Un sistema de memoria persistente de alto rendimiento para el Protocolo de Contexto de Modelo (MCP) basado en libSQL. Este servidor proporciona funciones de búsqueda vectorial y un almacenamiento eficiente de conocimiento utilizando libSQL como almacén de respaldo.
Búsqueda vectorial de alto rendimiento con libSQL
💾 Almacenamiento persistente de entidades y relaciones
🔍 Capacidades de búsqueda semántica
🔄 Gestión de gráficos de conocimiento
🌐 Compatible con bases de datos libSQL locales y remotas
🔒 Autenticación segura basada en tokens para bases de datos remotas
Related MCP server: dragon-brain
Este servidor está diseñado para usarse como parte de una configuración MCP. A continuación, se muestran ejemplos para diferentes entornos:
Agregue esto a su configuración de Cline MCP:
{
"mcpServers": {
"mcp-memory-libsql": {
"command": "npx",
"args": ["-y", "mcp-memory-libsql"],
"env": {
"LIBSQL_URL": "file:/path/to/your/database.db"
}
}
}
}Para obtener una guía detallada sobre cómo configurar este servidor con Claude Desktop en WSL, consulte Cómo hacer que el servidor MCP funcione con Claude Desktop en WSL .
Agregue esto a su configuración de Claude Desktop para entornos WSL:
{
"mcpServers": {
"mcp-memory-libsql": {
"command": "wsl.exe",
"args": [
"bash",
"-c",
"source ~/.nvm/nvm.sh && LIBSQL_URL=file:/path/to/database.db /home/username/.nvm/versions/node/v20.12.1/bin/npx mcp-memory-libsql"
]
}
}
}El servidor admite bases de datos SQLite locales y libSQL remotas a través de la variable de entorno LIBSQL_URL:
Para bases de datos SQLite locales:
{
"env": {
"LIBSQL_URL": "file:/path/to/database.db"
}
}Para bases de datos libSQL remotas (por ejemplo, Turso):
{
"env": {
"LIBSQL_URL": "libsql://your-database.turso.io",
"LIBSQL_AUTH_TOKEN": "your-auth-token"
}
}Nota: Al utilizar WSL, asegúrese de que la ruta de la base de datos utilice el formato del sistema de archivos Linux (por ejemplo, /home/username/... ) en lugar del formato de Windows.
De forma predeterminada, si no se proporciona ninguna URL, se utilizará file:/memory-tool.db en el directorio actual.
El servidor implementa la interfaz de memoria MCP estándar con capacidades de búsqueda vectorial adicionales:
Gestión de entidades
Crear/actualizar entidades con incrustaciones
Eliminar entidades
Buscar entidades por similitud
Gestión de relaciones
Crear relaciones entre entidades
Eliminar relaciones
Consultar entidades relacionadas
El servidor utiliza una base de datos libSQL con el siguiente esquema:
Tabla de entidades: almacena información de entidades e incrustaciones
Tabla de relaciones: almacena relaciones entre entidades
Capacidades de búsqueda vectorial implementadas utilizando las operaciones vectoriales integradas de libSQL
Debido a los requisitos de 2FA de npm, la publicación debe realizarse manualmente:
Crear un conjunto de cambios (documenta tus cambios):
pnpm changesetVersión del paquete (actualiza la versión y el REGISTRO DE CAMBIOS):
pnpm changeset versionPublicar en npm (se solicitará el código 2FA):
pnpm release¡Agradecemos sus contribuciones! Lea nuestras normas de contribución antes de enviar solicitudes de incorporación de cambios.
Licencia MIT: consulte el archivo LICENCIA para obtener más detalles.
Construido sobre el Protocolo de Contexto Modelo
Desarrollado por libSQL
Create new entities with observations and optional embeddings
| Name | Required | Description | Default |
|---|---|---|---|
| entities | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It states 'Create new entities' which implies a write/mutation operation, but doesn't disclose behavioral traits like permissions needed, whether it's idempotent, rate limits, or what happens on failure. The mention of 'optional embeddings' hints at functionality but lacks operational context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence with zero waste. It's front-loaded with the core action and resource, and every word ('new entities', 'observations', 'optional embeddings') adds value. No extraneous information or repetition.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no annotations, no output schema, and a single but complex parameter (nested array of objects), the description is incomplete. It doesn't explain return values, error handling, or the full scope of entity creation (e.g., validation rules, uniqueness constraints). For a mutation tool with rich nested data, more context is needed.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description must compensate. It adds meaning by specifying that entities include 'observations and optional embeddings', which clarifies the purpose of the 'entities' array parameter beyond the schema's structural definition. However, it doesn't detail all nested fields like 'entityType' or 'name', leaving some semantics uncovered.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Create' and the resource 'new entities', specifying they include 'observations and optional embeddings'. It distinguishes from siblings like delete_entity (deletion) and read_graph/search_nodes (read operations), though not explicitly named. The purpose is specific but could more directly contrast with create_relations.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives is provided. It doesn't mention prerequisites, when not to use it, or compare with siblings like create_relations (for relationships) or search_nodes (for finding existing entities). The description implies usage for entity creation but offers no contextual boundaries.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Create relations between entities
| Name | Required | Description | Default |
|---|---|---|---|
| relations | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden for behavioral disclosure. It states 'Create relations' which implies a write/mutation operation, but doesn't specify permissions needed, whether it's idempotent, error handling, or what happens on success/failure. It lacks details on rate limits, side effects, or response format, leaving significant gaps for a mutation tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise with a single sentence 'Create relations between entities'. It's front-loaded and wastes no words, though this brevity contributes to underspecification in other dimensions. Every word serves a purpose, making it efficient in structure.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (mutation operation with 1 parameter involving nested objects), lack of annotations, 0% schema description coverage, and no output schema, the description is incomplete. It doesn't cover behavioral aspects, parameter meanings, or expected outcomes, making it inadequate for safe and effective use by an AI agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description adds no parameter semantics beyond the input schema. With 0% schema description coverage and 1 parameter ('relations' array of objects with source, target, type), the description doesn't explain what these fields mean, valid values for 'type', or examples. It fails to compensate for the schema's lack of descriptions, leaving parameters poorly documented.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Create relations between entities' clearly states the action (create) and resource (relations between entities), but it's vague about what 'entities' refers to and doesn't distinguish from sibling tools like 'create_entities' or 'delete_relation'. It provides basic purpose but lacks specificity about the domain or system context.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites (e.g., entities must exist first), exclusions, or comparisons to siblings like 'create_entities' (for creating entities) or 'delete_relation' (for removing relations). Usage context is implied but not explicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Delete an entity and all its associated data (observations and relations)
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | Name of the entity to delete |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden. It discloses the destructive nature ('Delete... and all its associated data'), which is crucial behavioral context. However, it lacks details on permissions needed, error conditions, or what happens if the entity doesn't exist.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence that front-loads the core action and scope. Every word contributes meaning without redundancy, making it appropriately sized for a one-parameter tool.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a destructive mutation tool with no annotations and no output schema, the description adequately covers the basic action and scope. However, it lacks important context about permissions, confirmation requirements, or return values, leaving gaps for safe agent operation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, providing a clear parameter description. The tool description doesn't add any parameter-specific information beyond what's in the schema, so it meets the baseline for high schema coverage without compensating value.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the specific action ('Delete') and target resource ('an entity and all its associated data'), with explicit mention of what gets deleted ('observations and relations'). It distinguishes from sibling tools like 'delete_relation' by specifying broader scope.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives is provided. While the description implies destructive deletion, it doesn't specify prerequisites, warn about irreversible changes, or mention when to choose 'delete_entity' over 'delete_relation' or other siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Delete a specific relation between entities
| Name | Required | Description | Default |
|---|---|---|---|
| source | Yes | Source entity name | |
| target | Yes | Target entity name | |
| type | Yes | Type of relation |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It states 'Delete', implying a destructive mutation, but doesn't disclose behavioral traits such as whether deletion is permanent, requires specific permissions, has side effects (e.g., cascading deletions), or what happens on success/failure. This is a significant gap for a mutation tool with zero annotation coverage.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence with zero waste. It's appropriately sized and front-loaded, clearly stating the core action without unnecessary elaboration, making it easy to parse quickly.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity of a destructive operation with no annotations and no output schema, the description is incomplete. It lacks crucial context like what 'delete' entails (e.g., irreversible), expected outcomes, error handling, or how it differs from sibling tools. For a mutation tool, this minimal description is inadequate.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
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 three parameters (source, target, type) with basic descriptions. The description adds no additional meaning beyond what the schema provides, such as examples of relation types or how entities are identified. Baseline 3 is appropriate when the schema does the heavy lifting.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Delete') and the resource ('a specific relation between entities'), making the purpose understandable. However, it doesn't differentiate from sibling tools like 'delete_entity' or 'create_relations', which would require specifying what makes this tool unique for relation deletion versus entity deletion or relation creation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives. With siblings like 'delete_entity' and 'create_relations', it's unclear if this is for removing existing relations only, or if there are prerequisites (e.g., the relation must exist). No explicit when/when-not or alternative tools are mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get recent entities and their relations
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden but only states what the tool does, not behavioral traits like permissions needed, rate limits, or what 'recent' means (e.g., time frame). It doesn't disclose critical operational details for a read operation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence with no wasted words. It's front-loaded and appropriately sized for a simple tool.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no annotations, no output schema, and a simple tool with 0 parameters, the description is incomplete. It lacks details on what 'recent' entails, the format of returned data, or any behavioral constraints, making it insufficient for reliable use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
There are 0 parameters, and schema description coverage is 100%, so no parameter information is needed. The description adds context about retrieving 'recent' entities and relations, which is meaningful beyond the empty schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Get' and the resources 'recent entities and their relations', making the purpose understandable. It doesn't explicitly distinguish from siblings like 'search_nodes', but it's not vague or tautological.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives like 'search_nodes' or 'create_entities'. The description implies usage for retrieving recent data but doesn't specify contexts, exclusions, or prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search for entities and their relations using text or vector similarity
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. While it mentions the search functionality, it doesn't describe what happens during execution - whether it's read-only or has side effects, what permissions are required, how results are returned, or any rate limits. The description is too minimal for a search tool with no annotation support.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise - a single sentence that directly states the tool's function. There's no wasted language or unnecessary elaboration. It's front-loaded with the core purpose and uses efficient phrasing.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a search tool with no annotations, no output schema, and minimal parameter documentation, the description is insufficient. It doesn't explain what 'entities and relations' mean in this context, how results are structured, whether there are pagination or filtering options, or any operational constraints. The description leaves too many questions unanswered for effective tool use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description mentions 'text or vector similarity' which aligns with the schema's oneOf structure for the query parameter. However, with 0% schema description coverage, the description doesn't add meaningful details about parameter usage, format requirements, or search behavior. It provides basic context but doesn't compensate for the complete lack of schema documentation.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose as searching for entities and their relations using text or vector similarity. It specifies both the resource (entities and relations) and the method (text or vector similarity search). However, it doesn't explicitly differentiate from sibling tools like 'read_graph' which might also involve reading/searching operations.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives. It doesn't mention when this search tool should be used instead of 'read_graph' or other siblings, nor does it provide any context about prerequisites, limitations, or appropriate scenarios for text versus vector search.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v1.0.0create_entitiescreate_relationsdelete_entitydelete_relationread_graphsearch_nodesScored across 6 tools
Every tool has a clearly distinct purpose: create_entities and create_relations handle creation of different data types, delete_entity and delete_relation handle deletion of different data types, read_graph retrieves recent data, and search_nodes performs searches. There is no overlap or ambiguity between these functions.
All tools follow a consistent verb_noun pattern using snake_case: create_entities, create_relations, delete_entity, delete_relation, read_graph, and search_nodes. The naming is predictable and uniform throughout the set.
With 6 tools, this server is well-scoped for a memory/graph database system. Each tool serves a clear and necessary function (create, delete, read, search) without being too sparse or bloated, fitting typical expectations for such a domain.
The toolset covers core CRUD operations for entities and relations (create, delete, read, search), but lacks explicit update tools for modifying existing entities or relations. Agents can work around this by deleting and recreating, but it's a minor gap in lifecycle coverage.
Cloud-hosted MCP server for durable AI memory
Capability registry for the agentic economy. Semantic search over verified MCP server listings.
Shared cross-LLM long-term memory over MCP: semantic recall, sessions, and media (pgvector).
