Mimir's Vault
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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": true
} |
| logging | {} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| extensions | {
"io.modelcontextprotocol/ui": {}
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_root_nodeA | Fetch the main root node (.context/overview.md) of the project memory graph. ALWAYS call this tool FIRST before scanning raw codebase files. |
| navigate_nodeA | Navigate to a specific module or submodule node in the memory graph (e.g. 'modules/auth', 'decisions', 'overview') using Wikilinks. |
| search_nodesB | Search for keywords or topics across all Obsidian-wikilink nodes in the project memory graph. |
| init_context_graphB | Initialize a fresh human-readable .context/ memory graph in the workspace with overview.md, decisions.md, and module templates. |
| create_module_nodeA | Create a new module or submodule markdown note and automatically register its Wikilink [[modules/...]] in the parent overview node. |
| update_nodeB | Surgically update or append content under a specific section heading in a node markdown file. |
| log_decisionA | Record an Architectural Decision Record (ADR) in .context/decisions.md with title, context, decision, and consequences. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| memory_first_workflow | System prompt instructing the AI agent to consult the .context/ memory graph first before touching source code. |
| bootstrap_project_context | Prompt guiding the AI agent to scan the current codebase and initialize a structured .context/ Obsidian-wikilink graph. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| get_root_resource | Read the root overview.md note. |
| get_decisions_resource | Read the decisions.md note. |
TDQS
Scored across 7 tools
Each tool has a clearly distinct purpose: initialization, navigation, search, module creation, updating, and decision logging. There is no overlap in their responsibilities.
All tools follow a consistent verb_noun pattern in snake_case (e.g., get_root_node, create_module_node, log_decision). The naming convention is uniform and predictable.
With 7 tools, the set is well-scoped for managing a project memory graph. Each tool fulfills a specific need without unnecessary bloat or redundancy.
The toolset covers initialization, reading, creating, and updating nodes, plus decision logging. It lacks a delete or rename operation, which are minor gaps for a full lifecycle but not critical for the primary use case.