RAG MCP Server
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
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| injection_ragC | Analyse du projet complet + prépare et injecte les données automatiquement (Phase 0 → RAG) |
| add_observationsB | Add new observations to existing entities in the knowledge graph |
| create_entitiesB | Create multiple new entities in the knowledge graph |
| create_relationsB | Create multiple new relations between entities in the knowledge graph. Relations should be in active voice |
| delete_entitiesA | Delete multiple entities and their associated relations from the knowledge graph |
| delete_observationsB | Delete specific observations from entities in the knowledge graph |
| delete_relationsA | Delete multiple relations from the knowledge graph |
| manage_projectsC | Gérer et lister les projets indexés |
| open_nodesC | Open specific nodes in the knowledge graph by their names |
| read_graphC | Read the entire knowledge graph |
| search_codeC | Recherche sémantique dans le code indexé avec options RAG |
| search_nodesC | Search for nodes in the knowledge graph based on a query |
| update_projectC | Mettre à jour l'indexation d'un projet (indexation incrémentale) avec options RAG |
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 distinct purposes centered around knowledge graph operations, but there is some overlap between 'search_nodes' and 'search_code' that could cause confusion. Additionally, 'injection_rag' and 'update_project' both involve RAG indexing but differ in scope, which might lead to misselection if not carefully described.
The naming is inconsistent with a mix of snake_case English verbs (e.g., 'add_observations', 'create_entities') and French terms (e.g., 'injection_rag', 'manage_projects'), and some tools use different verb styles like 'open_nodes' vs. 'read_graph'. This lack of a predictable pattern reduces clarity and usability.
With 13 tools, the count is reasonable for a RAG and knowledge graph server, covering core operations like CRUD for entities, relations, and observations, as well as project management and search. It's slightly on the higher side but still well-scoped for the domain.
The tool set provides good coverage for knowledge graph management and RAG operations, including create, read, update, and delete functions for entities, relations, and observations. Minor gaps exist, such as no explicit tool for updating entities or relations, but agents can likely work around this using deletion and recreation.