grounding-ai
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| AGENTS_DIR | Yes | Directory of agent YAML files. Can point outside the repo if you keep agents in a separate repo. | |
| CORPUS_DIR | Yes | Root containing _index.json and <slug>/chunks/ (e.g., ./corpus or ~/Documents/Corpora/corpus) | |
| EMBEDDINGS_DIR | Yes | Root containing <agent>/_embeddings.faiss and _chunk_map.json |
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
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_corpusA | Search the agent's corpus for relevant documents using semantic similarity. Returns chunks from ingested PDFs, EPUBs, and documents that match the query. Use this to find information in your knowledge base before answering questions. |
| list_corpus_agentsA | List all agents that have corpus embeddings available for search. |
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 entirely distinct purposes: listing agents vs. searching the corpus. There is no overlap or ambiguity.
Both tools follow a consistent verb_noun pattern: list_corpus_agents and search_corpus, making the naming predictable.
With only two tools, the server feels under-scoped for a typical grounding AI service. While it covers basic search and agent listing, more tools would be expected for a complete experience.
The server lacks essential tools for managing the corpus, such as adding or removing documents or agents. This creates significant gaps for agents needing to update or maintain the knowledge base.