mcp-local-file-llm
by iryzhkov
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LOCAL_LLM_LOG | No | Usage log path, or off | $XDG_DATA_HOME/mcp-local-file-llm/usage.jsonl |
| LOCAL_LLM_URL | No | Ollama root (native /api/chat, so num_ctx is settable per request) | http://localhost:11434 |
| LOCAL_LLM_MODEL | No | Model tag | qwen3-coder:30b |
| LOCAL_LLM_NUM_CTX | No | Context window requested per call | 65536 |
| LOCAL_LLM_MAX_BYTES | No | Refuse inputs larger than this | 4000000 |
| LOCAL_LLM_TIMEOUT_MS | No | Per-request timeout | 300000 |
| LOCAL_LLM_CHUNK_CHARS | No | Chunk size before map-reduce kicks in | 140000 |
| LOCAL_LLM_CONCURRENCY | No | Chunks in flight during the map phase (see below) | 2 |
| LOCAL_LLM_LOG_PROMPTS | No | Set to off to log sizes and timings but no prompt text | on |
| LOCAL_LLM_ALLOW_SECRETS | No | Set to 1 to disable the credential-path guard | unset |
| LOCAL_LLM_FIND_BATCH_CHARS | No | Bytes of files per local_find request | 50000 |
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 | |
This server cannot be deployed
Maintenance
ActivityMaintained
ResponsivenessNo issues