RootMind
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| RLM_HOME | No | Data folder that holds config.yaml (folder list) and the index database; defaults to the working directory when unset. The MCP servers read config.yaml and the database from here. | |
| MCP_API_TOKEN | No | Bearer token for the MCP server over HTTP (rootmind-mcp-http). Alternatively, on first start the server generates a token and saves it to data/api_token.txt. |
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
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_documentsA | Search the user's own files on this computer (the local folders indexed by RootMind). Fast full-text search (SQLite FTS5) over all indexed documents. Matches exact words and word prefixes. USE THIS FIRST: it is fast and cheap. Returns matching documents with text snippets, the location (page/slide/sheet) when known, and a suggested read_document call around each hit. |
| search_fuzzyA | Trigram-based fuzzy search that tolerates typos. USE THIS ONLY when search_documents finds nothing or the search term may be misspelled (e.g. 'lantren' finds 'lantern'). |
| list_documentsA | List indexed documents with metadata (no content). Use it for an overview of the available files or to find a file by name. |
| read_documentA | Read the text of a document, or a character window of it. At most 50,000 characters are returned per call; for large documents read the window around a known hit instead of paging through everything. |
| get_statisticsA | Show statistics about the document collection (number of documents, file types, total size). |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 5 tools
Each tool has a clearly distinct role: listing metadata, reading content, exact full-text search, fuzzy fallback search, and collection statistics. The descriptions explicitly guide when to use search_documents versus search_fuzzy, eliminating ambiguity between the two search tools.
All names use consistent snake_case with a leading verb (list_, read_, search_, get_). The only slight variation is search_fuzzy using an adjective modifier rather than a noun, but it still follows the same verb-led convention and is clearly readable.
Five tools is well within the ideal range and each tool covers a distinct, necessary operation for a local document search server. There is no redundancy or filler.
The surface covers the core lifecycle: discover documents, read them, search exactly or fuzzily, and inspect collection stats. Minor gaps exist, such as no filtering of searches by metadata or file type, and no dedicated single-document metadata lookup beyond the list overview.