ChunkTuner
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CHUNK_TUNER_BASE_DIR | Yes | Base directory for your corpus |
Capabilities
Features and capabilities supported by this server
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_strategiesB | List registered chunking strategies, optionally filtered by content type. |
| preview_chunksC | Chunk inline text with one strategy + params (no embeddings). |
| evaluate_chunkingC | Dry-run cost estimate or full evaluation ( |
| recommend_configA | Run tuner and return ranked |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| explain_chunking_results | Help an assistant interpret evaluation / recommendation output. |
| design_eval_questions | Guide creation of domain-specific evaluation questions. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| doc_overview | |
| doc_strategy_guidelines | |
| doc_metrics_guide |
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/shantanu-deshmukh/chunktuner'
If you have feedback or need assistance with the MCP directory API, please join our Discord server