genesis-ai-bridge
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| bridge_healthB | Prüft Bridge, Ollama und optionale Provider read-only. |
| ollama_modelsB | Listet installierte Ollama-Modelle und wählt eine sichere Empfehlung. |
| run_shared_fileC | Prüft eine Datei, ein ZIP oder ein rekursives Verzeichnis mit Ollama und optional OpenClaw/Anthropic. Pfad oder UTF-8-Text angeben. |
| bridge_doctorB | Führt eine read-only Diagnose aus; Fehler/Warnungen werden nicht verschwiegen. |
| propose_correctionsB | Erzeugt nach einer Analyse nur einen Korrekturvorschlag. Es werden noch keine Dateien verändert. |
| apply_correctionsA | Wendet einen vorher angezeigten Vorschlag nur bei confirmed=true in einem neuen Korrekturordner an. |
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 6 tools
bridge_health and bridge_doctor both perform read-only health/diagnostics, creating potential confusion about which to use. The other tools are distinct in purpose, but this overlap reduces clarity.
All tools use snake_case, but the naming pattern is mixed: some are verb_noun (run_shared_file, propose_corrections, apply_corrections) while others are noun-like (bridge_health, bridge_doctor, ollama_models). This inconsistency makes the set less predictable.
With 6 tools, the server is well-scoped for its purpose—health checks, model listing, analysis, and correction workflow. Each tool has a clear role, and the count is within the ideal range.
The core workflow (check health, list models, run analysis, propose corrections, apply corrections) is covered, but there is no tool to retrieve past proposals or correction history, which is a minor gap.