Archon-KB
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PGHOST | No | PostgreSQL host. | localhost |
| PGPORT | No | PostgreSQL port. | 5432 |
| PGUSER | No | PostgreSQL username. | postgres |
| PGDATABASE | No | PostgreSQL database name. | technical_kb |
| PGPASSWORD | No | PostgreSQL password. | postgres |
| PYTHONPATH | No | Python module search path for Archon-KB, used in MCP client configurations. | |
| EMBEDDING_DIM | No | Embedding vector dimensions. | 384 |
| EMBEDDING_MODEL | No | Model name or embedding provider. | local-semantic-384 |
| KB_RECOGNIZED_FOLDERS | No | Comma-separated analysis workspace folder names. |
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
} |
| logging | {} |
| prompts | {
"listChanged": true
} |
| resources | {
"subscribe": false,
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| lookup_technical_entityC | Zero-hallucination lookup for a specific technical identifier. Returns canonical properties, implementation methods, graph relationships, and source provenance. |
| search_technical_knowledgeC | 5-stage hybrid retrieval across the knowledge base: Combines exact identifier matching, lexical full-text (GIN), and pgvector cosine similarity via RRF. |
| get_kb_health_statusC | Returns the current health status, document counts, and integrity metrics of the Technical KB. |
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 3 tools
lookup_technical_entity and search_technical_knowledge both retrieve technical info, but the descriptions clearly separate exact-identifier canonical lookup from broad 5-stage hybrid search. get_kb_health_status is unambiguously distinct (operational metrics only).
All three follow a snake_case verb_noun pattern (get_/lookup_/search_ + object). The 'kb' abbreviation in get_kb_health_status is a minor deviation from the other two using full domain nouns, but the convention is still readable and predictable.
Three focused tools suit a read-only technical KB retrieval server: health, point lookup, and search cover the core surface without bloat. It sits near the thin edge, but each tool earns its place with a distinct role.
Read paths are well covered (search + exact lookup + health), but there is no way to enumerate or browse entities, list available entity types/document sets, or fetch related entities except via lookup. Agents hitting an unknown identifier must fall back to search, which is a notable gap for a KB server.