knowledge-gateway-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| KNOWLEDGE_GATEWAY_SKILLS_ROOT | Yes | Path to the Pi skills root directory (equivalent to --skills-root). | |
| KNOWLEDGE_GATEWAY_DOCUMENTATION | Yes | Name of the Scribery documentation to use (equivalent to --documentation). | |
| KNOWLEDGE_GATEWAY_SCRIBERY_API_KEY | Yes | API key for the Scribery provider (equivalent to --api-key). | |
| KNOWLEDGE_GATEWAY_SCRIBERY_COMMAND | Yes | Path to the Scribery MCP server executable (equivalent to --scribery-command). | |
| KNOWLEDGE_GATEWAY_SCRIBERY_PROFILE | Yes | Scribery provider profile name (equivalent to --profile). | |
| KNOWLEDGE_GATEWAY_SCRIBERY_BASE_URL | No | Base URL for the Scribery provider (optional). | |
| KNOWLEDGE_GATEWAY_SCRIBERY_RERANK_MODEL | No | Reranking model to use (optional). | |
| KNOWLEDGE_GATEWAY_SCRIBERY_RERANK_INSTRUCTION | No | Reranking instruction to use (optional). |
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": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_skillsA | Search within local library of skills. Returns relevant candidates; it cannot list the complete skill catalog. Call load_skill for a relevant match. |
| load_skillA | Load the complete skill for an exact skill name returned by search_skills. |
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
search_skills handles discovery by returning candidate matches, while load_skill retrieves the full content for a specific skill name. Their purposes are clearly separated and complementary.
Both tools use the same verb_noun snake_case convention, with search_skills and load_skill being predictable and consistent. The naming clearly indicates the action and target resource.
Two tools is slightly below the typical range, but the server is intentionally scoped to a simple search-and-retrieve workflow. Each tool earns its place and there is no redundant surface.
For a read-only skill library gateway, the discover-then-retrieve flow is complete: search_skills finds relevant candidates and load_skill retrieves the full skill. No create, update, or delete operations are implied by the stated purpose.