ollama-handoff
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| OLLAMA_URL | No | Base URL of the Ollama server | http://localhost:11434 |
| OLLAMA_NUM_CTX | No | Context window in tokens | 32768 |
| OLLAMA_TIMEOUT_S | No | Per-request timeout, seconds | 600 |
| OLLAMA_KEEP_ALIVE | No | How long to keep the model resident in VRAM | 30m |
| OLLAMA_DEFAULT_MODEL | No | Default model for handoffs | qwen2.5-coder:14b |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| ask_localA | Send a one-shot prompt to a local Ollama model and return the response. Use for any handoff where the cloud model's full reasoning isn't needed: drafts, boilerplate, simple extractions, formatting, quick lookups. Runs on the user's own GPU and consumes no cloud-LLM usage. Args: prompt: The task / question. model: Override the default model. system: Optional system prompt to shape behavior. |
| chat_localA | Multi-turn chat against a local Ollama model. Use when the handoff needs more than one turn of context. |
| summarize_localB | Summarize a block of text using the local model. Cheap offload for long files, logs, transcripts, or docs the cloud model doesn't need to fully ingest. Returns a concise structured summary. Args: text: The content to summarize. Can be very long (context window is configurable). focus: Optional focus hint, e.g. "errors and stack traces" or "API surface only". |
| code_review_localA | Quick first-pass code review using the local coder model. Catches obvious bugs, style issues, and risky patterns. Use as a cheap pre-filter before asking the cloud model for a deeper review. Args: diff_or_code: A unified diff or a code block to review. |
| draft_commit_message_localA | Draft a conventional-style commit message from a diff using the local model. Cheap and fast — good for routine commits where the cloud model's analysis isn't needed. Args:
diff: The output of |
| extract_localB | Extract specific information from a text block using the local model. Good for pulling structured data out of unstructured text — function names, URLs, error messages, TODO comments, etc. Args: text: The source text. what_to_extract: What to pull out, e.g. "all function definitions" or "every URL in the file". |
| list_modelsA | List the Ollama models available locally. |
| server_infoA | Return the server's effective configuration (model, context size, etc.). |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 8 tools
Each tool has a clearly distinct purpose: one-shot vs. multi-turn chat, code review, commit message drafting, extraction, summarization, model listing, and server info. No overlap.
Most tools follow the `<action>_local` pattern, but `list_models` and `server_info` deviate by lacking the `_local` suffix. All are snake_case and readable.
With 8 tools, the server covers a comprehensive set of common local offload tasks without overloading. The count is well-scoped for its purpose.
The tool set covers major offload scenarios: general queries, chat, code review, commit messages, extraction, and summarization. Minor gaps like model management or generic generation are absent but not critical for a handoff server.