rostra
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| ROSTRA_CONFIG | No | Path to the configuration file. Overrides the default config locations (XDG_CONFIG_HOME/rostra/config.yaml, ~/.config/rostra/config.yaml, or the packaged config.example.yaml). | |
| XDG_DATA_HOME | No | Base directory for data files. Rostra looks for rostra under this path when ROSTRA_DATA_HOME is not set. | |
| XDG_CONFIG_HOME | No | Base directory for configuration files. Rostra looks for rostra/config.yaml under this path when ROSTRA_CONFIG is not set. | |
| ROSTRA_DATA_HOME | No | Directory where Rostra writes its SQLite database, transcripts, and model files. Overrides the default data locations (XDG_DATA_HOME/rostra, ~/.local/share/rostra). |
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
} |
| resources | {
"subscribe": true,
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| start_deliberationC | Submit a durable deliberation job |
| list_deliberationsC | List durable deliberation jobs |
| get_deliberationC | Get one job by ID or idempotency key |
| tail_deliberationC | Read job events after a sequence cursor |
| cancel_deliberationC | Request idempotent job cancellation |
| resume_deliberationC | Resolve a recovery-required uncertain attempt |
| list_modelsB | List enabled configured models |
| set_session_modelsA | Set default models by adapter for this server process. The overrides are process-scoped, so every client connected to the same HTTP endpoint shares them. |
| get_quality_metricsB | Read durable model quality metrics |
| query_decisionsC | Query decisions in the current workspace |
| list_stale_decisionsC | List stale decisions in the current workspace |
| record_decision_outcomeC | Append an observed decision outcome |
| review_decision_changeC | Review a Git change against workspace decisions |
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 13 tools
Most tools have clearly distinct purposes: deliberation lifecycle, decision queries, model management, and quality metrics are separated. A few query-style tools like list_deliberations, query_decisions, and list_stale_decisions could be confused at first glance, but their descriptions clarify jobs versus workspace decisions and stale subsets.
All tool names follow a consistent snake_case verb_noun pattern: start_deliberation, list_models, query_decisions, record_decision_outcome, etc. Pluralization is logical based on whether the tool returns multiple items or a single resource.
Thirteen tools is well within the ideal range for this server's scope. The count feels balanced across deliberation job lifecycle, decision workspace operations, and model/quality configuration without unnecessary redundancy.
The deliberation lifecycle is well covered with start, list, get, tail, cancel, and resume, and decision operations include query, stale detection, outcome recording, and change review. Minor gaps exist, such as no explicit update or delete operations for decisions and no persistent model configuration, but these are workable.