mcp-light-memory

Overview Schema Source Related Servers Discussions Admin

Search Project Memory

search

Read-only

Retrieve ranked durable project memories by natural-language query, with confidence and abstention metadata, for focused fact retrieval without starting a task.

Instructions

Search durable project memories and return ranked results with confidence and abstention metadata. Use for focused fact retrieval without starting a task; use context when beginning or resuming work. It does not alter durable memory content or the task stack; repeated calls may update retrieval or usage metadata, so it is not marked idempotent. It performs no network access.

Input Schema

TableJSON Schema

Name	Required	Description
`at`	No	Optional YYYY-MM-DD date used to filter memories by temporal validity.
`limit`	No	Maximum number of ranked memories to return.
`query`	Yes	Natural-language query describing the fact, decision, constraint, or prior work to retrieve.
`types`	No	Optional memory types to include; omit to search all supported types.
`explain`	No	Include per-channel retrieval scoring details for diagnostics.
`statuses`	No	Optional memory statuses to include; omit to use the server default.

Output Schema

TableJSON Schema

Name	Required	Description
`reason`	No	Human-readable explanation for the retrieval or abstention decision.
`results`	Yes	Ranked durable memory records returned by the search.
`admitted`	No	Number of candidate memories admitted to the result set.
`rejected`	No	Number of candidate memories rejected by retrieval admission rules.
`abstained`	Yes	True when retrieval intentionally returns no admitted result set.
`confidence_kind`	No	Whether retrieval confidence is heuristic or calibrated.
`retrieval_confidence`	No	Server confidence score for the retrieval result set.

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Oct 4, 2026

TDQS

A4.7/5.0

Behavior5/5

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

Annotations already declare readOnly/destructive/openWorld/idempotent hints, but the description goes further by explaining the reason for the non-idempotent hint (repeated calls may update retrieval or usage metadata) and clarifying that durable memory content and the task stack are not altered. The no-network-access statement also adds context beyond the openWorldHint.

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?

Three sentences, each load-bearing: purpose/output first, routing guidance second, behavioral caveats third. No repetition of schema content and no filler.

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?

With an output schema present, the description need not explain return values, and it still flags that results carry confidence and abstention metadata. Combined with full schema coverage and annotations, an agent has everything needed to call it 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 all six parameters are already documented in the schema. The description adds no syntax, format, or interaction details for query, types, statuses, at, limit, or explain, so the baseline 3 applies.

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?

States a specific verb and resource ('search durable project memories') plus the output character ('ranked results with confidence and abstention metadata'). It explicitly contrasts itself with the sibling 'context' tool, so an agent can route between them without opening 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?

Gives an explicit when ('focused fact retrieval without starting a task') and a when-not with the named alternative ('use context when beginning or resuming work'). Nothing about tool selection is left to inference.

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

Deploy Server