VeloxRAG
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| RAG_MCP_TOKEN | No | An agent key carrying the 'retrieve' capability. Set this when local trusted auth is switched off. | |
| RAG_MCP_BASE_URL | No | The base URL of the VeloxRAG API. Set this when the service is not at the default http://127.0.0.1:8000, including when RAG_API_HOST_PORT has been overridden. | http://127.0.0.1:8000 |
| RAG_MCP_KNOWLEDGE_BASE | No | The ID of the knowledge base to use. Required only when the service holds more than one knowledge base; with exactly one it resolves automatically, and with several it refuses to guess. |
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_memoryA | Search indexed memory and return the passages that match. Prefer a specific question over keywords. Retrieving more than you need and picking among them yourself works better than trusting the first result: the ranking is vector similarity, which cannot tell that a passage merely repeats the question. Leave rerank off unless this service has a rerank profile configured — the default setup has none, and asking for it fails with RERANK_NOT_CONFIGURED. |
| read_documentA | Read a document's text around a character range, to see what a search result was cut off from. Pass the document_id and the source.start_offset / source.end_offset of a passage, widened by a few hundred characters on each side. Offsets past either end are clamped rather than refused, and total_codepoints tells a clamped range from an exhausted one. |
| list_documentsB | List what is indexed, so a search can be narrowed or a gap in the memory can be recognised rather than guessed at. |
| memory_statusA | Report which knowledge base this server is bound to and whether the service can answer searches right now. |
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 4 tools
Each tool occupies a distinct role: status readiness, document inventory, passage search, and context reading. There is no real overlap between searching and reading, since read_document is explicitly tied to expanding a search result's context.
Most tools use verb_noun snake_case: list_documents, search_memory, read_document. memory_status breaks the verb pattern as a noun_noun status check, but the naming style is otherwise uniform and clear.
Four tools is a tight, well-scoped set for a read-oriented RAG memory server, and each one has a clear purpose in the search/inspect workflow. No tool feels redundant or missing at the count level.
The retrieval/inspection workflow is closed: an agent can check readiness, list what is indexed, search, and read around any hit. Ingestion and deletion are absent, but they appear to be outside this server's read-only scope rather than a dead end in its described workflow.