Hello, AI MCP
An MCP server that provides tools to interact with the Hello, AI directory of frontier AI models. It allows agents to list models, get specific model details, retrieve recommendations based on tasks, and access articles and status updates, all without authentication.
Endpoint and access
No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.
https://helloai.com/mcpWhat you can do with it
- Recommend models for specific tasks like coding
- List available frontier AI models with Elo scores
- Get detailed information about a specific model
- Retrieve status and data freshness information
Source and maintenance
Protocol and capabilities
- Server
- helloai 2.14.85
- MCP protocol
- 2025-06-18
- Tools
- 6 advertised
- Resources
- Not advertised
- Resource templates
- Not advertised
- Prompts
- Not advertised
{
"tools": {}
}Server-provided instructions
Untrusted server output shown for inspection. It is not Koskamo guidance and is excluded from knowledge search.
Tools
6 advertised
recommend_models — Recommend models for a task
Rank Hello, AI's tracked frontier models for a task. Same scoring as GET /api/recommend: task match 40%, Elo 35%, input cost 15%, context 10% (Elo 55%, cost 25%, context 20% when no task matches). Only rated models rank; unrated ones are listed separately. score is an ordering aid, not a quality measure.
{
"type": "object",
"properties": {
"task": {
"type": "string",
"maxLength": 64,
"description": "Use case, matched against the category names: Overall Preference, Coding & Engineering, Hard Reasoning & Science, Honest Daily Use. Examples: coding, reasoning, overall, daily."
},
"limit": {
"type": "integer",
"default": 3,
"maximum": 10,
"minimum": 1,
"description": "How many ranked rows to return, 1 to 10. Default 3."
},
"max_cost": {
"type": "number",
"description": "Maximum USD per 1 million input tokens; models above it are excluded.",
"exclusiveMinimum": 0
},
"provider": {
"type": "string",
"description": "Provider name, case-insensitive exact match (for example Anthropic, Google, xAI)."
},
"min_context": {
"type": "integer",
"minimum": 1,
"description": "Minimum context window in tokens; models below it are excluded."
}
},
"additionalProperties": false
}{
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true
}list_models — List tracked models
All tracked models with full records: Elo and its provenance (elo_source), prices per million tokens, context window, strengths, description. rated is false when the stored Elo is a predecessor's, missing or stale.
{
"type": "object",
"properties": {
"provider": {
"type": "string",
"description": "Provider name, case-insensitive substring match."
}
},
"additionalProperties": false
}{
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true
}get_model — Get one model
One tracked model's full record by id (claude, fable, muse, gemini, qwen, grok) or exact name.
{
"type": "object",
"required": [
"id"
],
"properties": {
"id": {
"type": "string",
"description": "Model id or exact name"
}
},
"additionalProperties": false
}{
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true
}list_categories — List use-case categories
The curated use-case categories with their curator-chosen leader and a one-paragraph insight. The leader is a hand-set label, not derived from Elo.
{
"type": "object",
"properties": {},
"additionalProperties": false
}{
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true
}list_articles — List recent articles
Recent Hello, AI articles, newest first: title, date, category, excerpt and URL.
{
"type": "object",
"properties": {
"limit": {
"type": "integer",
"default": 10,
"maximum": 50,
"minimum": 1,
"description": "Articles to return, 1 to 50. Default 10."
}
},
"additionalProperties": false
}{
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true
}get_status — Data freshness and version
Data freshness, app version, model and article counts, the scoring version and snapshot fingerprint, and the rate limit.
{
"type": "object",
"properties": {},
"additionalProperties": false
}{
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true
}Prompts
Not advertised
Resources
Not advertised
30-day availability
Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.
- Successful checks
- 1 of 1 (100%)
- Average latency
- 311 ms
- 95th percentile latency
- 311 ms
Maintenance history
Public check and source-refresh events. Editorial and ownership records remain private.
- · probe · passed · 311 ms · metadata changed · 6 tool(s)
Connect from your client
Each snippet registers the same endpoint; pick the client you use.
Claude Code
claude mcp add --transport http hello-ai-mcp https://helloai.com/mcpCodex
codex mcp add hello-ai-mcp --url https://helloai.com/mcpCursor
{
"mcpServers": {
"hello-ai-mcp": {
"url": "https://helloai.com/mcp"
}
}
}Cline
{
"mcpServers": {
"hello-ai-mcp": {
"type": "streamableHttp",
"url": "https://helloai.com/mcp",
"disabled": false
}
}
}VS Code
{
"servers": {
"hello-ai-mcp": {
"type": "http",
"url": "https://helloai.com/mcp"
}
}
}Gemini CLI
gemini mcp add --transport http hello-ai-mcp https://helloai.com/mcpClaude Desktop
{
"mcpServers": {
"hello-ai-mcp": {
"url": "https://helloai.com/mcp"
}
}
}Windsurf
{
"mcpServers": {
"hello-ai-mcp": {
"serverUrl": "https://helloai.com/mcp"
}
}
}Let your agent find its tools
Find servers like Hello, AI MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.
Other ai and machine learning servers
Do you run Hello, AI MCP?
Prove ownership with a DNS record, a well-known file, or your Official MCP Registry entry, and your edits publish immediately. Proofs are re-checked weekly; admins can still hide or remove a listing.