Synapse
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| SYNAPSE_HTTP_PORT | No | The port to use when running the server in HTTP mode (e.g., for browser-based AI clients). Default is 3777 if not specified via --port. | 3777 |
| SYNAPSE_VAULT_PATH | No | The path to your Obsidian vault or folder of markdown files. This is required when running the server via command line or in configurations that don't specify it as an argument. |
Capabilities
Features and capabilities supported by this server
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| prompts | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| vault_readA | Read a file from the Obsidian vault. Returns the full content including frontmatter. |
| vault_writeA | Write or overwrite a file in the Obsidian vault. Creates parent directories automatically. Use this to create new wiki pages, update existing ones, or save any markdown content. |
| vault_listA | List markdown files in the vault or a subdirectory. Returns relative paths. |
| vault_searchA | Search the vault for files containing a text query. Returns matching files with line numbers and context. Case-insensitive. |
| vault_statsA | Get vault statistics: file counts, folder structure, and whether the knowledge base has been initialized. |
| vault_frontmatterA | Read the YAML frontmatter metadata from a vault file. Returns parsed key-value pairs (title, tags, date, status, etc.). |
| synapse_saveA | Save content to the vault's sources folder from a URL or pasted text. Ideal for mobile users who find articles and want to save them without a web clipper. If a URL is provided, fetches the page and converts it to markdown. If content is provided directly, saves it as-is. Always adds frontmatter with metadata. |
| synapse_statusA | One-shot status overview. Returns everything needed to understand the vault state: configuration, file counts, recent activity, CLAUDE.md schema, and suggested next actions. This is THE tool to call when a user first connects or asks "what can you do?" |
| synapse_ingestA | Process a source file into the knowledge base. Reads the source, generates organized pages (summaries, concepts, entities), adds [[wikilinks]], and updates the index and log. You MUST read the source file content first, then generate all pages. Follow the CLAUDE.md schema in the vault root for conventions and folder paths. Steps:
|
| synapse_compileA | Scan for all unprocessed sources and compile them into organized pages. Lists which sources exist in the sources folder but don't have corresponding summaries yet. Use synapse_ingest on each one to process them. |
| synapse_queryA | Research a question against the knowledge base. Reads the index, identifies relevant pages, and returns their content so you can synthesize an answer. You MUST save the synthesized answer to the outputs folder using vault_write after responding. |
| synapse_lintA | Health-check the knowledge base. Scans for contradictions, orphan pages, broken wikilinks, missing frontmatter, stale content, and missing pages. Returns a report and instructions for fixing issues. |
| synapse_setupA | Onboarding entry point for Synapse. Scans the vault to detect existing structure, conventions, and CLAUDE.md, then returns configuration options for the user to choose from:
After the user chooses, call synapse_configure with their selection. |
| synapse_configureA | Save Synapse configuration based on the user's choice from synapse_setup. Three modes:
|
| synapse_initA | Initialize a structured knowledge base in the vault. Creates the folder structure, generates CLAUDE.md with the schema, and creates the initial index and log files. Safe to run on an existing vault — won't overwrite existing files. For new vaults only. If you have an existing vault, use |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| compile | Process all new sources in the knowledge base. Finds unprocessed raw sources and ingests each one into the wiki. |
| research | Research a question across the knowledge base, synthesize an answer with citations, and save it. |
| health-check | Run a health check on the knowledge base. Lint for issues and fix what you can. |
| save-article | Save an article from a URL to the knowledge base and process it into the wiki. |
| getting-started | Build my brain — reads your files, organizes everything, and makes it searchable. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Latest Blog Posts
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/tomjrworks/synapse-obsidian'
If you have feedback or need assistance with the MCP directory API, please join our Discord server