io.github.dbhat93/grounded
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GROUNDED_MCP_MODE | No | Set to 'hybrid' to enable semantic retrieval. Defaults to routed + lexical (instant start, no model download, no egress). | lexical |
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
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| grounded_answerA | Answer a product, integration, security, or commercial question from vetted, cited knowledge, or refuse. Returns EITHER a grounded answer, carrying a live-vs-roadmap status label (GA / BETA / ROADMAP / NOT SUPPORTED / BATTLE CARD) and a source citation, OR an explicit refusal when nothing is vetted matches. It never fabricates and never presents a roadmap item as live. Call this instead of answering such a question yourself. If it refuses, do not guess: follow up in writing. |
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 1 tool
With only one tool, there is no possibility of confusing it with another. The tool's purpose is clearly defined and self-contained.
A single tool cannot exhibit naming inconsistencies. 'grounded_answer' is descriptive and follows a readable pattern.
One tool feels thin for most servers, but the narrow scope of grounded question-answering justifies a minimal surface. It falls into the borderline category.
The tool covers the full domain of answering from vetted knowledge, including refusals and citations. There are no obvious missing operations for this purpose.