Skip to main content
Glama
Sign In
obsidian-mcp

obsidian-mcp

by thoreinstein
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

obsidian_rag_index

Build or update a semantic search index for your markdown vault. Re-index a single note or the whole vault, and only changed files are re-embedded unless a full rebuild is forced.

Instructions

Index the vault for semantic search (RAG). If file_path is provided, only that file is re-indexed. Incremental by default — only re-embeds changed files. Use force_reindex to rebuild from scratch.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "obsidian_rag_index"
  }
}

Input Schema

NameRequiredDescriptionDefault
file_pathNoRelative path to a specific note to re-index
vault_pathNoOptional vault path override
force_reindexNoForce full re-index, ignoring cached file hashes (default: false)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.8/5.0
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 behavioral burden. It does disclose useful traits — incremental by default, only changed files re-embedded, cached hashes honored unless force_reindex is set — but says nothing about cost/duration, whether it writes index files to disk, error behavior for a missing vault, or whether it blocks.

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?

Three short sentences, each earning its place: purpose first, then scope control, then default behavior, then the override. No redundancy and no filler.

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?

For a no-annotation, no-output-schema indexing tool this covers invocation but not outcomes. An agent cannot tell whether a result is a summary of indexed files, how long the operation takes, or what happens on partial failure — all relevant because the tool mutates a persistent index.

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

Parameters4/5

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

Schema description coverage is 100%, so the baseline is 3. The description goes beyond the schema by explaining the interaction between parameters — file_path narrows scope to one file, force_reindex ignores cached hashes for a full rebuild — giving the agent operational meaning the field descriptions alone do not convey.

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

Purpose4/5

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

The description states a specific verb and resource ('Index the vault for semantic search (RAG)') and its effect is unambiguous versus the sibling obsidian_rag_query, which reads rather than builds the index. It stops short of naming the sibling explicitly, so an agent must infer the index/query pairing from names alone.

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?

It gives clear conditional usage for each mode: omit file_path for an incremental vault-wide run, pass file_path to re-index a single note, set force_reindex to rebuild from scratch. What is missing is guidance on *when* in a workflow to run it (e.g., after editing notes) and whether it must precede queries.

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

Deploy Server

Other Tools