Deadzone
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| DEADZONE_DB_CACHE | No | Override the `deadzone.db` cache dir. | |
| DEADZONE_ORT_CACHE | No | Override the ORT library cache dir. | |
| DEADZONE_DB_OFFLINE | No | Refuse any network call. Fails loudly if nothing is cached. Set by default in the container image (which ships `deadzone.db` baked). | |
| DEADZONE_HUGOT_CACHE | No | Override the model-weights cache dir. | |
| DEADZONE_ORT_LIB_PATH | No | Hand-positioned `libonnxruntime` path. Skips the download. | |
| DEADZONE_DB_AUTOUPDATE | No | Disable the boot-time DB freshness probe (the probe runs by default; `fetch-db` always probes regardless of this flag). |
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": true
} |
| logging | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_docsA | Search documentation snippets for a library. Filter by library via lib_id (base form like /hashicorp/terraform). Pass version alongside lib_id to pin to a specific version (e.g. v1.14); omit version to search across all indexed versions of the lib. version without lib_id is rejected. |
| search_librariesA | Resolve a free-text library name into a ranked list of (lib_id, version) candidates that can be passed to search_docs. Returns one entry per indexed (lib_id, version) pair — group by lib_id on the client to see the versions of the same library. Pass an empty name to list the most-indexed libraries by doc_count. |
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 2 tools
The two tools have clearly distinct purposes: search_docs retrieves documentation snippets by library ID and version, while search_libraries resolves free-text library names into candidate identifiers. There is no overlap in functionality.
Both tools follow a consistent verb_noun pattern with 'search_' prefix, making it predictable and easy to understand.
With only 2 tools, the set feels thin but not extreme. It covers the basic search workflow, though more tools could enhance depth.
Missing obvious operations like retrieving a specific document by ID, listing all libraries, or version management. The tool surface is incomplete for thorough documentation search.