code-context
by infino-ai
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CX_ROOT | No | default repo root for the MCP server / CLI when not run from the repo | current directory |
| CX_NO_EMBED | No | keyword-only mode for the MCP server (skip the vector stage) | off |
| CX_SEARCH_K | No | default number of hits `search` returns (also settable per call and via the CLI `-k` flag) | 10 |
| CX_AUTO_SYNC | No | 0 disables the MCP server's background staleness sync | on |
| CX_INDEX_DIR | No | where the index lives | <repo>/.infino |
| CX_MAX_FILES | No | indexing cap on number of files | 20000 |
| CX_AUTO_INDEX | No | 0 makes a query on an unindexed repo error instead of building the index inline on the first `search`/`sql` | on |
| CX_NO_RECEIPT | No | 1 turns off usage accounting - the per-call receipt on results and the `cx usage` ledger | off |
| CX_MAX_FILE_BYTES | No | indexing cap on file size | 1MB |
| CX_SYNC_INTERVAL_SECS | No | auto-sync debounce between staleness checks | 30 |
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
| 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 | |