ken
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| KEN_MCP_MODE | No | hybrid / bm25 / semantic. Serves bm25 while the model is missing. | hybrid |
| KEN_MCP_CHUNKER | No | regex / treesitter / line / markdown. | regex |
| KEN_MCP_LOG_LEVEL | No | debug / info / warn / error. | warn |
| KEN_MCP_MODEL_DIR | No | Path to a Model2Vec snapshot containing model.safetensors. | ~/.ken/model |
| KEN_MCP_AUTO_FETCH | No | On first run with a model-needing mode and no model present, fetch potion-code-16M (~60 MB) in the background. | 1 |
| KEN_MCP_CACHE_SIZE | No | LRU bound on the repo→Index cache. | 16 |
| KEN_MCP_DEFAULT_REPO | No | Pre-indexed source; lets tools omit the repo arg. | (unset) |
| KEN_ALLOW_PRIVATE_CLONE_TARGETS | No | Off by default: for http(s) repo URLs, ken rejects loopback / link-local / RFC1918 addresses (SSRF guard). Set 1 to allow internal git hosts. | 0 |
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
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/townsendmerino/ken'
If you have feedback or need assistance with the MCP directory API, please join our Discord server