Skip to main content
Glama
aliasunder

Vault Cortex Obsidian MCP Server

Delete Memory Entry

vault_delete_memory
Destructive

Delete one dated memory entry by exact date and text match, ensuring only the intended bullet is removed from a specified section in an About Me memory file.

Instructions

Delete a single dated entry from a memory file in About Me/. Both date and entry text are required for exact matching — ensures only the intended entry is removed.

Example: vault_delete_memory({ file: "Opinions", section: "AI tooling & memory (newest first)", date: "2026-05-01", entry: "Prefer X over Y" })

When to use: Removing an entry that was wrong when it was written — a mistake, a misattribution, or something never true. Memory files are append-only by default, so do NOT delete to reflect a change: append the new state via vault_update_memory instead (newest-first naturally supersedes). The exception is a file whose frontmatter declares entry-policy: living (check via vault_list_memory_files) — a current-state file where deleting an expired entry is the intended maintenance. Call vault_get_memory(file, section) first to see exact entry text for matching. Prefer vault_delete_note for deleting entire non-protected notes.

Parameters:

  • date + entry together uniquely identify the bullet line within the given section. If multiple entries share the same date and text, deletion fails as ambiguous.

  • section scopes the match — an identical entry under a different heading is not found. Section matching is case-insensitive, with or without the "(newest first)" suffix.

Errors:

  • "memory file not found" — file does not exist in About Me/; call vault_list_memory_files to discover valid names.

  • "memory file must not start with a dot" / "memory file must be a bare name without path separators" — pass the file's bare name: no folder or slash, and no leading dot (that would target a hidden file; memory files are always visible notes).

  • "date must be a real ISO calendar date" — date only accepts an existing calendar date in bare YYYY-MM-DD form. A hand-edited bullet carrying an impossible date cannot be targeted by this tool — remove it with vault_delete_span or a manual edit.

  • "section not found: …" — no H2 heading matches; the error lists the file's available sections

  • "no entry matching …" — no bullet matched the given date and entry text; verify exact text via vault_get_memory(file, section).

  • "ambiguous: N entries match …" — more than one identical bullet exists in the section (e.g. from hand edits, sync conflicts, or entries predating duplicate protection; vault_update_memory refuses to write exact duplicates). Remove the extra copy with vault_delete_span (pass first_match: true — identical lines make every anchor ambiguous) or a manual edit, then retry.

  • "refusing memory write: … would shrink content" — safety guard blocked a write that would remove more than half the file. Re-read with vault_get_memory to confirm current content; an entry that really is that large needs vault_delete_span or a manual edit.

Returns: Confirmation message.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
dateYesISO YYYY-MM-DD date of the entry (e.g. "2026-05-01"). Must match the date shown by vault_get_memory.
fileYesMemory file name without .md (e.g. "Principles"). Use the exact letter case.
entryYesExact entry text as shown by vault_get_memory — without the "- **YYYY-MM-DD**: " prefix or bullet.
sectionYesH2 section heading containing the entry. Matched case-insensitively, with or without the "(newest first)" suffix.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.54.9
    • changedInput schema / properties / entry / description
      Previous value: -"Exact entry text as shown by vault_get_memory — without the \"- **YYYY-MM-DD**: \" prefix or bullet. Both date and entry must match for deletion."New value: +"Exact entry text as shown by vault_get_memory — without the \"- **YYYY-MM-DD**: \" prefix or bullet."
  2. Changed2 schema fields changedv0.54.7
    • addedInput schema / properties / entry / minLength
      Added value: +1
    • changedInput schema / properties / file / description
      Previous value: -"Memory file name without .md (e.g. \"Principles\")"New value: +"Memory file name without .md (e.g. \"Principles\"). Use the exact letter case."
  3. Changed2 schema fields changedv0.26.0
    • addedInput schema / properties / file / minLength
      Added value: +1
    • addedInput schema / properties / section / minLength
      Added value: +1
  4. Changed2 schema fields changedv0.23.5
    • changedInput schema / properties / date / description
      Previous value: -"ISO YYYY-MM-DD date of the entry"New value: +"ISO YYYY-MM-DD date of the entry (e.g. \"2026-05-01\"). Must match the date shown by vault_get_memory."
    • changedInput schema / properties / entry / description
      Previous value: -"Exact entry text (no date prefix or bullet)"New value: +"Exact entry text as shown by vault_get_memory — without the \"- **YYYY-MM-DD**: \" prefix or bullet. Both date and entry must match for deletion."
  5. Changed1 schema field changedv0.22.1
    • addedInput schema / properties / date / minLength
      Added value: +1
  6. Changed1 schema field changedv0.19.2
    • changedInput schema / properties / section / description
      Previous value: -"H2 section heading containing the entry"New value: +"H2 section heading containing the entry. Matched case-insensitively, with or without the \"(newest first)\" suffix."
  7. Added

TDQS

A4.8/5.0
Behavior5/5

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

Annotations declare destructiveHint=true and readOnlyHint=false, and the description is consistent with that while adding far more: the append-only default policy, the `entry-policy: living` exception, the ambiguity failure mode, and the 'refusing memory write: would shrink content' safety guard. This is unusually rich disclosure of destructive-operation semantics.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Purpose, example, when-to-use, parameters, and errors are cleanly headed and front-loaded, and the length is justified by a genuinely complex matching/error surface. The error list is exhaustive to the point of mild verbosity, but each entry maps to a distinct actionable recovery path.

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 destructive, non-idempotent tool with four required parameters and no output schema, the definition covers prerequisites, matching semantics, all failure modes with recovery steps, and the return value. Nothing needed to invoke it 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%, so the baseline is 3, but the description adds real meaning beyond it: date+entry together uniquely identify a bullet line, duplicate date+text pairs fail as ambiguous, and section scoping means an identical entry under a different heading will not match. Case-insensitive section matching is already covered by the schema, so it is not fully additive.

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 opens with a specific verb and resource ('Delete a single dated entry from a memory file in About Me/') and immediately scopes it against siblings by clarifying it removes one entry, not a note. The example makes the granularity concrete, so an agent can distinguish this from vault_delete_note without reading either schema.

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?

It gives explicit when-to-use ('removing an entry that was wrong when it was written'), explicit when-NOT-to-use ('do NOT delete to reflect a change: append via vault_update_memory instead'), and a named exception (files with `entry-policy: living`). It also routes to alternatives for adjacent cases (vault_delete_note for whole notes, vault_delete_span for duplicate/impossible-date lines).

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