Skip to main content
Glama
pvliesdonk

markdown-vault-mcp

by pvliesdonk
OverviewSchemaSourceRelated ServersScoreDiscussionsAdmin
Python
Hybrid

Search Vault

search
Read-onlyIdempotent

Find documents matching a query in a Markdown vault with keyword, semantic, or hybrid search. Filter by folder or frontmatter fields and get snippet results for quick scanning.

Instructions

Find documents matching a query using full-text or semantic search.

Search the vault. Omit 'mode' for the best mode this vault can serve — hybrid when embeddings are configured, keyword when they are not. Pass mode="keyword" for exact terms, operators, or filenames, where FTS5/BM25 beats fusion. Use mode="semantic" for pure vector similarity.

The 'content' field in each result is a snippet by default, not the full document. Use read(path, section=heading) to retrieve the full text of a specific section.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
modeNo"keyword" uses FTS5/BM25 for exact terms. "semantic" uses vector similarity (requires embeddings). "hybrid" fuses both via reciprocal rank fusion — best quality when available. Omit it (the default) to follow the vault's configured DEFAULT_SEARCH_MODE, which ships as "auto": hybrid where embeddings exist, keyword otherwise. Any configured default degrades to "keyword" when it needs embeddings the vault lacks; an explicit "semantic"/"hybrid" still errors when unconfigured.
limitNoMaximum results to return (default 10).
queryYesNatural language or keyword query string.
folderNoRestrict to documents under this folder path (e.g. "Journal"). Must match a value from 'list_folders'. Use folder="" for root-level (top-level) documents only.
filtersNoFilter by indexed frontmatter field values, e.g. {"cluster": "craft", "tags": "pacing"}. Only fields listed in indexed_frontmatter_fields (see 'stats') can be filtered. Multiple filters are ANDed. For list fields (e.g. tags), this checks membership — {"tags": "pacing"} matches any document where "pacing" appears in the tags list. On an OKF bundle three keys carry OKF semantics: status ("draft"/ "stable"/"deprecated"; "stable" also matches notes without a status field), stale ("true"/"false" — stale_after passed), and trust_tier ("unverified"/"machine-confirmed"/ "human-reviewed"); "type" filters normally, e.g. {"type": "Playbook", "stale": "false"}.
snippet_wordsNoWidth of the snippet window in words. Omit to use the server default. Set to 0 to return full chunk content. Use read(path, section=heading) for full section recovery.
chunks_per_fileNoMaximum number of sections to return per file (default 2). Set to 1 to get only the top-ranked section per file. Must be >= 1.
wait_for_pending_writesNoWhen True, wait until your recent document mutations have been applied to the index before answering, so the results reflect those changes. Use it right after modifying notes when this read must see them (e.g. right after a document mutation whose effect this read should reflect). Default False answers immediately from the current index — almost always already up to date; inspect the response's ``_meta.index_stale`` field to tell whether a write was still in flight. Bounded by a server timeout (default 60s); on timeout it answers from the current index rather than waiting longer.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Changed5 schema fields changedv4.1.0
    • addedInput schema / properties / mode / anyOf
      Added value: +[
+  {
+    "enum": [
+      "keyword",
+      "semantic",
+      "hybrid"
+    ],
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]
    • changedInput schema / properties / mode / default
      Previous value: -"keyword"New value: +null
    • changedInput schema / properties / mode / description
      Previous value: -"\"keyword\" uses FTS5/BM25 for exact terms. \"semantic\" uses\nvector similarity (requires embeddings). \"hybrid\" fuses both\nvia reciprocal rank fusion — best quality when available."New value: +"\"keyword\" uses FTS5/BM25 for exact terms. \"semantic\" uses\nvector similarity (requires embeddings). \"hybrid\" fuses both\nvia reciprocal rank fusion — best quality when available.\nOmit it (the default) to follow the vault's configured\nDEFAULT_SEARCH_MODE, which ships as \"auto\": hybrid where\nembeddings exist, keyword otherwise. Any configured default\ndegrades to \"keyword\" when it needs embeddings the vault\nlacks; an explicit \"semantic\"/\"hybrid\" still errors when\nunconfigured."
    • removedInput schema / properties / mode / enum
      Removed value: -[
-  "keyword",
-  "semantic",
-  "hybrid"
-]
    • removedInput schema / properties / mode / type
      Removed value: -"string"
  2. Changed2 schema fields changedv4.0.0
    • changedInput schema / properties / filters / description
      Previous value: -"Filter by indexed frontmatter field values, e.g.\n{\"cluster\": \"craft\", \"tags\": \"pacing\"}. Only fields listed\nin indexed_frontmatter_fields (see 'stats') can be filtered.\nMultiple filters are ANDed. For list fields (e.g. tags),\nthis checks membership — {\"tags\": \"pacing\"} matches any\ndocument where \"pacing\" appears in the tags list."New value: +"Filter by indexed frontmatter field values, e.g.\n{\"cluster\": \"craft\", \"tags\": \"pacing\"}. Only fields listed\nin indexed_frontmatter_fields (see 'stats') can be filtered.\nMultiple filters are ANDed. For list fields (e.g. tags),\nthis checks membership — {\"tags\": \"pacing\"} matches any\ndocument where \"pacing\" appears in the tags list. On an OKF\nbundle three keys carry OKF semantics: status (\"draft\"/\n\"stable\"/\"deprecated\"; \"stable\" also matches notes without\na status field), stale (\"true\"/\"false\" — stale_after\npassed), and trust_tier (\"unverified\"/\"machine-confirmed\"/\n\"human-reviewed\"); \"type\" filters normally, e.g.\n{\"type\": \"Playbook\", \"stale\": \"false\"}."
    • 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."
  3. First observedv3.1.0

TDQS

A4.9/5.0
Behavior5/5

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

Goes beyond the readOnly/idempotent/destructive annotations by revealing important runtime behavior: the default mode automatically adapts based on whether embeddings are configured, and the 'content' field returns snippets rather than full documents. This is genuinely useful behavioral context that an agent could not infer from annotations alone.

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 compact and well-structured: purpose first, then mode-selection guidance, then a critical output caveat. Every sentence earns its place, and the most actionable decision logic is front-loaded.

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?

For a search tool with 8 parameters, a dedicated output schema, and rich schema-level parameter documentation, the description covers the essential non-obvious context: mode fallback behavior, snippet semantics, and when to delegate to 'read'. Nothing an agent needs to select or invoke the tool correctly is missing.

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 coverage is 100% and each parameter already has a rich description, so the baseline is 3. The description adds value by condensing the mode decision logic into clear heuristics ('hybrid when embeddings are configured, keyword when they are not') and by explaining why keyword can beat fusion for exact-term queries. That goes slightly beyond the schema without duplicating it.

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?

Opens with a specific verb and resource: 'Find documents matching a query using full-text or semantic search.' This clearly identifies the tool's function and immediately distinguishes it from read-focused siblings. It also names the vault as the scope and the query as the primary input.

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?

Provides explicit mode-selection guidance: omit 'mode' for the best automatic option, pass keyword for exact terms/operators/filenames, and pass semantic for pure vector similarity. It also tells the agent when to use the sibling tool 'read' instead — when full section content is needed rather than snippets.

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

Install Server

Other Tools

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/pvliesdonk/markdown-vault-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server