protogrid
Sign inAdd to your agent

Search / io.github.Lykhoyda/ask-llm

ask-llm

L0· runs locally

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

v1.2.1 · active · repository · descriptor JSON · versions

Runs on your machine: something must execute the package.Only local packages are published (npm, PyPI, OCI, …). The registry never executes them, so tools are unknown until you run it.
Quality–not scored
Trust86of 100
Packages1
Tools seen0

Connect

8 clients · secrets stay placeholders
{
  "mcpServers": {
    "ask-llm": {
      "command": "npx",
      "args": [
        "-y",
        "@ask-llm/[email protected]"
      ],
      "env": {
        "XAI_API_KEY": "${XAI_API_KEY}",
        "ASK_GROK_HARNESS": "xai-api",
        "ASK_GROK_REASONING_EFFORT": "high",
        "ASK_GROK_MAX_OUTPUT_TOKENS": "16384",
        "ASK_GROK_TIMEOUT_MS": "600000",
        "CURSOR_API_KEY": "${CURSOR_API_KEY}",
        "ASK_CURSOR_TIMEOUT_MS": "600000",
        "ASK_CLAUDE_MODEL": "opus",
        "ASK_CLAUDE_FALLBACK_MODEL": "sonnet",
        "ASK_CLAUDE_TIMEOUT_MS": "600000",
        "OLLAMA_HOST": "http://localhost:11434",
        "ASK_ANTIGRAVITY_TIMEOUT_MS": "300000",
        "ASK_ANTIGRAVITY_SANDBOX": "1",
        "GMCPT_TIMEOUT_MS": "300000",
        "GMCPT_LOG_LEVEL": "warn"
      }
    }
  }
}
claude mcp add ask-llm -e "XAI_API_KEY=${XAI_API_KEY}" -e "ASK_GROK_HARNESS=xai-api" -e "ASK_GROK_REASONING_EFFORT=high" -e "ASK_GROK_MAX_OUTPUT_TOKENS=16384" -e "ASK_GROK_TIMEOUT_MS=600000" -e "CURSOR_API_KEY=${CURSOR_API_KEY}" -e "ASK_CURSOR_TIMEOUT_MS=600000" -e "ASK_CLAUDE_MODEL=opus" -e "ASK_CLAUDE_FALLBACK_MODEL=sonnet" -e "ASK_CLAUDE_TIMEOUT_MS=600000" -e "OLLAMA_HOST=http://localhost:11434" -e "ASK_ANTIGRAVITY_TIMEOUT_MS=300000" -e "ASK_ANTIGRAVITY_SANDBOX=1" -e "GMCPT_TIMEOUT_MS=300000" -e "GMCPT_LOG_LEVEL=warn" -- npx -y @ask-llm/[email protected]
[mcp_servers.ask-llm]
command = "npx"
args = ["-y", "@ask-llm/[email protected]"]
env = { "XAI_API_KEY" = "${XAI_API_KEY}", "ASK_GROK_HARNESS" = "xai-api", "ASK_GROK_REASONING_EFFORT" = "high", "ASK_GROK_MAX_OUTPUT_TOKENS" = "16384", "ASK_GROK_TIMEOUT_MS" = "600000", "CURSOR_API_KEY" = "${CURSOR_API_KEY}", "ASK_CURSOR_TIMEOUT_MS" = "600000", "ASK_CLAUDE_MODEL" = "opus", "ASK_CLAUDE_FALLBACK_MODEL" = "sonnet", "ASK_CLAUDE_TIMEOUT_MS" = "600000", "OLLAMA_HOST" = "http://localhost:11434", "ASK_ANTIGRAVITY_TIMEOUT_MS" = "300000", "ASK_ANTIGRAVITY_SANDBOX" = "1", "GMCPT_TIMEOUT_MS" = "300000", "GMCPT_LOG_LEVEL" = "warn" }

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "ask-llm": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@ask-llm/[email protected]"
      ],
      "enabled": true,
      "environment": {
        "XAI_API_KEY": "{env:XAI_API_KEY}",
        "ASK_GROK_HARNESS": "xai-api",
        "ASK_GROK_REASONING_EFFORT": "high",
        "ASK_GROK_MAX_OUTPUT_TOKENS": "16384",
        "ASK_GROK_TIMEOUT_MS": "600000",
        "CURSOR_API_KEY": "{env:CURSOR_API_KEY}",
        "ASK_CURSOR_TIMEOUT_MS": "600000",
        "ASK_CLAUDE_MODEL": "opus",
        "ASK_CLAUDE_FALLBACK_MODEL": "sonnet",
        "ASK_CLAUDE_TIMEOUT_MS": "600000",
        "OLLAMA_HOST": "http://localhost:11434",
        "ASK_ANTIGRAVITY_TIMEOUT_MS": "300000",
        "ASK_ANTIGRAVITY_SANDBOX": "1",
        "GMCPT_TIMEOUT_MS": "300000",
        "GMCPT_LOG_LEVEL": "warn"
      }
    }
  }
}
{
  "mcpServers": {
    "ask-llm": {
      "command": "npx",
      "args": [
        "-y",
        "@ask-llm/[email protected]"
      ],
      "env": {
        "XAI_API_KEY": "${XAI_API_KEY}",
        "ASK_GROK_HARNESS": "xai-api",
        "ASK_GROK_REASONING_EFFORT": "high",
        "ASK_GROK_MAX_OUTPUT_TOKENS": "16384",
        "ASK_GROK_TIMEOUT_MS": "600000",
        "CURSOR_API_KEY": "${CURSOR_API_KEY}",
        "ASK_CURSOR_TIMEOUT_MS": "600000",
        "ASK_CLAUDE_MODEL": "opus",
        "ASK_CLAUDE_FALLBACK_MODEL": "sonnet",
        "ASK_CLAUDE_TIMEOUT_MS": "600000",
        "OLLAMA_HOST": "http://localhost:11434",
        "ASK_ANTIGRAVITY_TIMEOUT_MS": "300000",
        "ASK_ANTIGRAVITY_SANDBOX": "1",
        "GMCPT_TIMEOUT_MS": "300000",
        "GMCPT_LOG_LEVEL": "warn"
      }
    }
  },
  "deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=ask-llm&config=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"
}
{
  "servers": {
    "ask-llm": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@ask-llm/[email protected]"
      ],
      "env": {
        "XAI_API_KEY": "${XAI_API_KEY}",
        "ASK_GROK_HARNESS": "xai-api",
        "ASK_GROK_REASONING_EFFORT": "high",
        "ASK_GROK_MAX_OUTPUT_TOKENS": "16384",
        "ASK_GROK_TIMEOUT_MS": "600000",
        "CURSOR_API_KEY": "${CURSOR_API_KEY}",
        "ASK_CURSOR_TIMEOUT_MS": "600000",
        "ASK_CLAUDE_MODEL": "opus",
        "ASK_CLAUDE_FALLBACK_MODEL": "sonnet",
        "ASK_CLAUDE_TIMEOUT_MS": "600000",
        "OLLAMA_HOST": "http://localhost:11434",
        "ASK_ANTIGRAVITY_TIMEOUT_MS": "300000",
        "ASK_ANTIGRAVITY_SANDBOX": "1",
        "GMCPT_TIMEOUT_MS": "300000",
        "GMCPT_LOG_LEVEL": "warn"
      }
    }
  }
}
{
  "mcpServers": {
    "ask-llm": {
      "command": "npx",
      "args": [
        "-y",
        "@ask-llm/[email protected]"
      ],
      "env": {
        "XAI_API_KEY": "${XAI_API_KEY}",
        "ASK_GROK_HARNESS": "xai-api",
        "ASK_GROK_REASONING_EFFORT": "high",
        "ASK_GROK_MAX_OUTPUT_TOKENS": "16384",
        "ASK_GROK_TIMEOUT_MS": "600000",
        "CURSOR_API_KEY": "${CURSOR_API_KEY}",
        "ASK_CURSOR_TIMEOUT_MS": "600000",
        "ASK_CLAUDE_MODEL": "opus",
        "ASK_CLAUDE_FALLBACK_MODEL": "sonnet",
        "ASK_CLAUDE_TIMEOUT_MS": "600000",
        "OLLAMA_HOST": "http://localhost:11434",
        "ASK_ANTIGRAVITY_TIMEOUT_MS": "300000",
        "ASK_ANTIGRAVITY_SANDBOX": "1",
        "GMCPT_TIMEOUT_MS": "300000",
        "GMCPT_LOG_LEVEL": "warn"
      }
    }
  }
}
extensions:
  "ask-llm":
    enabled: true
    name: "ask-llm"
    type: stdio
    cmd: "npx"
    args:
      - "-y"
      - "@ask-llm/[email protected]"
    envs:
      "XAI_API_KEY": "${XAI_API_KEY}"
      "ASK_GROK_HARNESS": "xai-api"
      "ASK_GROK_REASONING_EFFORT": "high"
      "ASK_GROK_MAX_OUTPUT_TOKENS": "16384"
      "ASK_GROK_TIMEOUT_MS": "600000"
      "CURSOR_API_KEY": "${CURSOR_API_KEY}"
      "ASK_CURSOR_TIMEOUT_MS": "600000"
      "ASK_CLAUDE_MODEL": "opus"
      "ASK_CLAUDE_FALLBACK_MODEL": "sonnet"
      "ASK_CLAUDE_TIMEOUT_MS": "600000"
      "OLLAMA_HOST": "http://localhost:11434"
      "ASK_ANTIGRAVITY_TIMEOUT_MS": "300000"
      "ASK_ANTIGRAVITY_SANDBOX": "1"
      "GMCPT_TIMEOUT_MS": "300000"
      "GMCPT_LOG_LEVEL": "warn"
    timeout: 300

Placeholders to fill from your own secret store: ${XAI_API_KEY}, ${CURSOR_API_KEY}. The registry never accepts secret values.

This is a local package: the command runs on your machine.

Quality – / 100not scored

Not scored: fewer than three checks apply, usually because no remote answered a credential-free probe or the server is a local package.

protocoln/a · weight 25
  • n/a
    protocol.modern, protocol.stateless, protocol.transport, protocol.list_ttlno remote answered a protocol handshake (not probed yet, unreachable, or local-only)
authorizationn/a · weight 15
  • n/a
    auth.prm, auth.as_metadata, auth.cimdno remote uses OAuth
  • n/a
    auth.secret_in_urlno templated URL
tool hygienen/a · weight 30
  • n/a
    tools.descriptions, tools.description_length, tools.schemas, tools.annotations, tools.directory_hints, tools.token_cost, tools.api_dumptool list unknown (behind auth, not probed, or empty)
stabilityn/a · weight 15
  • n/a
    stability.changes, stability.rug_pulltool list unknown
dependenciesn/a · weight 15
  • n/a
    deps.known_vulns, deps.mcp_sdk_version, deps.resolvabledeps.dev does not know @ask-llm/[email protected]

Tool list unknown · checked 2026-10-20 10:35 UTC

Tool changes

No tool definition changes recorded. A server's first observation is its baseline; later probes record what changes.

Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. How it is computed.

Trust 86 / 100

duplicate-repo
provenance80
livenessn/a
freshness100
hygiene80

+repository +namespace-matches-repo ~liveness-unmeasured +updated-7d-ago -duplicate-repo(7 names)

Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed. How it is computed.

Dependencies

@ask-llm/[email protected] npmthis version is not known to the dependency resolver

Dependency graphs from deps.dev; advisories from OSV.dev, including the GitHub Advisory Database and the PyPI Advisory Database; all CC BY 4.0. The graph is what a clean install of this version resolves today; nothing was installed or run. How it is checked.

Endpoints

packageregistryversionruntimesecrets
@ask-llm/mcpnpm1.2.1–XAI_API_KEY, CURSOR_API_KEY

Tools (0)

No tools observed. Local packages are never executed by the registry.

Schemas: list_tools.

Also listed as

6 other active names share this repository: io.github.Lykhoyda/ask-antigravity, io.github.Lykhoyda/ask-claude, io.github.Lykhoyda/ask-codex, io.github.Lykhoyda/ask-gemini, io.github.Lykhoyda/ask-grok, io.github.Lykhoyda/ask-ollama

Similar MCP servers

  • agent-mcp-hubL0
    io.github.blackaxgit/agent-mcp-hub

    One MCP server bridging the Codex, Cursor, OpenCode, Claude, and Antigravity CLI agents

  • MANNAL0
    io.github.NSF-Simons-CosmicAI-Institute/manna

    MCP server for IVOA astronomical archives: NOIRLab Astro Data Lab, NRAO/ALMA, CADC, ESO, Gaia

  • mcp-server-google-antigravityL0
    io.github.TurkerYakup/mcp-server-google-antigravity

    MCP server exposing Google Antigravity (agy CLI / Gemini): jobs, codebase analysis, file tools.

  • ligo-mcpL0
    io.github.mrfentmen/ligo-mcp

    Keyless MCP server for LIGO gravitational-wave catalogs: events, masses, distances.

  • geminiL0
    io.github.PavelGuzenfeld/gemini

    MCP server that exposes Google Gemini as tools for Claude Code

  • imagine-mcpL0
    io.github.n24q02m/imagine-mcp

    MCP server for image/video understanding & generation (Gemini/OpenAI/Grok)

More from io.github.Lykhoyda

  • ask-antigravityL0
    io.github.Lykhoyda/ask-antigravity

    Bridge Claude with Google's Antigravity CLI (agy) for code review and second opinions

  • ask-claudeL0
    io.github.Lykhoyda/ask-claude

    Bridge Codex and other MCP clients with Anthropic Claude Code CLI for read-only second opinions

  • ask-codexL0
    io.github.Lykhoyda/ask-codex

    Bridge Claude with OpenAI Codex CLI for AI-to-AI collaboration, code review, and second opinions

  • ask-geminiL0
    io.github.Lykhoyda/ask-gemini

    Bridge Claude with Gemini CLI for AI-to-AI collaboration, code review, and second opinions

  • ask-grokL0
    io.github.Lykhoyda/ask-grok

    Consult Grok through xAI's metered API with exact model selection and no fallback

  • ask-ollamaL0
    io.github.Lykhoyda/ask-ollama

    Bridge Claude with local Ollama LLMs for private AI-to-AI collaboration — no API keys, fully local

Official server.json
{
  "name": "io.github.Lykhoyda/ask-llm",
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "version": "1.2.1",
  "packages": [
    {
      "version": "1.2.1",
      "transport": {
        "type": "stdio"
      },
      "identifier": "@ask-llm/mcp",
      "registryType": "npm",
      "environmentVariables": [
        {
          "name": "XAI_API_KEY",
          "format": "string",
          "isSecret": true,
          "description": "xAI API key for metered Grok requests; Ask LLM never enables billing or credits"
        },
        {
          "name": "ASK_GROK_HARNESS",
          "format": "string",
          "default": "xai-api",
          "description": "Explicit Grok harness: xai-api (default) or grok-cli; no failover"
        },
        {
          "name": "ASK_GROK_MODEL",
          "format": "string",
          "description": "Exact selected-harness model override (API default grok-4.7; CLI default grok-4.7; no fallback)"
        },
        {
          "name": "ASK_GROK_REASONING_EFFORT",
          "format": "string",
          "default": "high",
          "description": "Grok reasoning effort: low, medium, high, or xhigh (default: high)"
        },
        {
          "name": "ASK_GROK_MAX_OUTPUT_TOKENS",
          "format": "string",
          "default": "16384",
          "description": "xAI API output-token ceiling to bound accidental spend (default: 16384)"
        },
        {
          "name": "ASK_GROK_TIMEOUT_MS",
          "format": "string",
          "default": "600000",
          "description": "Timeout for xAI API requests in milliseconds (default: 600000)"
        },
        {
          "name": "CURSOR_API_KEY",
          "format": "string",
          "isSecret": true,
          "description": "Optional Cursor CLI credential for ask-cursor-agent; alternative to agent login"
        },
        {
          "name": "ASK_CURSOR_TIMEOUT_MS",
          "format": "string",
          "default": "600000",
          "description": "Timeout for model-neutral Cursor Agent harness calls (default: 600000)"
        },
        {
          "name": "ASK_CLAUDE_MODEL",
          "format": "string",
          "default": "opus",
          "description": "Default Claude model alias or full model name (default: opus)"
        },
        {
          "name": "ASK_CLAUDE_FALLBACK_MODEL",
          "format": "string",
          "default": "sonnet",
          "description": "Claude CLI fallback when Opus is overloaded or unavailable (default: sonnet)"
        },
        {
          "name": "ASK_CLAUDE_TIMEOUT_MS",
          "format": "string",
          "default": "600000",
          "description": "Timeout for Claude CLI execution in milliseconds (default: 600000 = 10 minutes)"
        },
        {
          "name": "OLLAMA_HOST",
          "format": "string",
          "default": "http://localhost:11434",
          "description": "Ollama server address (default: http://localhost:11434)"
        },
        {
          "name": "ASK_ANTIGRAVITY_TIMEOUT_MS",
          "format": "string",
          "default": "300000",
          "description": "Timeout for Antigravity (agy) execution in milliseconds (default: 300000 = 5 minutes)"
        },
        {
          "name": "ASK_ANTIGRAVITY_SANDBOX",
          "format": "string",
          "default": "1",
          "description": "Set to '0' to drop agy's --sandbox flag if it blocks --add-dir context reads (default: sandbox on)"
        },
        {
          "name": "GMCPT_TIMEOUT_MS",
          "format": "string",
          "default": "300000",
          "description": "Timeout for CLI execution in milliseconds (default: 300000 = 5 minutes)"
        },
        {
          "name": "GMCPT_LOG_LEVEL",
          "format": "string",
          "default": "warn",
          "description": "Log verbosity: debug, info, warn, error (default: warn)"
        }
      ]
    }
  ],
  "repository": {
    "url": "https://github.com/Lykhoyda/ask-llm",
    "source": "github"
  },
  "description": "Unified MCP server for Gemini, Codex, Claude, Grok, Ollama, and Antigravity"
}