scplus-mcp
by Cesar514
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| OLLAMA_HOST | No | Override Ollama host | |
| OLLAMA_API_KEY | No | Required only if your Ollama setup needs auth | |
| OPENAI_API_KEY | No | Fallback alias for API key | |
| OPENAI_BASE_URL | No | Fallback alias for base URL | https://api.openai.com/v1 |
| OLLAMA_CHAT_MODEL | No | Chat model used in generated config examples | nemotron-3-nano:4b-128k |
| OLLAMA_EMBED_MODEL | No | Ollama embedding model tag | qwen3-embedding:0.6b-32k |
| OPENAI_EMBED_MODEL | No | Fallback alias for embedding model | text-embedding-3-small |
| SCPLUS_EMBED_NUM_CTX | No | Pass num_ctx into Ollama embed options | |
| SCPLUS_EMBED_NUM_GPU | No | Pass num_gpu into Ollama embed options | |
| SCPLUS_EMBED_LOW_VRAM | No | Pass low_vram into Ollama embed options | |
| SCPLUS_EMBED_MAIN_GPU | No | Pass main_gpu into Ollama embed options | |
| SCPLUS_EMBED_PROVIDER | No | Select embedding provider mode: 'ollama' or 'openai' | ollama |
| SCPLUS_OPENAI_API_KEY | No | Preferred OpenAI-compatible API key when provider is 'openai' | |
| SCPLUS_PARENT_POLL_MS | No | Parent-process polling interval | |
| SCPLUS_EMBED_NUM_BATCH | No | Pass num_batch into Ollama embed options | |
| SCPLUS_IDLE_TIMEOUT_MS | No | Idle shutdown timeout for MCP process | |
| SCPLUS_OPENAI_BASE_URL | No | Preferred OpenAI-compatible base URL | https://api.openai.com/v1 |
| SCPLUS_EMBED_BATCH_SIZE | No | Embedding batch size, clamped in code | 8 |
| SCPLUS_EMBED_NUM_THREAD | No | Pass num_thread into Ollama embed options | |
| SCPLUS_EMBED_CHUNK_CHARS | No | Chunk chars before vector merge, clamped in code | 2000 |
| SCPLUS_OPENAI_EMBED_MODEL | No | Preferred OpenAI-compatible embedding model | text-embedding-3-small |
| SCPLUS_MAX_EMBED_FILE_SIZE | No | Max file size for embed-aware search paths | |
| SCPLUS_SCAN_MAX_MS_PER_TICK | No | Max scanner milliseconds per tick | 100 |
| SCPLUS_SCAN_STAT_CONCURRENCY | No | Max concurrent file stat calls per scanner tick | 16 |
| SCPLUS_SCAN_MAX_DIRS_PER_TICK | No | Max directories scanned per bounded watcher tick | 32 |
| SCPLUS_SCAN_MAX_FILES_PER_TICK | No | Max files fingerprinted per bounded watcher tick | 256 |
| SCPLUS_SCAN_RESCAN_INTERVAL_MS | No | Scanner tick interval cap used while watching | 1000 |
| SCPLUS_WATCH_EVENT_PATH_SAMPLE | No | Max changed paths included in one streamed event payload | 100 |
| SCPLUS_WATCH_MAX_PENDING_PATHS | No | Max detailed pending paths before escalating to full rebuild | 5000 |
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/Cesar514/scplus-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server