Other · Local MCP server
Ask Ollama
Bridge Claude with local Ollama LLMs for private AI-to-AI collaboration — no API keys, fully local.
What the MCP Registry states
The entry as published to the official MCP Registry (read 2026-10-04), latest version.
- Registry name
io.github.Lykhoyda/ask-ollama- Version
- 0.7.0
- Status
- Active
- Category
- other
- Transport
- stdio (local process)
- Package
- npm
- Published
- 2026-09-27
- Updated
- 2026-09-27
- Publisher
- Lykhoyda (GitHub) · 7 servers with pages here
- Listed under
- Ollama MCP servers
- Repository
- github.com/Lykhoyda/ask-llm
- Source
- Registry API entry
Packages
| Registry | Package | Version | Transport |
|---|---|---|---|
| npm | @ask-llm/ollama-mcp | 0.7.0 | stdio |
How to connect Ask Ollama
Ask Ollama runs locally from a Node.js package published to the npm registry: @ask-llm/ollama-mcp version 0.7.0. It speaks MCP over stdio, so the client starts it as a program and talks to it through standard input and output. It needs Node.js; clients usually start it with npx — the usual command is npx -y @ask-llm/ollama-mcp@0.7.0. It reads these environment variables: OLLAMA_HOST, GMCPT_TIMEOUT_MS and GMCPT_LOG_LEVEL; set them in the client's configuration for this server.
In the mcpServers JSON format that many desktop and editor MCP clients read, the entry looks like this (placeholders in angle brackets):
{
"mcpServers": {
"ask-ollama": {
"command": "npx",
"args": [
"-y",
"@ask-llm/ollama-mcp@0.7.0"
],
"env": {
"OLLAMA_HOST": "<value>",
"GMCPT_TIMEOUT_MS": "<value>",
"GMCPT_LOG_LEVEL": "<value>"
}
}
}
}Derived from the registry entry, not tested here. What the server does, and on what terms, is set by its publisher; check its repository or website before giving it access to your accounts or files. How to add an MCP server to an assistant · Before you connect
More from Lykhoyda (GitHub)
| Server | Runs |
|---|---|
| Ask AntigravityBridge Claude with Google's Antigravity CLI (agy) for code review and second opinions. | Local · stdio |
| Ask ClaudeBridge Codex and other MCP clients with Anthropic Claude Code CLI for read-only second opinions. | Local · stdio |
| Ask CodexBridge Claude with OpenAI Codex CLI for AI-to-AI collaboration, code review, and second opinions. | Local · stdio |
| Ask GeminiBridge Claude with Gemini CLI for AI-to-AI collaboration, code review, and second opinions. | Local · stdio |
| Ask GrokConsult Grok through xAI's metered API with exact model selection and no fallback. | Local · stdio |
| Ask LlmUnified MCP server for Gemini, Codex, Claude, Grok, Ollama, and Antigravity. | Local · stdio |
More other servers
| Server | Runs |
|---|---|
| Ask HelenaOfficial answers about Helena Bioinformatics and its products, with citations to public sources. | Remote · HTTP |
| Ask JevEvaluate state with typed choice, score, and probability questions. | Remote · HTTP |
| Ask MeAsk about an operator's work, reusable patterns, availability and offer. Typed tools, eval-gated. | Remote · HTTP |
| Ask XverumFind and enrich people from 750M professional profiles, with Next Move Signal job-change scores. | Remote & Local · HTTP, stdio |
| ask-oginoQuery Shunki Ogino's public profile: his thesis, the tools he builds, and his writing. | Remote · HTTP |
| ask10aisIndependent measurements of how 12 AI models answer brand questions in Chinese and English. | Remote · HTTP |
| AskAiRankHow ChatGPT, Claude, Perplexity and Gemini mention your brand: visibility, mentions, competitors. | Remote · HTTP |