Scrollport
by scrollport

Verified, pay-per-use API tools for AI agents through one authenticated connection.

answering
Guru Remote MCP Server
by getguru

Guru MCP Server - Connect AI tools to your Guru knowledge base

answering
Voidfeed MCP
by voidfeedai-ops

Knowledge API for AI agents — content, agent directory, model benchmarks, semantic search.

23 installs/wk local only
Command+K
by commandplusk

Set up and run an in-product AI assistant: widgets, knowledge, MCP connections, usage.

answering
x402-market
by asaishota

Let AI agents pay-per-call for any HTTP API via x402 on Base mainnet. One tool: pay_and_call.

36 installs/wk local only
ToolRouter
by humanleap

The OpenRouter for tools. One MCP connection gives any AI agent 254 hosted tools, pay per call.

48 tools answering

inference.sh — questions

Answers built from our own checks of this server.

What can inference.sh do?
It exposes 25 tools, read directly from the server on our last check. Among them: app_get, app_list, app_run, knowledge_create, knowledge_delete, knowledge_get and 19 more. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →
What is inference.sh mostly used for?
Its tools cluster around mcp, skill and knowledge. That is what this server is built to work with — the grouping comes from the actual tool names, not from a category we assigned.
Is inference.sh working right now?
We send a real MCP handshake every 15 minutes. Over the last 24 hours 89 of 91 checks got a reply (97.8%), average response time 114 ms. The bar chart above shows every period we have measured.
How do I connect inference.sh?
Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address. You sign in through your browser once and the client keeps the session: no key to copy, and it refuses anonymous clients.
How do you sign in to inference.sh?
No API key is involved. inference.sh answers our knock with an OAuth challenge, so you authorise it once in your browser and the client keeps the session. That is also why we see no tool list: it will not describe itself to an anonymous client, and that is the server working as intended, not a fault.
How fast is inference.sh?
It answers our handshake in 114 ms on average, which is faster than 87% of all working MCP servers we measure. That puts it in the quick quarter of the ecosystem. The comparison comes from our own checks across the whole registry, every 15 minutes.