markdown-vault-mcp

Similar Notes

get_similar

Read-onlyIdempotent

Find semantically similar notes based on a reference document using stored embeddings. Excludes the reference and returns top matches, optionally filtered by folder or frontmatter.

Instructions

Find notes most semantically similar to the given document.

Uses stored embedding vectors — no re-embedding needed. The reference document is excluded from results. Requires semantic search to be configured (check 'stats' for semantic_search_available). Returns an empty list if embeddings are not configured (check 'embeddings_status') or the document has no stored vectors (call 'build_embeddings' to embed missing chunks).

Input Schema

TableJSON Schema

Name	Required	Description
`path`	Yes	Relative path of the reference document (e.g. "notes/topic.md"). Case-sensitive.
`limit`	No	Maximum number of similar notes to return (default 10).
`folder`	No	Restrict results to this folder (exact match or sub-folder prefix), e.g. "3-Resources". Useful to scope link candidates to one part of the vault. Use folder="" for root-level (top-level) documents only.
`filters`	No	Frontmatter equality filters, ANDed — e.g. {"type": "resource"}. Matched post-hoc against each candidate's full frontmatter, so any frontmatter key works (unlike keyword 'search' filters, which are limited to indexed_frontmatter_fields). List-valued fields match if the value is among them. On an OKF bundle three keys carry OKF semantics, exactly as in 'search': status ("stable" also matches notes without a status field), stale ("true"/"false"), and trust_tier.
`chunks_per_file`	No	Maximum sections returned per file (default 2). Set to 1 for one best section per file. Must be >= 1.
`wait_for_pending_writes`	No	Wait for recent index writes. On timeout, answer from the current index with _meta.index_stale=true. Default false.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv5.0.0Sep 15, 2026

changedInput schema / properties / wait_for_pending_writes / description

Previous value: -"When True, wait until your recent\ndocument mutations have been applied to the\nindex before answering, so the results reflect those changes.\nUse it right after modifying notes when this read must see\nthem (e.g. right after a document mutation whose\neffect this read should reflect). Default\nFalse answers immediately from the current index — almost\nalways already up to date; inspect the response's\n``_meta.index_stale`` field to tell whether a write was still\nin flight. Bounded by a server timeout (default 60s); on\ntimeout it answers from the current index rather than waiting\nlonger."New value: +"Wait for recent index writes. On timeout, answer from the current index with _meta.index_stale=true. Default false."

Changed3 schema fields changedv4.0.0Aug 26, 2026

addedInput schema / properties / filters

Added value: +{
+  "anyOf": [
+    {
+      "additionalProperties": {
+        "type": "string"
+      },
+      "type": "object"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Frontmatter equality filters, ANDed — e.g.\n{\"type\": \"resource\"}. Matched post-hoc against each\ncandidate's full frontmatter, so any frontmatter key works\n(unlike keyword 'search' filters, which are limited to\nindexed_frontmatter_fields). List-valued fields match if\nthe value is among them. On an OKF bundle three keys carry\nOKF semantics, exactly as in 'search': status (\"stable\"\nalso matches notes without a status field), stale\n(\"true\"/\"false\"), and trust_tier."
+}

addedInput schema / properties / folder

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Restrict results to this folder (exact match or\nsub-folder prefix), e.g. \"3-Resources\". Useful to scope\nlink candidates to one part of the vault.\nUse folder=\"\" for root-level (top-level) documents only."
+}

changedInput schema / properties / wait_for_pending_writes / description

Previous value: -"When True, wait until your recent\nwrite/edit/delete/rename operations have been applied to the\nindex before answering, so the results reflect those changes.\nUse it right after modifying notes when this read must see\nthem (e.g. right after a write/edit/delete/rename whose\neffect this read should reflect). Default\nFalse answers immediately from the current index — almost\nalways already up to date; inspect the response's\n``_meta.index_stale`` field to tell whether a write was still\nin flight. Bounded by a server timeout (default 60s); on\ntimeout it answers from the current index rather than waiting\nlonger."New value: +"When True, wait until your recent\ndocument mutations have been applied to the\nindex before answering, so the results reflect those changes.\nUse it right after modifying notes when this read must see\nthem (e.g. right after a document mutation whose\neffect this read should reflect). Default\nFalse answers immediately from the current index — almost\nalways already up to date; inspect the response's\n``_meta.index_stale`` field to tell whether a write was still\nin flight. Bounded by a server timeout (default 60s); on\ntimeout it answers from the current index rather than waiting\nlonger."

First observedv3.1.0Jul 8, 2026

TDQS

A4.7/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds valuable behavioral context: it uses stored embeddings (no re-embedding), excludes the reference document from results, and returns an empty list under certain conditions. It also mentions the wait_for_pending_writes behavior via the parameter description, which is a useful behavioral disclosure.

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 concise and well-structured. The core purpose is stated in the first sentence, followed by a brief mechanism note and then actionable guidance. Every sentence adds value, and the structure front-loads the most important information.

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

Completeness5/5

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

The description is complete for an agent to use this tool correctly. It covers prerequisites (semantic search configured), fallback behavior (empty list), and remediation (build_embeddings). The output schema exists, so return values are documented elsewhere. The parameter descriptions are exhaustive, covering edge cases and OKF semantics.

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 schema already documents all parameters thoroughly. The description adds context beyond the schema by explaining the overall mechanism (stored embeddings) and the fallback behavior (empty list if not configured). The parameter descriptions themselves are detailed, including edge cases like folder='' for root-level documents and the OKF semantics for filters.

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: 'Find notes most semantically similar to the given document.' It specifies the resource (notes), the operation (find similar), and the mechanism (stored embedding vectors). It also distinguishes itself from sibling tools like 'search' by emphasizing semantic similarity rather than keyword matching.

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

Usage Guidelines5/5

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

The description provides explicit guidance on when to use this tool: it requires semantic search to be configured, and it tells the agent to check 'stats' for semantic_search_available. It also explains what to do if embeddings are not configured (call 'build_embeddings') and how to handle missing vectors. This is clear, actionable usage guidance.

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