openmemory-rag-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| OPENMEMORY_URL | No | URL of the OpenMemory backend server | http://localhost:8080 |
| OPENMEMORY_USER_ID | No | User ID for the knowledge base (optional, used for scoping) |
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 | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| import_fileA | Import a local file into OpenMemory RAG knowledge base. Supports PDF, DOCX, TXT, MD, HTML files. |
| import_urlA | Import content from a URL into OpenMemory RAG knowledge base |
| import_textA | Import raw text content into OpenMemory RAG knowledge base |
| search_knowledgeB | Search the OpenMemory RAG knowledge base |
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
The three import tools are clearly distinguished by source type (file, URL, raw text), and search_knowledge is obviously the retrieval counterpart. There is no meaningful overlap or ambiguity among these tools.
All tools follow a consistent verb_noun pattern: import_file, import_url, import_text, search_knowledge. The naming convention is uniform and predictable.
Four tools is well-scoped for an RAG knowledge base focused on ingestion and retrieval. Each tool covers a distinct and necessary operation without redundancy or bloat.
The core workflow of adding knowledge via three input types and searching it is covered. Minor gaps exist, such as no list, delete, or clear knowledge base operations, but they are not essential to the primary import-and-search purpose.