Obsidian Server MCP

Overview Schema Source Related Servers Discussions Admin

search_query

Read-onlyIdempotent

Query Markdown notes in an Obsidian vault with JsonLogic over path, content, tags, frontmatter, and file stats, returning truthy matches. Scope limits the scan.

Instructions

Query Markdown with JsonLogic over path, content, tags, frontmatter and stat. Returns truthy values. Only scope limits the scan; query path/glob conditions only filter results. Overflow errors, never truncation. No link graph.

Input Schema

TableJSON Schema

Name	Required	Description
`query`	Yes
`scope`	No	Optional scan scope; omit for a recursive whole-Vault scan. directory "" is root; recursive=false scans only direct child files.
`maxFiles`	No	Optional scanned-file cap; omit for defaults.
`maxEntries`	No	Optional scanned-entry cap; omit for defaults.
`maxResults`	No	Optional match cap, not truncation; omit for defaults.
`maxFileBytes`	No	Optional per-file byte cap; omit for defaults.
`maxTotalBytes`	No	Optional scanned-byte cap, not response size; omit for defaults.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`results`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 3, 2026

addedInput schema / properties / scope

Added value: +{
+  "additionalProperties": false,
+  "description": "Optional scan scope; omit for a recursive whole-Vault scan. directory \"\" is root; recursive=false scans only direct child files.",
+  "properties": {
+    "directory": {
+      "type": "string"
+    },
+    "recursive": {
+      "type": "boolean"
+    }
+  },
+  "required": [
+    "directory",
+    "recursive"
+  ],
+  "type": "object"
+}

First observedv0.1.0Oct 3, 2026

TDQS

A3.9/5.0

Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the safety profile is covered. The description adds real behavioral context beyond that: query results are evaluated for truthy values, only scope limits the scan while path/glob conditions merely filter, and overflow produces errors rather than truncation. That is meaningful semantics the schema and annotations do not carry.

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?

Five short sentences, each carrying a distinct fact, with the core purpose front-loaded. No filler, no repetition of schema or annotation content, and the important overflow-vs-truncation guarantee is stated tersely.

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?

For a complex JsonLogic query tool with an output schema present, the description covers purpose, evaluation semantics, scope behavior, overflow handling, and the link-graph exclusion. The only meaningful gap is the absence of an explicit pointer to reference_query as the alternative for link queries, which would complete the routing picture.

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 86%, so the schema already documents scope, the max* caps, and the query object. The description still adds value by enumerating the queryable domains (path, content, tags, frontmatter, stat) that the bare 'query: object' schema does not reveal, and by clarifying that path conditions inside the query filter rather than limit scanning.

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?

States a specific verb and resource: query Markdown via JsonLogic over path, content, tags, frontmatter and stat. This clearly identifies what the tool does and its query domain. However, it never names the closest sibling (reference_query) even though the 'No link graph' clause hints at the boundary between them, so differentiation is only implicit.

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?

There is no explicit 'use this when' statement or named alternative. The clause 'No link graph' implicitly steers link-oriented queries toward reference_query, and the scope/path-filter clarification implies when scanning vs filtering applies, but an agent must infer the routing rather than read it.

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

Deploy Server