Schema | ollqd

ollqd

Describes the environment variables required to run the server.

Name	Required	Description	Default
`CHUNK_SIZE`	No	Approximate tokens per chunk	512
`OLLAMA_URL`	No	Ollama base URL	http://localhost:11434
`QDRANT_URL`	No	Qdrant REST URL	http://localhost:6333
`CHUNK_OVERLAP`	No	Overlap tokens between chunks	64
`MAX_TOOL_ROUNDS`	No	Max tool-calling rounds per query	6
`OLLAMA_TIMEOUT_S`	No	Request timeout in seconds	120
`OLLAMA_CHAT_MODEL`	No	Chat model for RAG	qwen2.5:14b
`OLLAMA_EMBED_MODEL`	No	Embedding model	nomic-embed-text

Features and capabilities supported by this server

Capability	Details
`tools`	{ "listChanged": false }
`prompts`	{ "listChanged": false }
`resources`	{ "subscribe": false, "listChanged": false }
`experimental`	{}

Functions exposed to the LLM to take actions

Name	Description
index_codebaseB	Index a codebase directory into Qdrant. Walks files, chunks at code boundaries, embeds via Ollama, upserts to Qdrant.
index_documentsC	Index document files (markdown, text, etc.) into Qdrant.
semantic_searchC	Semantic search over indexed content. Returns ranked results with file paths and code snippets.
list_collectionsA	List all Qdrant collections with point counts.
delete_collectionC	Delete a Qdrant collection. Set confirm=true to proceed.

Interactive templates invoked by user choice

Name	Description
No prompts

Contextual data attached and managed by the client

Name	Description
No resources

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/leomarviegas/Ollqd'

If you have feedback or need assistance with the MCP directory API, please join our Discord server