Skip to main content
Glama
Mnemosyne-OS

Mnemosyne OS

by Mnemosyne-OS
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

mnemosyne_memory_query

Retrieve raw chronicles from a Mnemosyne vault to quote or document. Search architecture notes, code, decisions, sessions, and git history, ranked by similarity.

Instructions

Raw chronicle search in a Mnemosyne OS vault. Returns the matching chronicles themselves (architecture notes, code, decisions, sessions, git history) for YOU to read, rank and cite. Nothing is rewritten, so this is what to use when you need the source text verbatim, e.g. to quote it or to write documentation from it. Ranked by vector similarity fused with a local BM25 channel, weighted by spineType. ⚠️ If your goal is to FIND something rather than to quote it, prefer mnemosyne_memory_ask even when you only want its sources: measured on 2026-08-31, ask surfaces notes on rare literal terms (proper nouns, identifiers, product names) that this tool misses, because it retrieves deeper and re-ranks. ⛔ And never read the score as confidence: a miss and a hit come back with indistinguishable scores, so judge the returned text, never the number beside it.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
limitNoMax number of results (default: 10, max: 50)
queryYesThe search query. Be specific. Examples: "Phase 51 auto-poll implementation", "SDK authentication bug", "why did we choose dual-vector dimensions".
vaultNoVault TOKEN to query (case-insensitive; the folder name uppercased, spaces and hyphens as underscores). The path-shaped `id` from mnemosyne_vault_list is also accepted and normalized. Mnemosyne OS exposes one vault per tracked folder. This deployment's default is "DEV". Tokens this MCP is SCOPED for (a config list, not a census, so some may not be mounted on this machine): PERSONAL, SOCIAL. Call mnemosyne_vault_list for the vaults that actually exist. Anything outside the scoped list is refused.DEV
max_content_charsNoPer-chronicle content snippet size in chars (default: 600). Each result is truncated to this length with a hint about total size. Raise to 2000+ when you genuinely need full file content, but be aware results stack up against your context window.
spine_type_filterNoOptional whitelist of spineTypes: restricts results to those types only. Use ["ARCHITECTURE"] to surface design docs over code, ["GIT"] for commit history, ["BUGFIX","DEBUG"] for incident knowledge, ["SOURCE_CODE"] to force code-only. Without this, all types are returned (the SOURCE_CODE scope weighting decides ranking).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.5.1-infinity

TDQS

A4.7/5.0
Behavior5/5

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

With no annotations present, the description carries the full behavioral burden, and it delivers: it states that nothing is rewritten, explains the ranking mechanism (vector similarity fused with BM25, weighted by spineType), and discloses the non-intuitive behavior that hits and misses have indistinguishable scores. This goes well beyond a generic search description.

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 front-loaded with the core purpose, then returns behavior, then use cases, then alternatives and caveats. Every sentence adds distinct value; the warnings and sibling comparison are dense but not padded.

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?

Even without an output schema, the description tells the agent what comes back (matching chronicles, truncated snippets, decorations hinting at total size) and how to interpret it. Combined with complete parameter documentation in the schema, the agent has enough context to select and call the tool correctly.

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

Parameters3/5

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

Schema description coverage is 100%, so the parameters themselves are already well documented in the input schema. The tool description adds ranking context and a score caveat but no additional parameter-level semantics, so the baseline of 3 is appropriate.

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 states a specific verb and resource: 'Raw chronicle search in a Mnemosyne OS vault' that returns 'the matching chronicles themselves' for reading, ranking, and citing. It also separates this tool from mnemosyne_memory_ask by framing query as verbatim-source retrieval and ask as find-and-surface retrieval.

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?

Usage guidance is explicit: use this tool when you need source text verbatim for quoting or documentation, and prefer mnemosyne_memory_ask when the goal is to find something rather than to quote it. It even warns against treating scores as confidence, which directly shapes correct invocation and interpretation.

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