A side-by-side look at the Frontier and Ask Gemini MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose Frontier for conversational ai work; choose Ask Gemini for conversational ai as a local process. You can also run both side by side in one mcpServers block.
ask-llm, multi-llm, ask-codex.Rows where the two servers differ are marked.
| Spec | F Frontier | |
|---|---|---|
| Category | Conversational AI | Conversational AI |
| Quality signal | 37/100 · Fair | 59/100 · Good |
| Install command | Not confirmed yet | Confirmed |
| Transport | — | Local subprocess (stdio) |
| Auth | Not declared | Not declared |
| Pricing | Not declared | Not declared |
| Required env vars | None listed | None listed |
| Verified owner | Community listing | Community listing |
| GitHub stars | — | 18 |
| Directory activity | 0 views 0 installs 0 upvotes | 0 views 0 installs 0 upvotes |
| Tools | Not listed | 14 |
| Full listing | View Frontier | View Ask Gemini |
No tool names declared yet. Check the project README from the listing page.
ask-llmUnified orchestrator: pick a provider per call, or fan out to every installed providermulti-llmSend one prompt to multiple providers in parallel; returns per-provider responses and usage in one callask-codexCodex CLI. GPT-6 Astra with Terra fallback. Omit `sessionId` for ephemeral use, or pass `sessionId: ""` first to persist and resumeask-claudeClaude Code CLI. `opus` (Opus 5.5) with Sonnet fallback; native sessions; Read/Glob/Grep-only workspace accessask-grokOne-shot Grok prompt through explicit `xai-api` (default) or `grok-cli`; exact harness model ID; no harness/model fallbackask-cursor-agentModel-neutral Cursor Agent harness: separate provider (`claude`, `codex`, `gemini`, `grok`) + exact Cursor catalog model verified against that family; read-only ask mode; no force/trust/spend changes or fallbackask-antigravityGoogle Antigravity (`agy`) for a subscription-backed second opinion. Experimental; one-shotask-ollamaLocal Ollama. Fully private, zero cost. Server-side conversation replay via `sessionIdask-geminiGemini CLI with `@` file syntax. 1M+ token context. Live progressive output via `stream-jsonask-gemini-editStructured OLD/NEW code edit blocks from Geminifetch-chunkRetrieve chunks from cached large responsesget-usage-statsPer-session token totals, fallback counts, breakdowns by provider/model. In-memory onlyPaste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.
No confirmed install command for Frontier yet — follow the setup steps linked from its listing page rather than a guessed package name.
{
"mcpServers": {
"ask-gemini": {
"command": "npx",
"args": [
"-y",
"@ask-llm/codex-mcp"
]
}
}
}