What can you do with this server?

Mímir's Vault is an MCP server that provides a structured, interlinked memory graph (in .context/) to help AI agents navigate codebases efficiently. With it, you can: * Initialize a project's memory graph with starter overview.md and decisions.md. * Fetch the root overview node to understand the project scope and file structure. * Navigate to specific module nodes using Obsidian-style wikilinks (e.g., [[modules/auth]]). * Search all nodes by keywords or topics to quickly find information. * Create new module/submodule notes that are automatically linked into the parent overview. * Update node content surgically by appending or replacing text under specific headings. * Log architectural decisions as structured ADRs in decisions.md. * Reduce token waste by guiding agents to only relevant source files mapped in the graph. * Visualize the interconnected memory graph using Obsidian or VS Code Foam.

Which integrations are available for this server?

Provides an Obsidian-compatible memory graph and context management system, allowing AI agents to navigate project architecture, module relationships, and target file paths via wikilinked markdown notes.

How do I use Mimir's Vault?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Mimir's Vault Navigate the memory graph to find the dependencies of the auth module" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

Mimir's Vault

by GopikChenth

Overview Schema Related Servers Score Discussions

Python

Local

Key Pillars • System Architecture • Installation • MCP Client Setup • Tool Reference • Agent Workflow Guide

The Problem: Wandering AI Coding Agents

When AI coding agents (Claude Code, Cursor, Antigravity) work on complex software repositories, they frequently suffer from Context Inflation & Wandering:

They blindly grep directories, re-scan full codebases, and load 30+ unrelated files into memory.
They waste thousands of LLM tokens, increase execution latency, and lose track of core architectural rules.

Related MCP server: vault-master-mcp

The Solution: Mímir's Vault Memory Graph

Mímir's Vault (Mimirs_Vault) is a high-performance Model Context Protocol (MCP) server built in Python (FastMCP).

It maintains a human-readable, interlinked Obsidian-Wikilink memory graph inside ./.context/ for any software repository.

AI agents follow the Memory-First Scanning Rule:

Inspect .context/overview.md via get_root_node.
Follow Obsidian wikilinks ([[modules/auth]]).
Inspect only the targeted source code files mapped in that module note.
Edit zero unnecessary files.

Key Pillars

Rune	Pillar	Rationale
ᛗ	Memory-First Protocol	Mandates AI agents to consult `.context/overview.md` before reading project source code.
ᛟ	Obsidian-Wikilink Graph	Interlinked notes (`[[modules/auth]]`) viewable natively in Obsidian, VS Code, and Foam graph visualizers.
⚡	Zero Token Waste	Reduces context consumption by up to 80%, eliminating agent codebase wandering.
⚔️	Surgical Node Updates	Tools to append, update, and log Architectural Decision Records (ADRs) without clobbering existing notes.
ᛚ	Human & Agent Shared Memory	Clean Markdown files (`.context/`) readable by both human developers and LLMs alike.

System Architecture

<your-project-root>/
└── .context/                        <-- Memory Graph Root (Ignored in .gitignore)
    ├── overview.md                  <-- ROOT NODE (Scope, File Structure Map, [[modules/*]] index)
    ├── decisions.md                 <-- Architectural Decision Records (ADRs)
    └── modules/                     <-- LINKED MODULE NODES
        ├── auth.md                  <-- Module Note (Scope, Mapped Source Files)
        ├── database.md              <-- Module Note
        └── ui/                      <-- Submodule Directory
            └── components.md        <-- Submodule Note ([[modules/ui/components]])

Installation

Prerequisites

Python 3.10+

1. Clone the Repository & Initialize Environment

# Clone repository
git clone https://github.com/GopikChenth/Mimir-s_Vault.git
cd "Mimir-s_Vault"

# Create virtual environment & install dependencies
python3 -m venv .venv
.venv/bin/pip install "fastmcp>=3.4.0" "mcp>=1.2.0" "pydantic>=2.0.0"

2. Verify Installation & Test Graph Engine

.venv/bin/python test_graph.py

Expected Result: ALL TESTS PASSED SUCCESSFULLY!

MCP Client Setup

Add Mimirs_Vault to your preferred AI Client configuration:

Google Antigravity IDE (`agy.json` / Settings) or Claude Desktop (`claude_desktop_config.json`)

{
  "mcpServers": {
    "Mimirs_Vault": {
      "command": "<path-to-repo>/.venv/bin/python",
      "args": [
        "<path-to-repo>/main.py"
      ]
    }
  }
}

Note: Replace <path-to-repo> with the absolute path where you cloned Mimir-s_Vault (e.g. /home/user/projects/Mimir-s_Vault or C:/Projects/Mimir-s_Vault).

Cursor IDE

Open Cursor Settings → Features → MCP Servers.
Click + Add New MCP Server.
Name: Mimirs_Vault
Type: command
Command: <path-to-repo>/.venv/bin/python "<path-to-repo>/main.py"

MCP Tool Reference

Mimirs_Vault exposes 7 core tools for AI agent navigation:

Tool	Signature	Purpose
`get_root_node`	`(workspace_path: str = ".")`	Fetches `.context/overview.md` (Project Scope, Master File Structure Map, [[modules/*]] index).
`navigate_node`	`(node_path: str, workspace_path: str = ".")`	Traverses a wikilink node (e.g. `modules/auth`, `decisions`). Returns content & mapped source files.
`search_nodes`	`(query: str, workspace_path: str = ".")`	Performs keyword and topic search across all `.context/` markdown notes.
`init_context_graph`	`(project_name, description, scope, workspace_path)`	Bootstraps `.context/` folder with starter `overview.md` and `decisions.md`.
`create_module_node`	`(module_name, scope, source_files, parent_node)`	Creates a module note and registers `[[modules/name]]` in the parent node.
`update_node`	`(node_path, content, section_heading, mode)`	Surgically appends or replaces content under a specific section heading.
`log_decision`	`(title, context, decision, consequences)`	Appends an Architectural Decision Record (ADR) in `.context/decisions.md`.

System Prompts & Resources

MCP Prompts

memory_first_workflow: Instructs AI agents: "Consult get_root_node first. Read ONLY the target source files mapped in module wikilinks."
bootstrap_project_context: Guides AI to auto-scan an un-documented repository and build .context/ notes.

MCP Resources

context://root — Direct read of .context/overview.md.
context://decisions — Direct read of .context/decisions.md.

Agent Workflow Guide

1. Bootstrapping a New Repository

In any project workspace, prompt your AI agent:

"Run the bootstrap_project_context prompt to initialize the memory graph for this repository."

The AI will call init_context_graph and create_module_node to build your project's .context/ tree.

2. Daily Task Execution

When asking your AI agent to implement a feature:

"Implement user authentication with JWT. Check the memory graph first."

The AI will:

Call get_root_node to inspect .context/overview.md.
Follow [[modules/auth]] to extract mapped file paths (src/auth/service.py).
Inspect & edit only src/auth/service.py (zero token waste).

3. Logging Architecture Decisions

"Log an architectural decision that we switched to RS256 JWT signing."

The AI calls log_decision, appending ADR-002 to .context/decisions.md.

Visualizing Your Memory Graph in 3D

Because all nodes use standard Obsidian Wikilink syntax ([[modules/auth]]), open your repository's .context/ directory in:

Obsidian
VS Code Foam Extension

Enjoy an interactive, 3D visual graph of your codebase's architectural memory!

ᛗ Built with Wisdom for AI-First Engineering ᛗ

Crafted with Python FastMCP • Report Issue • Submit Request

Available Tools

7 tools

create_module_nodeA

Create a new module or submodule markdown note and automatically register its Wikilink [[modules/...]] in the parent overview node.

ParametersJSON Schema

Name	Required	Default
`scope`	Yes
`module_name`	Yes
`parent_node`	No	overview
`source_files`	No
`workspace_path`	No	.

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

TDQS

A3.6/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Given that no annotations are provided, the description carries the burden of disclosing behavior. It discloses the main side effect (automatic Wikilink registration) but omits details like file overwrite behavior, failure modes, or required permissions. The core behavior is communicated, but not exhaustive.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, well-structured sentence that front-loads the primary action and destination. No unnecessary words or repetitions.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool has 5 parameters and an output schema, but the description is minimal. It conveys the essential purpose and a key side effect, yet misses parameter guidance and edge cases. The presence of an output schema mitigates the need to explain return values, but overall completeness is average for a creation tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% and the description does not clarify any parameter meanings. The phrase 'parent overview node' hints at parent_node but does not explain scope, source_files, or workspace_path. The description fails to compensate for the lack of schema descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb ('Create') and specifies the resource ('module or submodule markdown note') along with a key side effect (registering Wikilink in the parent overview node). This clearly differentiates from siblings like update_node and log_decision.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies when to use the tool (creating nodes in a module hierarchy) but does not explicitly state when not to use it or mention alternatives. No exclusions or comparisons to sibling tools are provided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

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.

ParametersJSON Schema

Name	Required	Description	Default
`workspace_path`	No		.

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

TDQS

A3.9/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It clarifies the tool fetches a specific file and implies a read-only operation via 'Fetch'. However, it does not disclose error cases (e.g., missing file) or other side effects, leaving some behavioral ambiguity.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description consists of two sentences, each adding essential information: the tool's function and a critical usage order. There is no filler or redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool has an output schema, so return values are likely covered there. The description provides the purpose, the exact file path, and usage priority. However, the unclear parameter semantics is a gap, though the tool's low complexity makes it mostly self-contained.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema has one parameter (workspace_path) with 0% description coverage, and the description never mentions it. The agent only sees a string with a default of '.', with no explanation that it likely refers to the workspace root. This is insufficient for a parameter with no schema documentation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool fetches the main root node at a specific path (.context/overview.md). The directive 'ALWAYS call this tool FIRST' distinguishes it from sibling tools by establishing it as the entry point.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly says 'ALWAYS call this tool FIRST before scanning raw codebase files,' providing a strong when-to-use instruction. It does not explicitly mention alternative tools or exclusions, but the 'FIRST' directive effectively positions it as a prerequisite.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

init_context_graphB

Initialize a fresh human-readable .context/ memory graph in the workspace with overview.md, decisions.md, and module templates.

ParametersJSON Schema

Name	Required	Default
`scope`	Yes
`description`	Yes
`project_name`	Yes
`workspace_path`	No	.

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

TDQS

B3.1/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description must disclose side effects. 'Fresh' hints at creating new files but does not clarify whether existing files are overwritten or if the tool fails when a graph exists. No mention of permissions or other behaviors.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence with no fluff, front-loading the key action. It communicates the core purpose efficiently.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

While the output schema exists, the description is incomplete for a tool with four parameters and no annotations. It lacks guidance on parameter meanings, failure modes, and the relationship to existing workspace state, making it insufficient for an agent to invoke confidently.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema has no descriptions for any of the four parameters, and the tool description doesn't explain project_name, description, scope, or workspace_path. At 0% schema coverage, the description must compensate but doesn't.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's function: initializing a fresh .context/ memory graph with specific files. The verb 'Initialize' and the resource '.context/ memory graph' are specific and distinguish it from sibling tools that operate on an existing graph.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies the tool is for bootstrapping a new workspace memory graph, but doesn't explicitly state when to use it versus sibling tools like create_module_node or update_node. No exclusions or alternative scenarios are provided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

log_decisionA

Record an Architectural Decision Record (ADR) in .context/decisions.md with title, context, decision, and consequences.

ParametersJSON Schema

Name	Required	Default
`title`	Yes
`context`	Yes
`decision`	Yes
`consequences`	Yes
`workspace_path`	No	.

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

TDQS

A3.5/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden of behavioral disclosure. It states the file and fields but does not disclose whether the tool appends to the file, overwrites existing content, or what side effects occur (e.g., file creation, permission requirements). For a mutation tool, this lack of transparency is a significant gap.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence that is concise and front-loaded with the primary verb and resource. Every word earns its place, and there is no irrelevant detail or repetition.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Although an output schema exists (so return values may be covered), the tool has 5 parameters with 0% schema coverage, no annotations, and a description that omits workspace_path and file behavior. This leaves the tool incomplete for an agent to invoke correctly without additional inference.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate. It only lists the parameter names (title, context, decision, consequences) without adding semantic meaning beyond their names. The optional workspace_path parameter is not mentioned in the description, leaving its purpose ambiguous. Overall, the description fails to provide meaningful parameter-level guidance.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: to record an Architectural Decision Record (ADR) in a specific file (.context/decisions.md) with the listed fields. It uses a specific verb ('Record') and resource, which distinguishes it from sibling tools focused on node graph operations.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The context is clearly implied: use this tool when you need to log an ADR. However, it does not explicitly provide when-not-to-use guidance or mention alternatives, though sibling tools are clearly different. The description gives enough context for an agent to infer appropriate usage.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

navigate_nodeA

Navigate to a specific module or submodule node in the memory graph (e.g. 'modules/auth', 'decisions', 'overview') using Wikilinks.

ParametersJSON Schema

Name	Required	Description	Default
`node_path`	Yes
`workspace_path`	No		.

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

TDQS

A3.5/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description must fully disclose behavior. It only says 'navigate' without clarifying whether this is a read-only operation or mutates the current context, nor does it mention error handling, permissions, or output details. The meaning of 'using Wikilinks' is also underspecified.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, concise sentence with a parenthetical example list. Every part serves a purpose with no filler, making it highly efficient.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no annotations and a tool with two parameters and an output schema, the description is too sparse. It lacks behavioral context, error behavior, and details about the workspace_path parameter, leaving critical gaps for an agent to use it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, so the description must compensate. It provides useful examples for node_path but entirely omits any explanation of workspace_path, its default, or its purpose. Thus, coverage of parameter semantics is incomplete.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool navigates to a specific module or submodule node in the memory graph using Wikilinks, with concrete examples. This distinguishes it from sibling tools like search_nodes or create_module_node.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The examples (e.g., 'modules/auth', 'decisions') convey clear context for when to use this tool. However, it does not explicitly state when not to use it or name alternative tools, though the purpose is distinct enough to infer.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

search_nodesB

Search for keywords or topics across all Obsidian-wikilink nodes in the project memory graph.

ParametersJSON Schema

Name	Required	Description	Default
`query`	Yes
`workspace_path`	No		.

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

TDQS

B3.4/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description bears full responsibility for behavioral disclosure. It states the search scope but does not mention read-only nature, result format, pagination, or any side effects, leaving significant behavioral details undisclosed.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence that conveys the core purpose without unnecessary words. It earns its place and is immediately scannable.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's modest complexity (2 parameters) and the existence of an output schema, the description covers the primary action but leaves the workspace_path parameter unexplained. It is minimally adequate but lacks detail on search scope nuances and parameter roles.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema has 0% description coverage, and the tool description does not explicitly mention either parameter. The phrase 'keywords or topics' hints at the query parameter but provides no explanation of workspace_path or its default behavior, failing to compensate for the schema gap.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states a specific verb ('Search') and resource ('all Obsidian-wikilink nodes in the project memory graph'). This unambiguously differentiates it from sibling tools like create_module_node or navigate_node.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage: search when you need to find nodes by keyword or topic. However, it provides no explicit guidance on when to prefer this tool over alternatives or any exclusions, so it relies on implied context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

update_nodeB

Surgically update or append content under a specific section heading in a node markdown file.

ParametersJSON Schema

Name	Required	Default
`mode`	No	append
`content`	Yes
`node_path`	Yes
`workspace_path`	No	.
`section_heading`	No

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

TDQS

B3.4/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description bears full responsibility. It discloses that the tool performs updates or appends under a heading, but fails to describe behavior such as whether it creates missing sections, how it handles existing content, or any permission requirements. This is insufficient for a mutation tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

A single, front-loaded sentence with no wasted words. It conveys the core action and scope efficiently.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has 5 parameters, 0% parameter descriptions, and no annotations, the description leaves important details unexplained such as mode semantics and defaults. While an output schema exists, the description still feels incomplete for effective invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description maps section_heading to 'specific section heading', content to 'content', and node_path to 'node markdown file', but does not explain mode or workspace_path. With 0% schema coverage, this partial compensation is not fully adequate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool updates or appends content under a section heading in a node markdown file, using a specific verb and resource. It distinguishes itself from sibling tools like create_module_node by emphasizing targeted modification rather than creation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The phrase 'surgically update or append' implies a precise, targeted edit for existing content, which provides some usage context. However, it does not explicitly state when to use this tool over alternatives like create_module_node or search_nodes, nor does it provide exclusion criteria.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

7 tool updatesv1.0.0Aug 5, 2026
- First observedcreate_module_node
- First observedget_root_node
- First observedinit_context_graph
- First observedlog_decision
- First observednavigate_node
- First observedsearch_nodes
- First observedupdate_node

Install Server

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A3.7/5.0

Disambiguation5/5

Each tool has a clearly distinct purpose: initialization, navigation, search, module creation, updating, and decision logging. There is no overlap in their responsibilities.

Naming Consistency5/5

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.

Tool Count5/5

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.

Completeness4/5

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.

Maintenance

ActivityMaintained

ResponsivenessSyncing

Resources

GitHub Repository

Need Help?

Related Servers

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

NeuroStack
io.github.raphasouthall
Token-efficient MCP memory for Markdown vaults. Tiered search, GraphRAG, AI memories.
Knowledge & Memory RAG Systems Vector Databases
246
gread A
io.github.NitroRCr
An MCP server that gives your AI access to the source code and docs of all public github repos
Version Control Code Analysis Documentation Access
5361
Agentage Memory
io.agentage
One memory, every AI. A shared, user-owned markdown memory your AI clients read and write over MCP.
Knowledge & Memory File Systems
2
Brainbox
dev.thexi
Persistent, portable memory for AI assistants — your private memory graph, from any MCP client.
Knowledge & Memory AI & Machine Learning
2

Related MCP Servers

knitbrain
Developer Tools Knowledge & Memory
PDgit12
A
license
A
quality
A
maintenance
Local-first MCP server that gives any AI coding agent per-project memory, workflow intelligence, and always-on, lossless token & context optimization.
Updated 2 months ago (2026-07-08 07:14 UTC)
37
18
3
MIT
vault-master-mcp
Note Taking Knowledge & Memory
mattbotcode
A
license
Not graded
quality
D
maintenance
An MCP server that treats Obsidian vaults as knowledge graphs, enabling AI agents to traverse wikilinks, assemble token-budgeted context, and search with backlink awareness.
Updated 6 months ago (2026-03-15 17:54 UTC)
3
1
MIT
research-memory-mcp
Knowledge & Memory Note Taking Research & Data
wuwususu
A
license
Not graded
quality
B
maintenance
An MCP server that provides controlled read/write tools for managing local-first research memory in an Obsidian vault, enabling AI agents to maintain project context across sessions.
Updated 3 months ago (2026-06-14 14:42 UTC)
11
1
MIT
ai-mind-map
Code Analysis Knowledge & Memory Developer Tools
shdra06
A
license
Not graded
quality
A
maintenance
An MCP server that reduces AI coding agent token usage by 80-99% through a queryable knowledge graph of code, change tracking, and persistent memory across sessions.
Updated 2 months ago (2026-07-14 18:39 UTC)
101
1
MIT

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/GopikChenth/Mimir-s_Vault'

If you have feedback or need assistance with the MCP directory API, please join our Discord server

The Problem: Wandering AI Coding Agents

The Solution: Mímir's Vault Memory Graph

Key Pillars

System Architecture

Installation

Prerequisites

1. Clone the Repository & Initialize Environment

2. Verify Installation & Test Graph Engine

MCP Client Setup

Google Antigravity IDE (agy.json / Settings) or Claude Desktop (claude_desktop_config.json)

Cursor IDE

MCP Tool Reference

System Prompts & Resources

MCP Prompts

MCP Resources

Agent Workflow Guide

1. Bootstrapping a New Repository

2. Daily Task Execution

3. Logging Architecture Decisions

Visualizing Your Memory Graph in 3D

ᛗ Built with Wisdom for AI-First Engineering ᛗ

Available Tools

Output Schema

Output Schema

Output Schema

Output Schema

Output Schema

Output Schema

Output Schema

Tool Schema Changelog

Maintenance

Resources

Looking for Admin?

Related MCP Connectors

Related MCP Servers

Latest Blog Posts

MCP directory API

Google Antigravity IDE (`agy.json` / Settings) or Claude Desktop (`claude_desktop_config.json`)