The Obsidian Diary MCP Server enables AI-powered smart journaling within Obsidian by automating entry creation, content management, and intelligent backlinking.
Core Features:
Generate diary templates with AI-powered reflection prompts based on analysis of recent entries and writing patterns
Save diary entries with automatic intelligent backlink generation to related entries using AI theme detection
Read existing entries by date in YYYY-MM-DD format
List recent entries with configurable count to track journaling history
Update backlinks for individual entries or refresh all backlinks across the diary based on current content
Create meaningful connections between entries through automatic [[YYYY-MM-DD]] format backlinks that link thematically related diary entries
Integrates with GitHub Copilot CLI to enable natural language commands for creating diary templates and journaling assistance
Provides smart journaling capabilities for Obsidian vaults with AI-powered reflection prompts, automatic backlink generation between diary entries, and adaptive templates that learn from writing patterns
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Obsidian Diary MCP Server create a memory log for today"
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.
AI-powered journaling with local processing, automatic backlinks, and smart prompts.
AI-generated reflection prompts based on past 3 calendar days
Day citations with automatic [[YYYY-MM-DD]] backlinks
Brain dump prioritization (analyzes your writing, not prompts)
Smart #tag extraction using theme similarity
Todo extraction to organized checklists
Memory trace analysis with theme evolution
Sunday synthesis (weekly reflection prompts)
Related MCP server: Enhanced Obsidian MCP Server
uv (Python package manager)
Ollama (llama3.1 or compatible model)
MCP client (e.g., GitHub Copilot CLI)
Obsidian vault (for markdown files)
1. Clone and install:
git clone https://github.com/madebygps/obsidian-diary-mcp.gitcd obsidian-diary-mcpuv syncchmod +x start-server.sh2. Configure:
cp .env.example .envEdit .env: set DIARY_PATH and PLANNER_PATH (required)
3. Add to MCP client config (e.g., GitHub Copilot CLI):
Name: diary
Command: /full/path/to/obsidian-diary-mcp/start-server.sh
Configuration (.env):
Required: DIARY_PATH, PLANNER_PATH
Optional: OLLAMA_MODEL (default: llama3.1:latest), OLLAMA_TIMEOUT (60s), OLLAMA_TEMPERATURE (0.7), OLLAMA_NUM_PREDICT (1000 tokens)
Create: "create a memory log for today" → AI prompts based on past 3 days
Write: Open in Obsidian, write freely in Brain Dump section
Extract: "extract todos from today's entry" → Action items to planner
Link: "link today's memory log" → Auto-generates [[YYYY-MM-DD]] & #tags
Explore: Use Obsidian's backlinks panel and graph view
More Commands: "show themes from last week", "create memory trace for 30 days", "refresh memory links for 30 days"
Logs in logs/ directory: server-YYYY-MM-DD.log (protocol), debug-YYYY-MM-DD.log (operations)
tail -f logs/debug-$(date +%Y-%m-%d).log # Watch in real-time
grep ERROR logs/debug-*.log # Find errors
grep "similarity" logs/debug-*.log # Debug backlinksServer issues: Check .env exists with DIARY_PATH and PLANNER_PATH set. Run ./start-server.sh directly to test.
Ollama issues: Verify running with curl http://localhost:11434/api/tags. Pull model: ollama pull llama3.1:latest
No backlinks: Need 2+ entries with similar themes (>8% overlap). Ensure Brain Dump section has substantial content (>50 chars). Check: grep "Brain Dump" logs/debug-*.log
Timeouts: Increase OLLAMA_TIMEOUT (90+) and OLLAMA_NUM_PREDICT (2000+) for reasoning models.
Local AI: Ollama processes entries locally—content never leaves your machine
Calendar-Based: Analyzes past 3 calendar days (not just last 3 entries)
Brain Dump Focus: Prioritizes your writing over answered prompts for themes
Day Citations: AI cites [Day 1]/[Day 2] → converts to [[2025-10-07]] backlinks
Smart Linking: Jaccard similarity connects entries with >8% theme overlap
Sundays: 5 weekly synthesis prompts (vs 3 daily)
Todo Extraction: AI identifies action items from brain dumps
Each entry (YYYY-MM-DD.md) has plain text headers:
## Reflection Prompts
**1. Question with [[2025-10-06]] backlink (reason)...**
---
## Brain Dump
Your thoughts, experiences, observations...
---
## Memory Links
**Temporal connections:** [[2025-10-05]] • [[2025-10-04]]
**Topic tags:** #career-growth #self-reflectionMIT • Python 3.13+ • FastMCP 2.12.4+ • Ollama
Create a new diary entry template with reflection prompts based on recent entries.
Args: date: Date for the entry in YYYY-MM-DD format. If not provided, uses today's date.
Returns: A formatted diary template with reflection prompts
| Name | Required | Description | Default |
|---|---|---|---|
| date | No |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It states the tool creates a template, implying a write operation, but doesn't mention permissions, side effects, or error handling. The mention of 'based on recent entries' hints at data access, but lacks details on how this influences the template generation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is front-loaded with the core purpose, followed by clear sections for Args and Returns. Every sentence adds value without redundancy, making it efficient and well-structured for quick understanding.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has an output schema (covering return values), no annotations, and low schema coverage, the description does a good job by explaining the parameter and return purpose. However, as a creation tool with no behavioral annotations, it could benefit from more context on permissions or side effects to be fully complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description adds significant meaning beyond the input schema, which has 0% description coverage. It explains the 'date' parameter's purpose, format (YYYY-MM-DD), and default behavior (uses today's date if not provided), compensating well for the schema's lack of documentation.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Create' and resource 'new diary entry template', specifying it includes 'reflection prompts based on recent entries'. However, it doesn't explicitly differentiate from sibling tools like 'save_diary_entry' or 'update_entry_backlinks', which might also involve diary entry creation or modification.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives like 'save_diary_entry' or 'update_entry_backlinks'. The description mentions 'based on recent entries', but doesn't specify prerequisites or exclusions, leaving the agent to infer usage context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List recent diary entries.
Args: count: Number of recent entries to list (default: 10)
Returns: A list of recent entry dates
| Name | Required | Description | Default |
|---|---|---|---|
| count | No |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the tool lists entries and returns dates, but lacks details on permissions needed, rate limits, pagination (beyond the 'count' parameter), error handling, or whether it's read-only (implied by 'list' but not explicit). For a tool with zero annotation coverage, this 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.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is appropriately sized and front-loaded. The first sentence states the core purpose clearly. The 'Args' and 'Returns' sections are structured efficiently, with each sentence adding value—no wasted words. It's concise without being under-specified.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's low complexity (one optional parameter) and the presence of an output schema (which handles return value details), the description is mostly complete. It covers the purpose, parameter semantics, and return type. However, it lacks behavioral context (e.g., permissions, errors), which is a minor gap since annotations are absent and the tool is simple.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description adds meaningful context beyond the input schema. The schema only defines 'count' as an integer with a default of 10, with 0% description coverage. The description explains that 'count' is the 'Number of recent entries to list (default: 10)', clarifying its purpose and default value. Since there's only one parameter and schema coverage is low, this compensates well.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: 'List recent diary entries.' It specifies the verb ('list') and resource ('diary entries'), and the 'recent' qualifier distinguishes it from siblings like 'read_diary_entry' (which reads a specific entry) and 'save_diary_entry' (which creates/updates). However, it doesn't explicitly differentiate from 'create_diary_template' or 'update_entry_backlinks', which are less similar.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives. It doesn't mention siblings like 'read_diary_entry' for accessing specific entries or 'save_diary_entry' for creating new ones. There's no context on prerequisites, such as whether entries must exist first, or exclusions, like when not to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Read an existing diary entry.
Args: date: Date of the entry in YYYY-MM-DD format
Returns: The diary entry content
| Name | Required | Description | Default |
|---|---|---|---|
| date | Yes |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It states this is a read operation but doesn't mention error handling (e.g., what happens if the entry doesn't exist), authentication needs, rate limits, or other behavioral traits. This is a significant gap for a tool with no annotation coverage.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is appropriately sized and front-loaded, with the core purpose stated first. The Args and Returns sections are structured clearly, though the formatting could be more integrated. There's minimal waste, earning a high score.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's low complexity (one parameter) and the presence of an output schema (which handles return values), the description is minimally adequate. However, it lacks behavioral context (e.g., error cases) and usage guidelines, which are important for completeness despite the simple schema.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description adds meaningful context beyond the input schema, which has 0% description coverage. It specifies that the 'date' parameter should be in 'YYYY-MM-DD format', clarifying the expected syntax. With only one parameter, this is sufficient for a high score, though it doesn't cover edge cases like invalid dates.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose with a specific verb ('Read') and resource ('an existing diary entry'), making it immediately understandable. However, it doesn't explicitly differentiate from sibling tools like 'list_recent_entries' or 'save_diary_entry', which prevents a perfect score.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives like 'list_recent_entries' or 'save_diary_entry'. It lacks context about prerequisites (e.g., entry must exist) or exclusions, leaving usage decisions ambiguous.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Save a diary entry and automatically add relevant backlinks.
Args: date: Date for the entry in YYYY-MM-DD format content: The diary entry content
Returns: Success message with the file path and auto-generated backlinks
| Name | Required | Description | Default |
|---|---|---|---|
| content | Yes | ||
| date | Yes |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden. It discloses that the tool saves entries and automatically adds backlinks, which are behavioral traits. However, it doesn't mention permission requirements, whether it overwrites existing entries, rate limits, or error conditions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is appropriately sized with clear sections (purpose, args, returns). The first sentence states the core functionality, and subsequent sections provide necessary details. However, the 'Args' and 'Returns' headings could be more integrated with the flow.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given 2 parameters with 0% schema coverage and an output schema exists, the description provides adequate context. It explains the tool's purpose, parameter formats, and return value expectations. The output schema means the description doesn't need to detail return structure, but it could better address behavioral aspects given no annotations.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
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 provides format guidance for the date parameter ('YYYY-MM-DD format') and clarifies that 'content' is 'The diary entry content', adding meaningful context beyond the bare schema. However, it doesn't explain constraints like content length or date validation.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Save' and resource 'diary entry', and adds 'automatically add relevant backlinks' which distinguishes it from basic creation tools. However, it doesn't explicitly differentiate from sibling tools like 'create_diary_template' or 'update_entry_backlinks'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided about when to use this tool versus alternatives like 'create_diary_template' or 'update_entry_backlinks'. The description only states what the tool does, not when it's appropriate compared to sibling tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Update the backlinks for an existing diary entry based on its current content.
Args: date: Date of the entry in YYYY-MM-DD format
Returns: Success message with updated backlinks
| Name | Required | Description | Default |
|---|---|---|---|
| date | Yes |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It states the tool updates backlinks based on content, implying a mutation operation, but fails to address critical aspects such as required permissions, whether changes are reversible, or any rate limits. This leaves significant gaps in understanding the tool's behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is well-structured and front-loaded, with the core purpose stated first, followed by clear sections for 'Args' and 'Returns.' Every sentence adds value without redundancy, making it efficient and easy to parse.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (a mutation with no annotations), the description is moderately complete. It covers the purpose and parameter semantics adequately, and the presence of an output schema means return values need not be detailed. However, it lacks usage guidelines and sufficient behavioral transparency, leaving gaps for an AI agent to fully understand when and how to invoke it correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema description coverage is 0%, so the description must compensate. It adds meaningful context: the 'date' parameter is explained as 'Date of the entry in YYYY-MM-DD format,' which clarifies its purpose beyond the bare schema. Since there is only one parameter, this is sufficient to earn a high score, though not a 5 due to lack of deeper semantic details (e.g., timezone handling).
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: 'Update the backlinks for an existing diary entry based on its current content.' It specifies the verb ('Update'), resource ('backlinks'), and scope ('existing diary entry'), but does not explicitly differentiate it from sibling tools like 'save_diary_entry' or 'read_diary_entry', which prevents a score of 5.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives. It does not mention prerequisites (e.g., entry must exist), exclusions, or compare it to siblings like 'save_diary_entry' (which might handle content updates). This lack of contextual direction limits its utility for an AI agent.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v1.0.0create_diary_templatelist_recent_entriesread_diary_entrysave_diary_entryupdate_entry_backlinksEach tool has a clearly distinct purpose with no overlap: create_diary_template generates templates, list_recent_entries lists entries, read_diary_entry reads content, save_diary_entry saves new entries, and update_entry_backlinks updates backlinks. The descriptions reinforce these distinct functions, making misselection unlikely.
All tools follow a consistent verb_noun pattern with clear, descriptive names (e.g., create_diary_template, list_recent_entries). There are no deviations in naming style, making the set predictable and easy to understand at a glance.
With 5 tools, this server is well-scoped for a diary management system. Each tool serves a specific, necessary function (CRUD operations and backlink management) without redundancy, making the count appropriate for the domain's scope.
The toolset covers core diary operations well: create (via save_diary_entry), read (read_diary_entry), list (list_recent_entries), and update (update_entry_backlinks), plus template creation. A minor gap is the lack of a delete tool, but agents can work around this, and the surface supports essential workflows without dead ends.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Search your Obsidian vault to quickly find notes by title or keyword, summarize related content, a…
Connect AI assistants to your GitHub-hosted Obsidian vault to seamlessly access, search, and analy…
Privacy-first work tracking with summaries, reports, coaching, and AI-ready long-term memory.
A daily notebook your AI writes in — on today's page, in your entity graph, marked as its own.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/madebygps/obsidian-diary-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
