RAG Document Server
by Vamshi9415
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GPU_CONCURRENCY | No | Max concurrent FAISS build/retrieval operations (GPU semaphore) | 2 |
| HUGGINGFACE_TOKEN | No | HuggingFace model access (for gated models) | |
| MCP_RATE_LIMIT_RPM | No | Per-user rate limit (requests/minute); global cap is 5× this value | 60 |
| MCP_REQUEST_TIMEOUT | No | Default tool timeout in seconds | 300 |
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
- 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/Vamshi9415/docrag-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server