SERVER

Ask Llm

Rank #10,211

io.github.Lykhoyda/ask-llm

Unified MCP server for Gemini, Codex, Claude, Grok, Ollama, and Antigravity

33 versions

18 GitHub stars

by Lykhoyda (10 servers)View repository ↗

First listed

Apr 13, 2026

Last publish date

Oct 13, 2026

PURPOSE

What you can do with Ask Llm

Ask Llm is a Model Context Protocol (MCP) server published by Lykhoyda. It ranks #10,211 of 144,396 active servers on MCP Toplist, and its repository has 18 GitHub stars. Ask Llm is listed on Official MCP, with 33 tracked versions. It was first listed on Apr 13, 2026 and most recently updated on Oct 13, 2026.

Not verifiedMCP Toplist has not yet written a checked profile for this server, so the paragraph above is assembled from registry data only. The repository README is the authority on what it does.

CAPABILITIES AND LIMITATIONS

What Ask Llm can and cannot do

Not verifiedMCP Toplist has not catalogued this server's tools or limitations. The repository README lists them.

REQUIREMENTS

What you need before using Ask Llm

DeclaredNo credentialsNo credentials declared

The registry listing declares no required environment variables or authentication. This is declared metadata, not a verified install — the repository README is the authority.

Declared by the Official MCP Registry, last synced Oct 16, 2026. Not independently verified by MCP Toplist.

Declared in the registry install config

XAI_API_KEY · optional
ASK_GROK_HARNESS · optional
ASK_GROK_MODEL · optional
ASK_GROK_REASONING_EFFORT · optional
ASK_GROK_MAX_OUTPUT_TOKENS · optional
ASK_GROK_TIMEOUT_MS · optional
CURSOR_API_KEY · optional
ASK_CURSOR_TIMEOUT_MS · optional
ASK_CLAUDE_MODEL · optional
ASK_CLAUDE_FALLBACK_MODEL · optional
ASK_CLAUDE_TIMEOUT_MS · optional
OLLAMA_HOST · optional
ASK_ANTIGRAVITY_TIMEOUT_MS · optional
ASK_ANTIGRAVITY_SANDBOX · optional
GMCPT_TIMEOUT_MS · optional
GMCPT_LOG_LEVEL · optional

INSTALLATION AND FIRST TASK

Connect Ask Llm and confirm it works

npm package

claude mcp add ask-llm -e "XAI_API_KEY=<your XAI_API_KEY>" -e "ASK_GROK_HARNESS=<your ASK_GROK_HARNESS>" -e "ASK_GROK_MODEL=<your ASK_GROK_MODEL>" -e "ASK_GROK_REASONING_EFFORT=<your ASK_GROK_REASONING_EFFORT>" -e "ASK_GROK_MAX_OUTPUT_TOKENS=<your ASK_GROK_MAX_OUTPUT_TOKENS>" -e "ASK_GROK_TIMEOUT_MS=<your ASK_GROK_TIMEOUT_MS>" -e "CURSOR_API_KEY=<your CURSOR_API_KEY>" -e "ASK_CURSOR_TIMEOUT_MS=<your ASK_CURSOR_TIMEOUT_MS>" -e "ASK_CLAUDE_MODEL=<your ASK_CLAUDE_MODEL>" -e "ASK_CLAUDE_FALLBACK_MODEL=<your ASK_CLAUDE_FALLBACK_MODEL>" -e "ASK_CLAUDE_TIMEOUT_MS=<your ASK_CLAUDE_TIMEOUT_MS>" -e "OLLAMA_HOST=<your OLLAMA_HOST>" -e "ASK_ANTIGRAVITY_TIMEOUT_MS=<your ASK_ANTIGRAVITY_TIMEOUT_MS>" -e "ASK_ANTIGRAVITY_SANDBOX=<your ASK_ANTIGRAVITY_SANDBOX>" -e "GMCPT_TIMEOUT_MS=<your GMCPT_TIMEOUT_MS>" -e "GMCPT_LOG_LEVEL=<your GMCPT_LOG_LEVEL>" -- npx -y @ask-llm/mcp

Replace each placeholder with your own value before saving.

npm package

[mcp_servers.ask-llm]
command = "npx"
args = ["-y", "@ask-llm/mcp"]

[mcp_servers.ask-llm.env]
XAI_API_KEY = "<your XAI_API_KEY>"
ASK_GROK_HARNESS = "<your ASK_GROK_HARNESS>"
ASK_GROK_MODEL = "<your ASK_GROK_MODEL>"
ASK_GROK_REASONING_EFFORT = "<your ASK_GROK_REASONING_EFFORT>"
ASK_GROK_MAX_OUTPUT_TOKENS = "<your ASK_GROK_MAX_OUTPUT_TOKENS>"
ASK_GROK_TIMEOUT_MS = "<your ASK_GROK_TIMEOUT_MS>"
CURSOR_API_KEY = "<your CURSOR_API_KEY>"
ASK_CURSOR_TIMEOUT_MS = "<your ASK_CURSOR_TIMEOUT_MS>"
ASK_CLAUDE_MODEL = "<your ASK_CLAUDE_MODEL>"
ASK_CLAUDE_FALLBACK_MODEL = "<your ASK_CLAUDE_FALLBACK_MODEL>"
ASK_CLAUDE_TIMEOUT_MS = "<your ASK_CLAUDE_TIMEOUT_MS>"
OLLAMA_HOST = "<your OLLAMA_HOST>"
ASK_ANTIGRAVITY_TIMEOUT_MS = "<your ASK_ANTIGRAVITY_TIMEOUT_MS>"
ASK_ANTIGRAVITY_SANDBOX = "<your ASK_ANTIGRAVITY_SANDBOX>"
GMCPT_TIMEOUT_MS = "<your GMCPT_TIMEOUT_MS>"
GMCPT_LOG_LEVEL = "<your GMCPT_LOG_LEVEL>"

Add to ~/.codex/config.toml. Replace each placeholder with your own value before saving.

npm package

{
  "mcpServers": {
    "ask-llm": {
      "command": "npx",
      "args": [
        "-y",
        "@ask-llm/mcp"
      ],
      "env": {
        "XAI_API_KEY": "<your XAI_API_KEY>",
        "ASK_GROK_HARNESS": "<your ASK_GROK_HARNESS>",
        "ASK_GROK_MODEL": "<your ASK_GROK_MODEL>",
        "ASK_GROK_REASONING_EFFORT": "<your ASK_GROK_REASONING_EFFORT>",
        "ASK_GROK_MAX_OUTPUT_TOKENS": "<your ASK_GROK_MAX_OUTPUT_TOKENS>",
        "ASK_GROK_TIMEOUT_MS": "<your ASK_GROK_TIMEOUT_MS>",
        "CURSOR_API_KEY": "<your CURSOR_API_KEY>",
        "ASK_CURSOR_TIMEOUT_MS": "<your ASK_CURSOR_TIMEOUT_MS>",
        "ASK_CLAUDE_MODEL": "<your ASK_CLAUDE_MODEL>",
        "ASK_CLAUDE_FALLBACK_MODEL": "<your ASK_CLAUDE_FALLBACK_MODEL>",
        "ASK_CLAUDE_TIMEOUT_MS": "<your ASK_CLAUDE_TIMEOUT_MS>",
        "OLLAMA_HOST": "<your OLLAMA_HOST>",
        "ASK_ANTIGRAVITY_TIMEOUT_MS": "<your ASK_ANTIGRAVITY_TIMEOUT_MS>",
        "ASK_ANTIGRAVITY_SANDBOX": "<your ASK_ANTIGRAVITY_SANDBOX>",
        "GMCPT_TIMEOUT_MS": "<your GMCPT_TIMEOUT_MS>",
        "GMCPT_LOG_LEVEL": "<your GMCPT_LOG_LEVEL>"
      }
    }
  }
}

Add to claude_desktop_config.json (Settings → Developer → Edit Config). Replace each placeholder with your own value before saving.

npm package

{
  "mcpServers": {
    "ask-llm": {
      "command": "npx",
      "args": [
        "-y",
        "@ask-llm/mcp"
      ],
      "env": {
        "XAI_API_KEY": "<your XAI_API_KEY>",
        "ASK_GROK_HARNESS": "<your ASK_GROK_HARNESS>",
        "ASK_GROK_MODEL": "<your ASK_GROK_MODEL>",
        "ASK_GROK_REASONING_EFFORT": "<your ASK_GROK_REASONING_EFFORT>",
        "ASK_GROK_MAX_OUTPUT_TOKENS": "<your ASK_GROK_MAX_OUTPUT_TOKENS>",
        "ASK_GROK_TIMEOUT_MS": "<your ASK_GROK_TIMEOUT_MS>",
        "CURSOR_API_KEY": "<your CURSOR_API_KEY>",
        "ASK_CURSOR_TIMEOUT_MS": "<your ASK_CURSOR_TIMEOUT_MS>",
        "ASK_CLAUDE_MODEL": "<your ASK_CLAUDE_MODEL>",
        "ASK_CLAUDE_FALLBACK_MODEL": "<your ASK_CLAUDE_FALLBACK_MODEL>",
        "ASK_CLAUDE_TIMEOUT_MS": "<your ASK_CLAUDE_TIMEOUT_MS>",
        "OLLAMA_HOST": "<your OLLAMA_HOST>",
        "ASK_ANTIGRAVITY_TIMEOUT_MS": "<your ASK_ANTIGRAVITY_TIMEOUT_MS>",
        "ASK_ANTIGRAVITY_SANDBOX": "<your ASK_ANTIGRAVITY_SANDBOX>",
        "GMCPT_TIMEOUT_MS": "<your GMCPT_TIMEOUT_MS>",
        "GMCPT_LOG_LEVEL": "<your GMCPT_LOG_LEVEL>"
      }
    }
  }
}

Add to ~/.cursor/mcp.json (global) or .cursor/mcp.json (per project). Replace each placeholder with your own value before saving.

npm package

{
  "servers": {
    "ask-llm": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@ask-llm/mcp"
      ],
      "env": {
        "XAI_API_KEY": "<your XAI_API_KEY>",
        "ASK_GROK_HARNESS": "<your ASK_GROK_HARNESS>",
        "ASK_GROK_MODEL": "<your ASK_GROK_MODEL>",
        "ASK_GROK_REASONING_EFFORT": "<your ASK_GROK_REASONING_EFFORT>",
        "ASK_GROK_MAX_OUTPUT_TOKENS": "<your ASK_GROK_MAX_OUTPUT_TOKENS>",
        "ASK_GROK_TIMEOUT_MS": "<your ASK_GROK_TIMEOUT_MS>",
        "CURSOR_API_KEY": "<your CURSOR_API_KEY>",
        "ASK_CURSOR_TIMEOUT_MS": "<your ASK_CURSOR_TIMEOUT_MS>",
        "ASK_CLAUDE_MODEL": "<your ASK_CLAUDE_MODEL>",
        "ASK_CLAUDE_FALLBACK_MODEL": "<your ASK_CLAUDE_FALLBACK_MODEL>",
        "ASK_CLAUDE_TIMEOUT_MS": "<your ASK_CLAUDE_TIMEOUT_MS>",
        "OLLAMA_HOST": "<your OLLAMA_HOST>",
        "ASK_ANTIGRAVITY_TIMEOUT_MS": "<your ASK_ANTIGRAVITY_TIMEOUT_MS>",
        "ASK_ANTIGRAVITY_SANDBOX": "<your ASK_ANTIGRAVITY_SANDBOX>",
        "GMCPT_TIMEOUT_MS": "<your GMCPT_TIMEOUT_MS>",
        "GMCPT_LOG_LEVEL": "<your GMCPT_LOG_LEVEL>"
      }
    }
  }
}

Save as .vscode/mcp.json in your workspace. Replace each placeholder with your own value before saving.

npm package

{
  "mcpServers": {
    "ask-llm": {
      "command": "npx",
      "args": [
        "-y",
        "@ask-llm/mcp"
      ],
      "env": {
        "XAI_API_KEY": "<your XAI_API_KEY>",
        "ASK_GROK_HARNESS": "<your ASK_GROK_HARNESS>",
        "ASK_GROK_MODEL": "<your ASK_GROK_MODEL>",
        "ASK_GROK_REASONING_EFFORT": "<your ASK_GROK_REASONING_EFFORT>",
        "ASK_GROK_MAX_OUTPUT_TOKENS": "<your ASK_GROK_MAX_OUTPUT_TOKENS>",
        "ASK_GROK_TIMEOUT_MS": "<your ASK_GROK_TIMEOUT_MS>",
        "CURSOR_API_KEY": "<your CURSOR_API_KEY>",
        "ASK_CURSOR_TIMEOUT_MS": "<your ASK_CURSOR_TIMEOUT_MS>",
        "ASK_CLAUDE_MODEL": "<your ASK_CLAUDE_MODEL>",
        "ASK_CLAUDE_FALLBACK_MODEL": "<your ASK_CLAUDE_FALLBACK_MODEL>",
        "ASK_CLAUDE_TIMEOUT_MS": "<your ASK_CLAUDE_TIMEOUT_MS>",
        "OLLAMA_HOST": "<your OLLAMA_HOST>",
        "ASK_ANTIGRAVITY_TIMEOUT_MS": "<your ASK_ANTIGRAVITY_TIMEOUT_MS>",
        "ASK_ANTIGRAVITY_SANDBOX": "<your ASK_ANTIGRAVITY_SANDBOX>",
        "GMCPT_TIMEOUT_MS": "<your GMCPT_TIMEOUT_MS>",
        "GMCPT_LOG_LEVEL": "<your GMCPT_LOG_LEVEL>"
      }
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json. Replace each placeholder with your own value before saving.

npm package

{
  "mcpServers": {
    "ask-llm": {
      "command": "npx",
      "args": [
        "-y",
        "@ask-llm/mcp"
      ],
      "env": {
        "XAI_API_KEY": "<your XAI_API_KEY>",
        "ASK_GROK_HARNESS": "<your ASK_GROK_HARNESS>",
        "ASK_GROK_MODEL": "<your ASK_GROK_MODEL>",
        "ASK_GROK_REASONING_EFFORT": "<your ASK_GROK_REASONING_EFFORT>",
        "ASK_GROK_MAX_OUTPUT_TOKENS": "<your ASK_GROK_MAX_OUTPUT_TOKENS>",
        "ASK_GROK_TIMEOUT_MS": "<your ASK_GROK_TIMEOUT_MS>",
        "CURSOR_API_KEY": "<your CURSOR_API_KEY>",
        "ASK_CURSOR_TIMEOUT_MS": "<your ASK_CURSOR_TIMEOUT_MS>",
        "ASK_CLAUDE_MODEL": "<your ASK_CLAUDE_MODEL>",
        "ASK_CLAUDE_FALLBACK_MODEL": "<your ASK_CLAUDE_FALLBACK_MODEL>",
        "ASK_CLAUDE_TIMEOUT_MS": "<your ASK_CLAUDE_TIMEOUT_MS>",
        "OLLAMA_HOST": "<your OLLAMA_HOST>",
        "ASK_ANTIGRAVITY_TIMEOUT_MS": "<your ASK_ANTIGRAVITY_TIMEOUT_MS>",
        "ASK_ANTIGRAVITY_SANDBOX": "<your ASK_ANTIGRAVITY_SANDBOX>",
        "GMCPT_TIMEOUT_MS": "<your GMCPT_TIMEOUT_MS>",
        "GMCPT_LOG_LEVEL": "<your GMCPT_LOG_LEVEL>"
      }
    }
  }
}

Replace each placeholder with your own value before saving.

First successful task

After adding the config, ask your client to list this server's tools. A tool list confirms the connection; an empty list or an error means the server did not start or needs credentials.

ALTERNATIVES

When to choose another server

Other servers by Lykhoyda

Ask Gemini MCP#42,081

View all Lykhoyda servers →

No task-specific alternatives are catalogued for Ask Llmyet; the list above is its publisher's other servers.

MAINTENANCE AND EVIDENCE

What changed, and when this was checked

First listed: Apr 13, 2026
Latest version published: Oct 13, 2026
Version history: 33 versions tracked (below)
Requirements evidence: Declared by the Official MCP Registry, last synced Oct 16, 2026. Not independently verified by MCP Toplist.
Profile checked: Not yet — purpose, capabilities and requirements above come from registry data only
Ranking data as of: Oct 13, 2026

Registry sightings

Official MCP ↗listed since Apr 28, 2026 · still listed

Do you maintain Ask Llm? to correct or enrich this profile.

VERSIONS

Available versions (33)

Version	Published
1.2.1	Oct 13, 2026
1.2.0	Oct 11, 2026
1.1.0	Sep 29, 2026
1.0.0	Sep 29, 2026
0.12.1	Sep 27, 2026
0.12.0	Sep 27, 2026
0.11.0	Sep 26, 2026
0.9.3	Sep 13, 2026
0.9.2	Sep 11, 2026
0.6.2	Jul 24, 2026
0.6.0	Jul 15, 2026
0.5.2	Jul 14, 2026
0.4.5	Jul 7, 2026
0.4.4	Jul 2, 2026
0.4.3	Jun 30, 2026
0.4.2	Jun 18, 2026
0.4.1	Jun 15, 2026
0.4.0	Jun 14, 2026
0.3.16	Jun 10, 2026
0.3.15	Jun 9, 2026
0.3.14	Jun 8, 2026
0.3.13	Jun 8, 2026
0.3.12	Jun 8, 2026
0.3.11	Jun 5, 2026
0.3.10	May 28, 2026
0.3.8	May 27, 2026
0.3.7	May 14, 2026
0.3.6	May 7, 2026
0.3.2	Apr 28, 2026
0.3.1	Apr 24, 2026
0.3.0	Apr 17, 2026
0.2.9	Apr 14, 2026
0.2.8	Apr 13, 2026

STANDING

#10,211of 144,396 active serversTop 10%

Ranks ahead of 134,185 of 144,396 servers on MCP Toplist.

Recent momentum

+14GitHub stars since Apr 27 (+350%)

BADGE

Show your rank

Maintain this server? Add the live rank badge to your README — it updates automatically as the leaderboard changes.

Markdown

[![MCP Toplist](https://mcptoplist.com/badge/io.github.Lykhoyda%2Fask-llm.svg)](https://mcptoplist.com/server/io.github.Lykhoyda%2Fask-llm)

HTML

<a href="https://mcptoplist.com/server/io.github.Lykhoyda%2Fask-llm"><img src="https://mcptoplist.com/badge/io.github.Lykhoyda%2Fask-llm.svg" alt="MCP Toplist: Top 10% of 144,396" /></a>

Variants: append ?metric=score or ?metric=stars to the image URL.

FAQ

Frequently asked questions

Who maintains Ask Llm?: Ask Llm is maintained by Lykhoyda, which publishes 10 MCP servers (146 total versions) tracked on MCP Toplist.
Is Ask Llm listed on the Official MCP Registry?: Yes — Ask Llm is listed on the Official MCP Registry.
How many versions does Ask Llm have?: MCP Toplist tracks 33 versions of Ask Llm, most recently published on Oct 13, 2026.
Where can I find the source code for Ask Llm?: The source code for Ask Llm is hosted at github.com/Lykhoyda/ask-llm.

Used in projects

Do you run this server?

Community projects list the MCP servers behind real agents and apps. Publish yours and this page will link to it.

EXPLORE

All MCP Servers Official MCP Servers GitHub MCP Servers Best MCP Servers Most Active MCP Servers New MCP Servers Best New MCP Servers