markdown-memory-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| config | No | Path to a TOML config file (equivalent to --config). Defaults to .markdown-memory.toml in the vault root. | |
| allow_write | No | Set to 'true' to expose the write_note tool (equivalent to --allow-write). | |
| MARKDOWN_MEMORY_CACHE | No | Cache directory. Defaults to $XDG_CACHE_HOME/markdown-memory-mcp or ~/.cache/markdown-memory-mcp. | |
| MARKDOWN_MEMORY_VAULT | No | Path to the vault. Can also be provided with the --vault argument. Defaults to the current directory. |
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 |
|---|---|
| search_notesA | Find notes by meaning and by words. Use this to recall what the vault knows. Args: query: What to look for, in natural language. k: How many notes to return (1-50). Returns a list, best first, of {name, path, description, rrf, cosine, bm25}. |
| read_noteA | Read one note in full. Args:
name: The note's file name without Returns {name, path, description, content}, where content is the whole file. |
| backlinksA | List the notes and index files that link to a note, by [[wikilink]] or Markdown link. Args:
name: The note's file name without Returns a list of {name, path, line}. Empty if nothing links to it. |
| lint_vaultA | Check the vault for broken links, missing frontmatter, duplicate names, orphans and an oversized index. Takes no arguments. Returns {findings: [{code, level, path, line, message}]}. Codes VR001-VR010. |
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 4 tools
Each tool targets a clearly distinct operation: semantic/keyword retrieval (search_notes), full-text retrieval by name (read_note), link-graph inspection (backlinks), and vault health checking (lint_vault). There is no overlap — search vs. read is a natural retrieve-then-expand split, and backlinks/lint are separate concerns entirely.
Three of four tools follow a clean verb_noun snake_case pattern (search_notes, read_note, lint_vault). 'backlinks' breaks the pattern as a bare noun, a minor but noticeable deviation.
Four tools is lean but each one earns its place in a read/retrieve workflow. It sits just under the comfortable range, so the surface feels slightly minimal rather than over-scoped.
The surface is read-only: there is no way to create, update, or delete a note, and no listing/enumeration of the vault. For a 'memory' server, the inability to write a memory is a significant gap that will force agents to fail on store/update workflows.