Ask Gemini vs Ollama Handoff
A side-by-side look at the Ask Gemini and Ollama Handoff MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose Ask Gemini for conversational ai work as a local process; choose Ollama Handoff for conversational ai as a local process. You can also run both side by side in one mcpServers block.
Which MCP server should you choose?
Choose Ask Gemini when
- You need dedicated capabilities in the Conversational AI domain.
- You prefer a local stdio subprocess transport.
- You want tools like
ask-codex, ask-codex-edit, ping.
Choose Ollama Handoff when
- You need dedicated capabilities in the Conversational AI domain.
- You prefer a local stdio subprocess transport.
- Its auth model fits you: No auth required.
- You have the keys it needs:
OLLAMA_URL, OLLAMA_DEFAULT_MODEL, OLLAMA_NUM_CTX, OLLAMA_KEEP_ALIVE, OLLAMA_TIMEOUT_S. - You want tools like
ask_local, chat_local, summarize_local.
Feature & specification comparison
Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Conversational AI | Conversational AI |
| Quality signal | 63/100 · Good | 41/100 · Fair |
| Install command | Confirmed | Confirmed |
| Transport | Local subprocess (stdio) | Local subprocess (stdio) |
| Auth | Not declared | No auth required |
| Pricing | Not declared | Free |
| Required env vars | None listed | OLLAMA_URLOLLAMA_DEFAULT_MODELOLLAMA_NUM_CTXOLLAMA_KEEP_ALIVEOLLAMA_TIMEOUT_S |
| Verified owner | Community listing | Community listing |
| GitHub stars | 18 | 3 |
| Directory activity | 1 views 0 installs 0 upvotes | 3 views 0 installs 0 upvotes |
| Tools | 4 | 8 |
| Full listing | View Ask Gemini | View Ollama Handoff |
Tools & capabilities
Ask Gemini tools 4
ask-codexSend a prompt to OpenAI Codex CLI (defaults to gpt-6-astra with automatic fallback on quota errors). Use for code review, second opinions, analysis, and AI-to-AI collaboration. Do not override the model parameter unless the user explicitly asks. Returns both human-readable text and a structured response (provider, model, sessionId, usage) via outputSchema. Calls are ephemeral by default; pass sessionId: "" on the first call to persist its Codex thread_id, then pass the returned sessionId on follow-up calls to continue the conversation.ask-codex-editSend a code edit request to OpenAI Codex CLI and get structured search/replace edit blocks back (via codex --output-schema). Codex reads the existing files (read-only) and proposes precise, applyable changes for Claude to apply. Use this when you want Codex to suggest specific code modifications to existing files rather than just analysis. Mirrors ask-gemini-edit.pingTest connectivity with the MCP serverget-usage-statsGet the current MCP server's session usage stats: total LLM calls, token totals (input/output/thinking/cached), wall time, and breakdowns per provider and per model. No data leaves your machine — counts are tracked in-memory for the lifetime of the server process. Returns both human-readable markdown and a structured JSON snapshot via outputSchema.
Ollama Handoff tools 8
ask_localA single prompt with an optional system instructionchat_localA conversation with explicit message historysummarize_localSummaries of supplied text, optionally focused on a topiccode_review_localInitial review of supplied code or a diffdraft_commit_message_localA commit message from a supplied diffextract_localExtracting items such as URLs, names, or error codeslist_modelsDiscovering installed Ollama modelsserver_infoInspecting effective server configuration
Ready-to-paste client configs
Paste 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.
Ask Gemini
{
"mcpServers": {
"ask-gemini": {
"command": "npx",
"args": [
"-y",
"@ask-llm/codex-mcp"
]
}
}
}
Ollama Handoff
{
"mcpServers": {
"michael-whitecapdata-ollama-handoff": {
"command": "uvx",
"args": [
"ollama-handoff@0.1.3"
],
"env": {
"OLLAMA_URL": "YOUR_OLLAMA_URL_HERE",
"OLLAMA_DEFAULT_MODEL": "YOUR_OLLAMA_DEFAULT_MODEL_HERE",
"OLLAMA_NUM_CTX": "YOUR_OLLAMA_NUM_CTX_HERE",
"OLLAMA_KEEP_ALIVE": "YOUR_OLLAMA_KEEP_ALIVE_HERE",
"OLLAMA_TIMEOUT_S": "YOUR_OLLAMA_TIMEOUT_S_HERE"
}
}
}
}
Frequently asked questions
Ask Gemini is categorized under Conversational AI and uses a local stdio subprocess. Ollama Handoff belongs to Conversational AI and uses a local stdio subprocess. Pick Ask Gemini for conversational ai work and Ollama Handoff for conversational ai.
Copy the mcpServers block from the config section on this page into your client's config (for example claude_desktop_config.json or ~/.cursor/mcp.json), then fully restart the client.
Ask Gemini has no declared pricing — check the project's own site. Ollama Handoff is listed as free. Auth: no auth required. If a server needs environment variables such as API keys, define them under the env key in your client's MCP config.
Yes. MCP clients support multiple servers: add ask-gemini and michael-whitecapdata-ollama-handoff as separate keys in the same mcpServers object, and your assistant will call tools from either one.
On AllMCPs, Ask Gemini has a quality signal of 63/100 (Good) with 1 views, 0 installs and 18 GitHub stars. Ollama Handoff has 41/100 (Fair) with 3 views, 0 installs and 3 GitHub stars.