governed-rag-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GOVERNED_RAG_INDEX | No | SQLite index path. | data/knowledge.sqlite |
| OLLAMA_EMBEDDINGS_URL | No | Ollama embeddings endpoint. | http://127.0.0.1:11434/api/embeddings |
| OLLAMA_EMBEDDING_MODEL | No | Ollama model name. | nomic-embed-text |
| GOVERNED_RAG_CLIENT_PROFILE | No | Process-wide ACL profile. Missing, empty, or unknown values resolve to restricted. | restricted |
| OLLAMA_EMBEDDING_DIMENSIONS | No | Expected Ollama vector dimensions. | 768 |
| GOVERNED_RAG_HASH_DIMENSIONS | No | Demo hashing-vector dimensions. | 64 |
| GOVERNED_RAG_EMBEDDING_PROVIDER | No | hash or ollama; unknown values currently select hash. | hash |
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 |
|---|---|
| search_knowledgeA | Search governed knowledge. Low-confidence context is removed in strict mode. |
| list_knowledge_sourcesA | List source classes and chunk counts without returning chunk text. |
| rag_statusA | Return safe aggregate health and telemetry without query or chunk text. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| Governed RAG capabilities | Machine-readable, non-sensitive description of this server's real capabilities. |
TDQS
Scored across 3 tools
Each tool has a distinct purpose: listing source metadata, checking system status, and performing search. There is no overlap or ambiguity between them.
Two tools use verb_noun naming (list_knowledge_sources, search_knowledge), while rag_status follows a noun_noun pattern. The inconsistency is minor and does not hinder readability.
Three tools is a reasonable count for a focused RAG server that provides search and monitoring capabilities. While on the small side, it is neither too sparse nor overwhelming.
The surface covers core operations: listing sources, searching, and checking status. Missing management operations like adding/removing sources may be out of scope for a governed read-only interface.