io.github.Michael-WhiteCapData/ollama-handoff MCP Server
io.github.Michael-WhiteCapData/ollama-handoff
What this kind of tool is for
- Hand your agent a structured way to call a model or an inference API.
- Compare outputs from two different providers on the same prompt.
- Wire retrieval, embeddings, or generation into an existing agent workflow.
How to compare servers like this
- Provider coverage:
- Match the tool's supported providers and models to the ones your project uses.
- Cost exposure:
- Model-backed tools spend real API budget; check how usage and limits are configured.
- Maintenance signal:
- The provider landscape shifts weekly; prefer tools updated within the last few months.
- Config surface:
- Prefer tools whose environment-variable or config keys are documented plainly.
This page carries your copy-paste config: pick your MCP client in the install section on this page and use the copy button.
What is the io.github.Michael-WhiteCapData/ollama-handoff MCP server?
Offload cheap work from your AI agent to a local Ollama model, at zero cloud cost.
How to install io.github.Michael-WhiteCapData/ollama-handoff
Copy-paste configuration for popular MCP clients.
OLLAMA_URLBase URL of the Ollama server.
OLLAMA_DEFAULT_MODELDefault model used for handoffs.
OLLAMA_NUM_CTXContext window in tokens.
OLLAMA_KEEP_ALIVEHow long to keep the model resident in VRAM.
OLLAMA_TIMEOUT_SPer-request timeout in seconds.
{
"mcpServers": {
"ollama-handoff": {
"command": "uvx",
"args": [
"ollama-handoff"
],
"env": {
"OLLAMA_URL": "<YOUR_OLLAMA_URL>",
"OLLAMA_DEFAULT_MODEL": "<YOUR_OLLAMA_DEFAULT_MODEL>",
"OLLAMA_NUM_CTX": "<YOUR_OLLAMA_NUM_CTX>",
"OLLAMA_KEEP_ALIVE": "<YOUR_OLLAMA_KEEP_ALIVE>",
"OLLAMA_TIMEOUT_S": "<YOUR_OLLAMA_TIMEOUT_S>"
}
}
}
}Related MCP servers
Query a folder of CSV / Parquet / JSON files with SQL — one queryable source, read-only.
Operate a k3s / Kubernetes cluster from your AI agent — safe-by-default MCP server.
CroweLM tiers and frontier engines by name, metered per Crowe Logic plan. Ask, list models, account.
View repository →
MidOS - MCP Community Library
Curated knowledge base for AI agents — 19K chunks, 121 skills, semantic search via MCP

WASM sandbox for MCP tools with enforced CPU/memory/I/O limits, WASI isolation, and attested execution records.

SandboxAPI
Execute code in 8 languages (Python, JS, TS, Go, Java, C++, C, Bash) in gVisor sandboxes.

