ontology-rag-mcp
by Pawangunjkar
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MCP_HOST | No | Bind address for HTTP transport. | 0.0.0.0 |
| MCP_PORT | No | Port for streamable HTTP transport. | 8765 |
| SSH_HOST | No | Target Linux host for remote MCP deploy. Required if DEPLOY_PROVIDER is 'ssh'. | |
| SSH_PORT | No | SSH port. | 22 |
| LLM_MODEL | No | Model name for chat completions. | llama3 |
| SOLR_PORT | No | Host port for Solr container. | 8983 |
| JENKINS_URL | No | Jenkins server URL. Required if ORCHESTRATOR is 'jenkins'. | |
| LLM_API_KEY | No | API key (OpenAI, Azure, etc.). Not needed for Ollama. | |
| LLM_ENABLED | No | Enable LLM for answer synthesis and domain summaries. | false |
| RAG_PRODUCT | No | Collection prefix. Creates {product}-raw and {product}-rag. | petclinic |
| GITHUB_TOKEN | No | Enables private repo access. Never commit this value. | |
| JENKINS_USER | No | Jenkins username. Required if ORCHESTRATOR is 'jenkins'. | |
| LLM_BASE_URL | No | OpenAI-compatible API base URL. | http://localhost:11434/v1 |
| ORCHESTRATOR | No | Orchestrator: 'local' = CLI, 'jenkins' = Jenkins MCP orchestrator. | local |
| REPOS_CONFIG | No | Path to repos configuration file. | repos.yml |
| SSH_KEY_PATH | No | Path to SSH private key. | |
| SSH_PASSWORD | No | SSH password (or use key). | |
| SSH_USERNAME | No | SSH username. Required if DEPLOY_PROVIDER is 'ssh'. | |
| JENKINS_TOKEN | No | Jenkins API token. Required if ORCHESTRATOR is 'jenkins'. | |
| MCP_TRANSPORT | No | Transport type: 'streamable-http' or 'stdio'. | streamable-http |
| RAG_EMBED_DIM | No | Vector dimension (must match model). | 384 |
| RAG_FLOW_SEED | No | Inject flow/endpoint doc for vague flow questions. | true |
| SOLR_BASE_URL | No | Solr base URL (no trailing collection name). | http://localhost:8983/solr |
| RAG_COLLECTION | No | Override serving collection name. Defaults to {RAG_PRODUCT}-rag. | |
| DEPLOY_PROVIDER | No | Deploy provider: 'docker' = docker compose, 'ssh' = Linux SSH MCP deploy. | docker |
| RAG_EMBED_MODEL | No | Local sentence-transformers model. | BAAI/bge-small-en-v1.5 |
| RAG_MMR_ENABLED | No | Maximal Marginal Relevance diversity (cap chunks per class). | true |
| SOURCE_PROVIDER | No | Source provider: 'local' = GitPython clone, 'github' = GitHub MCP adapter (falls back to local). | local |
| INGEST_CACHE_DIR | No | Git clone cache + commit SHA store. | ./.ingest-cache |
| JENKINS_JOB_NAME | No | Pipeline job name. | ontology-rag-onboard |
| RAG_METHOD_LEVEL | No | Also index per-method chunks (in addition to class-level). | false |
| RAG_RERANK_MODEL | No | Reranker model name. | BAAI/bge-reranker-base |
| RAG_SKIP_PATTERNS | No | Comma-separated file/path patterns to skip during ingest. | target/,build/,.git/,node_modules/,*.class,*.jar,/test/,generated-sources/ |
| RAG_RERANK_ENABLED | No | Enable cross-encoder reranking (BAAI/bge-reranker-base). | false |
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/Pawangunjkar/ontology-rag-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server