Skip to main content
Glama
Pawangunjkar

ontology-rag-mcp

by Pawangunjkar
OverviewSchemaRelated ServersScoreDiscussions
Python
Hybrid

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
MCP_HOSTNoBind address for HTTP transport.0.0.0.0
MCP_PORTNoPort for streamable HTTP transport.8765
SSH_HOSTNoTarget Linux host for remote MCP deploy. Required if DEPLOY_PROVIDER is 'ssh'.
SSH_PORTNoSSH port.22
LLM_MODELNoModel name for chat completions.llama3
SOLR_PORTNoHost port for Solr container.8983
JENKINS_URLNoJenkins server URL. Required if ORCHESTRATOR is 'jenkins'.
LLM_API_KEYNoAPI key (OpenAI, Azure, etc.). Not needed for Ollama.
LLM_ENABLEDNoEnable LLM for answer synthesis and domain summaries.false
RAG_PRODUCTNoCollection prefix. Creates {product}-raw and {product}-rag.petclinic
GITHUB_TOKENNoEnables private repo access. Never commit this value.
JENKINS_USERNoJenkins username. Required if ORCHESTRATOR is 'jenkins'.
LLM_BASE_URLNoOpenAI-compatible API base URL.http://localhost:11434/v1
ORCHESTRATORNoOrchestrator: 'local' = CLI, 'jenkins' = Jenkins MCP orchestrator.local
REPOS_CONFIGNoPath to repos configuration file.repos.yml
SSH_KEY_PATHNoPath to SSH private key.
SSH_PASSWORDNoSSH password (or use key).
SSH_USERNAMENoSSH username. Required if DEPLOY_PROVIDER is 'ssh'.
JENKINS_TOKENNoJenkins API token. Required if ORCHESTRATOR is 'jenkins'.
MCP_TRANSPORTNoTransport type: 'streamable-http' or 'stdio'.streamable-http
RAG_EMBED_DIMNoVector dimension (must match model).384
RAG_FLOW_SEEDNoInject flow/endpoint doc for vague flow questions.true
SOLR_BASE_URLNoSolr base URL (no trailing collection name).http://localhost:8983/solr
RAG_COLLECTIONNoOverride serving collection name. Defaults to {RAG_PRODUCT}-rag.
DEPLOY_PROVIDERNoDeploy provider: 'docker' = docker compose, 'ssh' = Linux SSH MCP deploy.docker
RAG_EMBED_MODELNoLocal sentence-transformers model.BAAI/bge-small-en-v1.5
RAG_MMR_ENABLEDNoMaximal Marginal Relevance diversity (cap chunks per class).true
SOURCE_PROVIDERNoSource provider: 'local' = GitPython clone, 'github' = GitHub MCP adapter (falls back to local).local
INGEST_CACHE_DIRNoGit clone cache + commit SHA store../.ingest-cache
JENKINS_JOB_NAMENoPipeline job name.ontology-rag-onboard
RAG_METHOD_LEVELNoAlso index per-method chunks (in addition to class-level).false
RAG_RERANK_MODELNoReranker model name.BAAI/bge-reranker-base
RAG_SKIP_PATTERNSNoComma-separated file/path patterns to skip during ingest.target/,build/,.git/,node_modules/,*.class,*.jar,/test/,generated-sources/
RAG_RERANK_ENABLEDNoEnable cross-encoder reranking (BAAI/bge-reranker-base).false

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

NameDescription

No tools

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Latest Blog Posts

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