gdrive-rag-mcp
by phamviet86
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GEMINI_API_KEY | No | API key for the Gemini embedding provider. | |
| OPENAI_API_KEY | No | API key for OpenAI-compatible endpoints when GOOGLE_DRIVE_RAG_EMBED_API_KEY_ENV=OPENAI_API_KEY. | |
| OPENROUTER_API_KEY | No | API key for OpenRouter when using an OpenAI-compatible endpoint with that provider. | |
| GOOGLE_DRIVE_FOLDER_ID | Yes | Root folder ID indexed by the worker; required to verify against the index and serve. | |
| GOOGLE_DRIVE_RAG_DB_PATH | No | Path to the shared SQLite index. | data/index.db |
| GOOGLE_DRIVE_RAG_EMBED_MODEL | No | Embedding model name; must match the indexed model. | gemini-embedding-001 |
| GOOGLE_DRIVE_SHARED_DRIVE_ID | No | Shared Drive ID when serving a Shared Drive corpus; still set GOOGLE_DRIVE_FOLDER_ID. | |
| GOOGLE_DRIVE_RAG_EMBED_DEVICE | No | Optional device for Sentence Transformers. | |
| GOOGLE_DRIVE_RAG_EMBED_BASE_URL | No | Base URL for OpenAI-compatible /embeddings endpoints. | |
| GOOGLE_DRIVE_RAG_EMBED_PROVIDER | No | Embedding provider used for query vectors. | gemini |
| GOOGLE_DRIVE_RAG_EMBED_BATCH_SIZE | No | Embedding batch size. | 32 |
| GOOGLE_DRIVE_RAG_EMBED_DIMENSIONS | No | Embedding dimensions; must match the index. | 768 |
| GOOGLE_DRIVE_RAG_EMBED_API_KEY_ENV | No | Name of the environment variable that holds the API key for the selected embedding provider. | GEMINI_API_KEY |
| GOOGLE_DRIVE_RAG_EVIDENCE_THRESHOLD | No | Minimum top score for sufficient evidence. | 0.35 |
| GOOGLE_DRIVE_RAG_PATH_FILTER_ENABLED | No | Enable the fail-closed path filtering policy for this service instance. | false |
| GOOGLE_DRIVE_RAG_EMBED_SEND_DIMENSIONS | No | Whether to send the optional dimensions field to OpenAI-compatible endpoints. | true |
| GOOGLE_DRIVE_RAG_EMBED_TIMEOUT_SECONDS | No | Hosted embedding request timeout in seconds. | 60 |
| GOOGLE_DRIVE_RAG_EMBED_QUERY_INPUT_TYPE | No | Optional provider-specific query input type. | |
| GOOGLE_DRIVE_RAG_PATH_ALLOW_PREFIXES_JSON | No | JSON array of active Drive-relative folder prefixes. | [] |
| GOOGLE_DRIVE_RAG_EMBED_DOCUMENT_INPUT_TYPE | No | Optional provider-specific document input type. | |
| GOOGLE_DRIVE_RAG_PATH_EXCLUDE_PREFIXES_JSON | No | JSON array of prefixes that override the allowlist. | [] |
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
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/phamviet86/google-drive-rag-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server