A
licenseA
qualityC
maintenanceEnables AI assistants to query and analyze past Claude Code sessions, providing structured insights like file changes, decisions, errors, and git history across projects.
11
9 npm
1
MIT
claude-find
by Cavinooo
claude-find
Extrae memoria profunda de todas tus sesiones de Claude Code, cuando la necesites.
Búsqueda semántica en todas tus sesiones pasadas de Claude Code. Encuentra contexto por significado y palabras clave. Busca en las transcripciones de conversación sin procesar, no en resúmenes comprimidos, por lo que Claude obtiene la imagen completa: razonamiento, restricciones, enfoques fallidos y decisiones.
Configuración
brew install bun ollama
bunx claude-find setupsetup inicia Ollama, descarga el modelo de incrustación (embedding), establece la retención de sesiones como permanente y registra el servidor MCP con Claude Code. Las sesiones se indexan en segundo plano al iniciar. Las búsquedas funcionan de inmediato y devuelven resultados progresivamente más completos a medida que continúa la indexación.
Instala Bun y Ollama, luego ejecuta bunx claude-find setup. Detecta tu plataforma y te guía a través de cualquier cosa que falte.
Related MCP server: am-memory
Uso
En cualquier sesión de Claude Code:
/find that database migration we discussed last week
/find why we chose websockets over polling
/find the session where we kept getting timeout errors
/find refactoring the payment module across all projectsClaude busca en tus sesiones pasadas de forma semántica, encuentra las conversaciones relevantes y sintetiza el contexto: qué se intentó, qué falló, qué restricciones estableciste y qué decisiones se tomaron.
Cómo funciona
Indexa todos los archivos JSONL de sesiones de Claude Code desde
~/.claude/projects/Extrae mensajes de usuario y asistente, resúmenes compactos y rutas de archivos de las llamadas a herramientas
Enriquece cada fragmento con contexto de metadatos (proyecto, rama, archivos, fecha) para una mejor recuperación
Incrusta fragmentos de conversación usando qwen3-embedding a través de Ollama (acelerado por GPU)
Busca con semántica híbrida + palabras clave (FTS5) fusionadas mediante Reciprocal Rank Fusion
Devuelve fragmentos de conversación sin procesar para que Claude pueda sintetizar con el contexto completo
Después de actualizar, ejecuta bunx claude-find index para reconstruir el índice con las últimas mejoras.
Qué lo hace diferente
Busca en transcripciones sin procesar. No se pierde nada mediante compresión.
Retroactivo: funciona en todas las sesiones existentes de inmediato. No se necesitan ganchos.
Historial permanente: la configuración deshabilita la limpieza de sesiones de 30 días de Claude Code para que tus sesiones sean buscables para siempre.
No bloqueante: indexa en segundo plano al iniciar. Las búsquedas funcionan al instante, incluso a mitad de la indexación.
Utiliza resúmenes compactos: la propia comprensión de sesión de Claude, potenciada en la clasificación.
Indexa metadatos de llamadas a herramientas: busca por archivos tocados, errores encontrados.
Rápido: Ollama + GPU mantiene la indexación rápida y con memoria limitada.
Requisitos
Licencia
MIT
Available Tools
1 toolsearch_sessionsA
Search the full conversation history from past Claude Code sessions stored in ~/.claude/projects/. This tool has access to the complete raw transcripts of all previous sessions — including the actual back-and-forth discussion, reasoning, failed approaches, user constraints, and code decisions. Use this tool FIRST whenever the user mentions anything from a past session, asks 'what did we discuss', 'pull in context from', 'remember when we', 'how did we handle', or references any prior work. This tool searches semantically — the user doesn't need to remember exact words. Much more detailed than built-in memory.
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | What to search for — natural language description of the past session or topic | |
| max_sessions | No | Max sessions to return (default 3, max 5) | |
| max_chunks | No | Max conversation chunks per session (default 3, max 3) | |
| scope | No | 'current' searches only the current project (default), 'all' searches across all projects. Use 'all' when user says 'across all projects' or doesn't specify a project. | current |
| project_filter | No | Filter to a specific project by name (e.g. 'visk', 'myapp'). Use when user says 'in visk' or 'in the payments project'. |
TDQS
A4.4/5.0
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden. It discloses the scope of data ('complete raw transcripts', 'discussion, reasoning, failed approaches') and the semantic search nature. It does not mention any destructive actions or potential privacy concerns, but for a read-only search tool, the disclosure is sufficient.
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?
The description is concise with four sentences, starting with the core purpose and then usage guidance. Every sentence contributes meaning, though it could be slightly trimmed without loss.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description adequately explains the tool's function and when to use it, but it does not describe the return value format or content. The schema hints at output via parameters like max_sessions and max_chunks, but without an output schema, the description should explicitly state what is returned (e.g., matching sessions with chunks).
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% with detailed parameter descriptions. The tool description adds context about the underlying data ('complete raw transcripts') that enriches understanding of what the 'query' parameter searches over, going beyond the schema's literal description.
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 clearly states the tool searches 'full conversation history from past Claude Code sessions' and specifies the exact storage location. It distinguishes itself from built-in memory by claiming to be 'much more detailed', which is useful even though no siblings are listed.
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?
The description explicitly tells when to use the tool first, listing example phrases like 'what did we discuss' and 'remember when we'. It also explains that searches are semantic, reducing the need for exact words, which is a clear usage recommendation.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
1 tool update
- First observed
search_sessions
TDQS
A4.4/5.0
Scored across 1 tool
Disambiguation5/5
With only one tool, there is no possibility of confusion between tools. The tool's purpose is clearly defined.
Naming Consistency5/5
The single tool name 'search_sessions' follows a consistent verb_noun pattern, though there are no other tools to compare against.
Tool Count3/5
A single tool for searching is borderline thin; most servers of this scope would benefit from at least 2-3 tools (e.g., list_sessions, get_session). The count is at the low end of reasonable.
Completeness4/5
The tool covers the core search functionality well, but lacks complementary tools such as listing available sessions or retrieving full transcripts by ID, which would make the surface more complete.
Maintenance
ActivityInactive
ResponsivenessNo issues
Related MCP Connectors
Persistent memory for Claude Code and Cursor. Stop re-explaining your project every session.
Persistent cross-session memory shared by Codex, Claude Code, ChatGPT, and other AI agents.
Shared memory for coding agents. Stop re-explaining your codebase every session.
- SeturosOAuthcom.seturos
Shared work memory for Claude Code, Codex, Cursor and chat, scoped to each repository.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenancePersistent memory for Claude Code — a self-evolving knowledge layer that survives across sessions, grows from every conversation, and surfaces relevant context automatically.14MIT
- AlicenseNot gradedqualityDmaintenanceProvides persistent memory for Claude Code, automatically extracting and surfacing relevant context from past sessions to avoid re-explaining issues and decisions.MIT
- AlicenseNot gradedqualityAmaintenanceEnables Claude Code to search and retrieve past chat history from Claude.ai exports and Claude Code sessions, allowing the AI to reference previous conversations and decisions.MIT