Claude-Code MCP Runner
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 | {} |
| logging | {} |
| completions | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| run_agentB | Exécute une commande sur l'agent Claude configuré via CLI |
| create_agentB | Crée un nouvel agent (Prompt + Config) compatible avec ce runner |
| list_agentsA | Liste tous les agents disponibles. Option 'details=true' pour voir la config complète. |
| delete_agentA | Supprime définitivement un agent (Prompt et Config) |
| update_agent_configB | Modifie la configuration technique d'un agent (Modèle, Serveurs MCP, Variables d'environnement) |
| create_promptA | Crée ou écrase un fichier prompt Markdown (Persona) |
| edit_promptC | Modifie un prompt existant en remplaçant un bloc de texte spécifique |
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 7 tools
Each tool targets a distinct operation: agent creation vs prompt creation, agent deletion, prompt editing, listing agents, running agents, and config updating. The descriptions clearly differentiate them, so no ambiguity.
All tool names follow a consistent verb_noun pattern in snake_case (e.g., create_agent, edit_prompt, run_agent), making them predictable and easy to understand.
With 7 tools, the server covers the essential operations for managing and running agents without being overly narrow or bloated. The number fits the scope well.
The tool set covers create, read, update, delete for agents and prompts, plus execution. A minor gap is the lack of a dedicated get_agent tool (though list_agents with details=true partly covers it), but overall the surface is solid.