Folio
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LLM_MODEL | No | The model identifier for the LLM | ollama_chat/qwen2.5:7b |
| LLM_PROVIDER | No | The LLM provider (ollama, cerebras, openrouter, anthropic, openai) | ollama |
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
Features and capabilities supported by this server
Protocol revision2025-11-25
| 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_rootsA | List the folders this assistant is allowed to access. Call this first to discover where files live. |
| list_dirB | List the entries (files and sub-folders) of a directory inside a granted root. |
| read_fileA | Read the full text contents of a file inside a granted root. |
| searchA | Search the documents for the SIGNIFICANT WORDS in your query (case-insensitive; a line matches when it contains those words, in any order — so 'free shipping' matches 'shipping is free'). Returns matching lines with file and line number. For a full natural-language question, prefer the 'answer' tool. |
| edit_fileA | Edit a file inside a granted root by replacing an exact string with a new string, then saving it to disk. |
| summarizeA | Summarize a file using the host's own LLM (via MCP sampling). Returns a concise summary of the file's key points. |
| answerA | USE THIS to answer any natural-language question about the documents (e.g. 'how long are backups kept?'). It retrieves the relevant lines across the granted files and has the host's LLM answer from them in one step. Prefer this over 'search' for questions. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| summarize | Summarize a file in a granted folder. |
| format | Reformat a file into clean, well-structured markdown (saved in place). |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| roots_resource | Return the granted root folders as a JSON array of absolute paths. The host can read this at startup to show "you've granted: ~/Documents/notes". |
| files_resource | Return every readable text file across all granted roots, as absolute paths. This powers the web UI's file list and the CLI's @-mention autocompletion — the same role `docs://documents` played in Module 2, but over real files. We include only text files; binaries are skipped. |
TDQS
Scored across 7 tools
Most tools have clearly distinct purposes. The only overlap is between 'answer' and 'search', but their descriptions clarify the appropriate use case (natural language vs. keyword search).
All tool names use snake_case and follow a consistent verb_noun pattern (e.g., edit_file, list_dir) or single verbs (answer, search). No mixing of conventions.
With 7 tools, the set is well-scoped for a document query and editing server. Not too many or too few, though some minor operations (e.g., create file) are absent.
The domain of file management is partially covered: read, edit, list, search, summarize. However, missing tools for file creation, deletion, or renaming leave noticeable gaps for full lifecycle operations.