Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
PORTNoserve only. The HTTP port.3000
RAGDOWN_TOKENNoserve: the bearer token /mcp and /api/context require. Hook: the token it sends.
RAGDOWN_WATCHNoWatch the folder; without a watcher, sync on start and on ragdown_reindex only.true
RAGDOWN_MODELSNoModel cache, shared by every folder.~/.cache/ragdown/models
RAGDOWN_THREADSNoONNX Runtime threads for bge-small.half the cores
RAGDOWN_DATA_DIRNoThe index. Deleting it only costs a rebuild.~/.cache/ragdown/<hash of docs dir>
RAGDOWN_DOCS_DIRYesThe Markdown folder, walked recursively. Dot-folders and node_modules are skipped, and symlinks are not followed. Indexes .md, .markdown and .mdx.
RAGDOWN_EMBEDDERNobge-small, openai:<model> (any OpenAI-compatible /embeddings endpoint, such as Ollama or llama.cpp), or hash (tests only).bge-small
SECURE_LOCAL_NETNoserve only. Skip the token on a trusted network. serve refuses to start with neither.false
RAGDOWN_NOTES_DIRNoWhere ragdown_remember writes. Must be inside the docs folder.notes
RAGDOWN_READ_ONLYNoHide the write tools.false
RAGDOWN_HOOK_TOP_KNoMost sections injected per prompt.4
RAGDOWN_TEXT_LIMITNoCharacters per hit in text output. Every cut names the ragdown_read_doc call that returns the rest.2000
RAGDOWN_EMBEDDING_URLNoFor openai:<model>. The URL of the OpenAI-compatible embeddings endpoint.OpenAI
RAGDOWN_HOOK_MAX_CHARSNoMost characters injected per prompt.6000
RAGDOWN_HOOK_MIN_SCORENoLowest cosine similarity the hook injects.0.7
RAGDOWN_HOOK_TIMEOUT_MSNoHow long the hook waits for the server.5000
RAGDOWN_EMBEDDING_API_KEYNoFor openai:<model>. The API key for the OpenAI-compatible embeddings endpoint.OpenAI

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

CapabilityDetails
tools
{
  "listChanged": true
}

Tools

Functions exposed to the LLM to take actions

NameDescription
ragdown_recallA

Hybrid (semantic + keyword) search over the user's Markdown notes. Returns the most relevant sections with file path, line range, heading breadcrumb and cosine similarity (above ~0.7 is usually on topic). Use it before answering anything the notes may cover; follow up with ragdown_read_doc for the surrounding text.

ragdown_read_docA

Read a Markdown file from the notes folder, whole or by line range, straight from disk. Never clipped. Use it to see the context around a ragdown_recall hit.

ragdown_statsA

The notes folder, index size (files, chunks), embedder, whether this process is the indexing primary, and the last sync. include_files lists every indexed file.

ragdown_rememberA

Save something worth keeping (a decision, a fix, a how-to) as a new Markdown note in the notes folder, indexed immediately so later searches find it. Never overwrites an existing file.

ragdown_reindexA

Bring the index up to date with the folder now. Changes are normally picked up automatically within a second; use this after bulk edits made while no server was running, or full: true to re-embed everything.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

A4.1/5.0

Scored across 5 tools

Disambiguation5/5

Each tool has a clearly distinct purpose: recall is search, read_doc is read, stats is metadata, remember is create, reindex is maintenance. No overlap or ambiguity exists.

Naming Consistency5/5

All tools use the ragdown_ prefix with a concise verb/noun pattern (recall, read_doc, stats, remember, reindex). Consistent and predictable.

Tool Count5/5

Five tools provide a complete, well-scoped set for a note-taking RAG server: search, read, create, inspect, and maintain. No tool feels redundant or missing.

Completeness4/5

Core CRUD plus search and index maintenance are covered, but update and delete operations for notes are absent, leaving minor gaps for lifecycle management.

Maintenance

ActivityMaintained
ResponsivenessNo issues