📄 工具详情 ⚙️ 安装教程 📚 使用教程
能力标签
🔌 MCP🤖 Agent🔄 工作流🐳 Docker🧬 Embedding🧠 Claude✨ GPT
🔌
MCP工具

SQLite内存MCP服务器

基于 Python · 让 AI 助手直接操作你的系统与工具
英文名：sqlite-memory-mcp
⭐ 10 Stars 🍴 3 Forks 💻 Python 📄 MIT 🏷 AI 7.5分
7.5AI 综合评分
MCP协议AI内存SQLite并发安全全文搜索
⬇ 下载源码 ZIP ⚙️ 配置说明
✦ AI Skill Hub 推荐

经 AI Skill Hub 精选评估，SQLite内存MCP服务器 获评「推荐使用」。这款MCP工具在功能完整性、社区活跃度和易用性方面表现出色，AI 评分 7.5 分，适合有一定技术背景的用户使用。

📚 深度解析
SQLite内存MCP服务器 是一款基于 MCP（Model Context Protocol）标准协议的 AI 工具扩展。MCP 协议由 Anthropic 开发并开源，旨在建立 AI 模型与外部工具之间的标准化通信接口，目前已被 Claude Desktop、Claude Code、Cursor 等主流 AI 工具采纳。

通过安装 SQLite内存MCP服务器，你的 AI 助手将获得额外的工具调用能力，可以用自然语言直接操控该工具的功能，无需学习复杂的命令行语法。MCP 工具的核心价值在于"一次配置，永久增强"——配置完成后，每次与 AI 对话时都可以无缝调用这些工具。

在技术实现上，MCP 工具通过标准的 JSON-RPC 协议与 AI 客户端通信，工具的功能以"工具列表"的形式暴露给 AI 模型，AI 可以按需调用。SQLite内存MCP服务器 提供了结构化的工具调用接口，使 AI 模型能够精确地理解和使用每个功能点，显著降低 AI 在工具使用上的错误率。

与传统的 API 集成相比，MCP 工具的优势在于无需编写代码——用户只需在配置文件中添加几行 JSON，即可让 AI 获得全新能力。AI Skill Hub 将 SQLite内存MCP服务器 评为 AI 评分 7.5 分，属于同类工具中的优质选择。
📋 工具概览

基于SQLite的MCP内存服务器，提供WAL并发安全、FTS5全文搜索和会话管理功能。支持Claude等AI助手的持久化记忆存储，适合需要为AI系统构建知识库和对话历史管理的开发者。

SQLite内存MCP服务器 是一款遵循 MCP（Model Context Protocol）标准协议的 AI 工具扩展。通过 MCP 协议，它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务，实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用，都可以通过自然语言在 AI 对话中直接触发，极大提升生产效率。

GitHub Stars
⭐ 10
开发语言
Python
支持平台
Windows / macOS / Linux
维护状态
轻量级项目，按需更新
开源协议
MIT
AI 综合评分
7.5 分
工具类型
MCP工具
Forks
3
📖 中文文档
以下内容由 AI Skill Hub 根据项目信息自动整理，如需查看完整原始文档请访问底部「原始来源」。

基于SQLite的MCP内存服务器，提供WAL并发安全、FTS5全文搜索和会话管理功能。支持Claude等AI助手的持久化记忆存储，适合需要为AI系统构建知识库和对话历史管理的开发者。

SQLite内存MCP服务器 是一款遵循 MCP（Model Context Protocol）标准协议的 AI 工具扩展。通过 MCP 协议，它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务，实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用，都可以通过自然语言在 AI 对话中直接触发，极大提升生产效率。

📌 核心特色
  • 通过标准 MCP 协议与 Claude、Cursor 等主流 AI 客户端深度集成
  • 提供结构化工具调用接口，显著降低 AI 集成复杂度
  • 支持 Claude Desktop 和 Claude Code 无缝接入，开箱即用
  • 可与其他 MCP 工具组合叠加，构建完整 AI 工作站
  • 轻量无侵入设计，不影响现有系统架构
🎯 主要使用场景
  • 在 Claude Desktop 对话中直接调用本地工具，实现 AI 与系统的深度联动
  • 通过自然语言驱动复杂的多步骤自动化任务，代替繁琐手动操作
  • 将多个 MCP 工具组合使用，构建个人专属 AI 工作站
以下安装命令基于项目开发语言和类型自动生成，实际以官方 README 为准。
安装命令
# 方式一：通过 Claude Code CLI 一键安装
claude skill install https://github.com/RMANOV/sqlite-memory-mcp

# 方式二：手动配置 claude_desktop_config.json
{
  "mcpServers": {
    "sqlite--mcp---": {
      "command": "npx",
      "args": ["-y", "sqlite-memory-mcp"]
    }
  }
}

# 配置文件位置
# macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
# Windows: %APPDATA%/Claude/claude_desktop_config.json
📋 安装步骤说明
  1. 确认已安装 Node.js（v18 或以上版本）
  2. 打开 Claude Desktop 或 Claude Code 的 MCP 配置文件
  3. 按「交给 Agent 安装 → Claude Desktop」标签中的 JSON 配置填入 mcpServers 字段
  4. 保存配置文件并重启 Claude 客户端
  5. 重启后，在对话中即可使用本工具
以下用法示例由 AI Skill Hub 整理，涵盖最常见的使用场景。
常用命令 / 代码示例
# 安装后在 Claude 对话中直接使用
# 示例：
用户: 请帮我用 SQLite内存MCP服务器 执行以下任务...
Claude: [自动调用 SQLite内存MCP服务器 MCP 工具处理请求]

# 查看可用工具列表
# 在 Claude 中输入："列出所有可用的 MCP 工具"
以下配置示例基于典型使用场景生成，具体参数请参照官方文档调整。
配置示例
// claude_desktop_config.json 配置示例
{
  "mcpServers": {
    "sqlite__mcp___": {
      "command": "npx",
      "args": ["-y", "sqlite-memory-mcp"],
      "env": {
        // "API_KEY": "your-api-key-here"
      }
    }
  }
}

// 保存后重启 Claude Desktop 生效
📑 README 深度解析 真实文档 完整度 94/100 查看 GitHub 原文 →
以下内容由系统直接从 GitHub README 解析整理，保留代码块、表格与列表结构。

SQLite Memory MCP Server

Features

  • WAL mode -- 10+ concurrent Claude Code sessions with no file locking conflicts
  • Hybrid search (BM25 + semantic) -- FTS5 keyword search fused with optional sqlite-vec cosine similarity via Reciprocal Rank Fusion, then re-ranked with 6 contextual signals (recency, project affinity, graph proximity, observation richness, canonical facts, active session)
  • Session tracking -- Save and recall session snapshots for context continuity across restarts
  • Task management -- Structured task CRUD with typed queries, priorities, sections, due dates, and recurring tasks
  • Kanban board -- Optional HTML report generator for visual task overview via GitHub Pages
  • Cross-project sharing -- Optional project field scopes entities; omit it to share across all projects
  • Cross-machine sync -- Bridge tools push/pull shared entities between machines via a private git repo
  • Premium runtime boundary -- The OSS core can gate-load a separate private premium repo via signed entitlement checks, signed artifact manifests, signed control-plane policy, explicit owner approval, audit logging, cached revocation-aware policy fallback, and local revocation
  • Drop-in compatible core -- All 9 tools from @modelcontextprotocol/server-memory work identically in sqlite_memory, with 47 more tools available from companion servers
  • Zero required dependencies beyond stdlib -- Only fastmcp is required for MCP protocol; sqlite3 is Python stdlib. Optional orjson, sqlite-vec, and sentence-transformers add speed and semantic search
  • Automatic FTS sync -- Full-text index stays in sync with every write operation
  • JSONL migration -- Optionally import existing memory.json knowledge graphs on first run

Premium feature packs

The premium layer is not meant to be a vague "enterprise edition". It is structured as a set of gated operational packs that sit on top of the OSS memory core.

Entitlements can now be modular:

  • choose packs
  • choose explicit features
  • combine both in one entitlement
  • rely on dependency expansion so high-level premium surfaces pull in the lower-level capabilities they need

That means a customer can license one pack, one feature, or a hybrid bundle without forcing the whole private runtime scope on every deployment.

Commercially, numeric pricing is intentionally not published in this OSS README. Serious paid prospects receive a scoped questionnaire first, then a customized offer that is valid for 7 working days.

1. access_governance

  • acl_rbac
  • governance_audit

This is the control plane for customers that need scoped trust, explainable decisions, and audit-safe premium workflows.

2. communication_context

  • multi_mailbox_ingestion
  • cross_mailbox_context

This pack turns memory into governed communication context instead of passive storage. It is where shared inboxes, thread memory, and client-scoped cross-mailbox views become first-class premium surfaces.

3. client_memory_twin

  • client_memory_twin
  • human_approved_notes

Dependency expansion also brings in memory_action_snapshots, client_history_notes, canonical_facts, and provenance-aware context. The result is a live client twin built from trusted facts, approved notes, action checkpoints, and surrounding communication state.

4. briefing_suite

  • instant_briefing
  • team_digest
  • chief_of_staff_queries

This is the fastest-to-sell premium layer because it removes cold starts before calls, emails, or meetings. It combines ranking, query templates, partner/team digests, and scoped memory retrieval into concise operator briefings.

5. commitment_radar

  • commitment_radar
  • silence_drift_detection

This pack is about not dropping the ball. It detects commitments, blockers, deadlines, stale threads, and drift before they become visible operational failures.

6. decision_ledger

  • decision_ledger
  • provenance_pointers

This pack makes premium memory defensible. Important conclusions can be traced back to governance decisions, human-approved promotion, and source-linked provenance instead of vague AI summaries.

7. custom_design_surface

  • custom_design_tab

This is the premium operator UI layer. It lets an entitled user shape a live working view over premium rows, grouping, risk, mailbox/client focus, and custom search/sort surfaces without flattening everything back into the OSS task model.

8. protected_operator_surface

  • password_protected_views

This pack adds local password-gated premium views on top of the Custom Design surface for the highest-sensitivity operator slices, so a premium view can require an explicit per-session unlock before it renders its real rows.

Feature-level premium surfaces

On top of the pack structure, the private runtime now exposes concrete premium-only features for the most valuable operator workflows:

  • password_protected_views for especially sensitive client, governance, or operator-specific surfaces inside the premium tray
  • instant_briefing for fast pre-call or pre-mail context
  • commitment_radar for open commitments, deadlines, blockers, and stale follow-ups
  • client_memory_twin for a scoped memory profile per client
  • decision_ledger for governance plus provenance-backed review trails
  • chief_of_staff_queries for questions like what depends on me, what is blocked, what changed recently, and who is risky
  • team_digest for internal handoff and management-style summaries
  • silence_drift_detection for unanswered threads and slow-moving risk
  • cross_mailbox_context for unified client context across multiple inboxes

High-control deployment surface

The commercial design still assumes that the local machine may be untrusted.

  • explicit entitlements
  • signed artifact manifests over the private runtime entrypoint
  • signed control-plane policy with cached offline fallback
  • remote issuer delivery for entitlements / manifests / policy over URL + runtime headers when desired
  • local revocation
  • owner approval for protected runtime loading
  • host/runtime compatibility checks plus minimum protection phase enforcement
  • installation fingerprinting for audit correlation
  • password-protected premium views for the highest-sensitivity operator surfaces
  • separate private runtime packaging
  • optional extra service boundaries for the most sensitive premium logic

The point is not obfuscation theater. The point is to keep premium execution gated, auditable, and operationally controllable.

Installation

Two-minute install + demo

Use this path when you want to verify the install before wiring Claude Code:

```bash git clone https://github.com/RMANOV/sqlite-memory-mcp.git cd sqlite-memory-mcp python -m venv .venv source .venv/bin/activate pip install -e ".[gui,dev]"

Install from source

pip install -e .

pip install -e ".[gui,vector,speed]"

Setup

```bash

One-time setup on each machine

mkdir -p ~/.claude/memory/bridge cd ~/.claude/memory/bridge git init

Install PyQt6 (one-time)

pip install PyQt6

Claude Code quick start

```bash

Usage

```python

FTS5 Search Examples

The search_nodes tool uses SQLite FTS5 with BM25 ranking. Queries support the standard FTS5 syntax:

```

Example usage

```python

Seed a safe demo DB with one entity, one task, one note, a reminder,

Verify Python, FastMCP, SQLite schema, DB write access, and optionally

Optional desktop demo against the demo DB.

SQLITE_MEMORY_DB=/tmp/sqlite-memory-mcp-demo.db task-tray ```

If sqlite-memory-doctor is clean and the tray opens the demo DB, the local install is healthy enough to connect to Claude Code.

Optional extras

Optional: run the full stack as one all-in-one server instead

claude mcp add --scope user sqlite_unified -- python /path/to/unified_server.py 


If you install the package instead of running from a checkout, the same servers are available as console scripts:
bash claude mcp add --scope user sqlite_memory -- sqlite-memory-core claude mcp add --scope user sqlite_tasks -- sqlite-memory-tasks claude mcp add --scope user sqlite_session -- sqlite-memory-session claude mcp add --scope user sqlite_bridge -- sqlite-memory-bridge claude mcp add --scope user sqlite_collab -- sqlite-memory-collab claude mcp add --scope user sqlite_entity -- sqlite-memory-entity claude mcp add --scope user sqlite_intel -- sqlite-memory-intel

Optional all-in-one server

claude mcp add --scope user sqlite_unified -- sqlite-memory-unified 


Codex can use the same console-script servers:
bash codex mcp add sqlite_memory -- sqlite-memory-core codex mcp add sqlite_tasks -- sqlite-memory-tasks codex mcp add sqlite_session -- sqlite-memory-session codex mcp add sqlite_bridge -- sqlite-memory-bridge codex mcp add sqlite_collab -- sqlite-memory-collab codex mcp add sqlite_entity -- sqlite-memory-entity codex mcp add sqlite_intel -- sqlite-memory-intel

Optional all-in-one server

codex mcp add sqlite_unified -- sqlite-memory-unified ```

Manual Configuration

Prefer claude mcp add --scope user ... above and verify with claude mcp list; prefer codex mcp add ... and verify with codex mcp list for Codex. Some Claude Code builds no longer surface legacy ~/.claude/settings.json mcpServers entries in claude mcp list, and Codex uses its own ~/.codex/config.toml, so one client's manual block does not prove the other client can load the servers.

If you need a manual fallback, add these server/file pairs to your ~/.claude/settings.json under mcpServers:

MCP server namePython entry filePurpose
sqlite_memoryserver.pyCore 9 drop-in memory tools
sqlite_taskstask_server.pyTask CRUD, digest, archive, overdue bump
sqlite_sessionsession_server.pySession recall, project search, health, resume
sqlite_bridgebridge_server.pyCross-machine bridge sync, sharing review
sqlite_collabcollab_server.pyCollaborator and public-knowledge workflows
sqlite_entityentity_server.pyTask-entity linking and merge helpers
sqlite_intelintel_server.pyContext assessment and enrichment tools
sqlite_unifiedunified_server.pyOptional all-in-one server that mounts the full 57-tool OSS stack

Each server should share the same environment values:

"env": {
  "SQLITE_MEMORY_DB": "/home/user/.claude/memory/memory.db",
  "BRIDGE_REPO": "/home/user/.claude/memory/bridge"
}

The SQLITE_MEMORY_DB environment variable controls where the database is stored. If omitted, it defaults to ~/.claude/memory/memory.db. BRIDGE_REPO is only needed for bridge/collab flows.

Tool Reference

The 57 OSS tools are grouped by MCP server:

MCP serverTool countTools
sqlite_memory9create_entities, add_observations, create_relations, delete_entities, delete_observations, delete_relations, read_graph, search_nodes, open_nodes
sqlite_session5session_save, session_recall, search_by_project, knowledge_health, resume_context
sqlite_tasks8create_task_or_note, upsert_note_by_title_project, update_task, query_tasks, find_by_title, task_digest, archive_done_tasks, bump_overdue_priority
sqlite_bridge7bridge_push, bridge_pull, bridge_status, bridge_doctor, assign_task, review_shared_tasks, process_recurring_tasks
sqlite_collab9manage_collaborators, share_knowledge, review_shared_knowledge, request_publish, cancel_publish, search_public_knowledge, rate_public_knowledge, get_knowledge_ratings, update_verification
sqlite_entity7link_task_entity, unlink_task_entity, get_task_links, get_entity_tasks, suggest_task_links, find_entity_overlaps, merge_entities
sqlite_intel12assess_context, queue_clarification, record_human_answer, extract_candidate_claims, promote_candidate, build_context_pack, explain_impact, audit_memory, replay_memory, govern_fact, list_memory_issues, enrich_context

Hook integration

You can extend your Claude Code session hook (~/.claude/hooks/session_context.py) to automatically recall recent sessions and inject them into the system prompt. See examples/session_context_hook.py for a reference implementation.

Section-based workflow

Tasks are organized into five sections following a GTD-style workflow:

SectionPurpose
inboxUnprocessed tasks (default)
todayTasks to complete today
nextNext actions queue
somedayDeferred / maybe
waitingBlocked on someone else

Shared Module -- `db_utils.py`

All Python files share constants and helpers via db_utils.py:

from db_utils import (
    DB_PATH, BRIDGE_REPO,
    TASK_SECTIONS, TASK_PRIORITIES, TASK_STATUSES,
    PRIORITY_RANK, PRIORITY_COLORS,
    get_conn, now_iso, parse_iso_date, is_overdue,
    build_priority_order_sql, priority_sort_key,
)

This eliminates duplication of DB connection setup, task constants, and timestamp helpers across server.py, task_tray.py, and the utility scripts.

Competitor Comparison

Featuresqlite-memory-mcpOfficial MCP Memoryclaude-mem0@pepk/sqlitesimple-memorymcp-memory-servicememsearchmemory-mcpMemoryGraph
StorageSQLiteJSONL fileMem0 CloudSQLiteJSON fileChromaDBQdrantSQLiteNeo4j
Concurrent 10+ sessionsWAL modefile lockscloudno WALfile locksyesyesnoyes
Hybrid search (BM25 + vector)yes (RRF fusion)substringnononovector onlyvector onlynoCypher only
Session trackingbuilt-innononononononono
Task managementbuilt-innononononononono
Cross-project sharingproject fieldnononononononono
Drop-in compatible9/9 toolsbaselinenopartialnononopartialno
Setup effortpip installnpxAPI key + pippipnpxDocker + pipDocker + pippipDocker + Neo4j
Dependenciessqlite3 (stdlib)Node.jsCloud APIsqlite3Node.jsChromaDBQdrantsqlite3Neo4j

Convergent evolution: sqlite-memory-mcp vs GBrain

GBrain — Garry Tan's structured knowledge layer for AI agents — launched 2026-04-10. It and sqlite-memory-mcp arrived independently at the same architectural conclusions: local-first storage, hybrid lexical + vector search fused via Reciprocal Rank Fusion, rule-based zero-LLM entity extraction, and a memory-consolidation cycle (GBrain calls it dream, sqlite-memory-mcp calls it reflect). When two solo founders converge on the same architecture, the design space is real.

The two projects ship different bets for different deployments. Public git history establishes that sqlite-memory-mcp's hybrid search shipped on 2026-03-18 (commit feat(search): add hybrid semantic search via sqlite-vec + RRF fusion) — twenty-three days before GBrain's first public release.

AxisGBrainsqlite-memory-mcp
Initial public release2026-04-10**2026-03-01** (v0.1.0, 40-day lead)
Hybrid search (BM25 + vector + RRF)shipped 2026-04-10**shipped 2026-03-18** (23-day lead)
Storage primitiveMarkdown files in git + PGLite (embedded Postgres) + pgvectorSingle SQLite file (FTS5 + sqlite-vec) + bridge git repo
Infrastructure footprintPostgres runtime + git remote + LLM APISingle binary, single file, optional local embeddings
EmbeddingsOpenAI API (network call per page write)sentence-transformers, fully local
Memory consolidation"dream cycle" (uses LLM)reflect_audit Phase 0.5 — **deterministic SQL, no LLM cost**
Per-candidate reviewatomic store-level outputper-row accept / reject / defer with apply snapshots
Cross-machine syncgit remote of the brain repobridge JSON + per-field LWW-Register CRDT (proven 2000+ tasks across 3 machines)
Source of truthMarkdown (human-readable)SQLite + JSON bridge exports (machine-portable)
Air-gapped / regulated deploymentblocked by OpenAI embedding requirement**fully supported** (no external network in hot path)
Companion stackGStack (Garry's Claude Code setup)MCP-native, works with any MCP client (Claude Code, Codex, Cursor)

Where each one wins:

  • GBrain is right for teams that want a markdown-first knowledge base, are happy paying for OpenAI embeddings on every page write, and benefit from Garry Tan's distribution. The forthcoming hosted gbrain.io targets teams that don't want to run their own runtime.
  • sqlite-memory-mcp is right for solo developers, privacy-first / offline / embedded deployments, regulated environments where data cannot reach OpenAI (DoD, healthcare, finance), and anyone who needs the consolidation pipeline to run on a Raspberry Pi or inside an air-gapped network. The deterministic Phase 0.5 audit produces real candidate counts with zero LLM cost per run.

This is convergent validation, not derivative work. The architecture is decided; the markets diverge.

FAQ: how is this different from sqlite.ai / sqlite-vector?

sqlite.ai is adjacent, not identical. It is a broader SQLite platform around cloud sync, extensions, AI inference, vector search, agent memory, and MCP tooling. Its related projects include sqlite-memory, a Markdown-based agent memory system, and sqlite-vector, a vector-search extension for embedded SQLite workloads.

sqlite-memory-mcp is focused on local-first MCP memory governance for coding agents, not on vector search as the center of the product:

- WAL-backed task, session, entity, and note memory in one local SQLite file - FTS5-first retrieval, with vector search as an optional backend - cross-machine bridge sync for private multi-machine workflows - event/provenance tracking for memory mutations - reviewable consolidation instead of silent memory rewriting - debate/protocol workflows for conductor, executor, and devil's advocate agents - an explicit OSS/premium runtime boundary with signed entitlement, manifest, and policy checks

sqlite-vec is therefore not the product center; it is one possible local retrieval backend. If sqlite-vector proves better for this workload, it can become a candidate backend. The harder problem this project targets is memory governance: how agents remember, revise, sync, debate, and promote durable context without turning the memory store into an unreviewable pile of contradictions.

🇨🇳 中文文档镜像 AI 翻译 2026-05-24
英文原文章节由系统翻译为中文摘要，便于快速理解。完整原文见上方 "📑 README 深度解析"。
📌 简介

SQLite 内存 MCP 服务器概述

⚡ 功能介绍

SQLite 内存 MCP 服务器功能

📋 环境依赖

环境依赖与系统要求

🛠 安装步骤（Docker/pip/源码）

安装 SQLite 内存 MCP 服务器

🚀 使用教程

使用 SQLite 内存 MCP 服务器

⚙️ 配置说明（含 MCP / env）

配置 SQLite 内存 MCP 服务器

🔌 API 说明

SQLite 内存 MCP 服务器 API

🔄 工作流/模块

SQLite 内存 MCP 服务器工作流

❓ FAQ 摘要

SQLite 内存 MCP 服务器常见问题

🎯 aiskill88 AI 点评 B 级 2026-05-21

创新的MCP内存解决方案，采用SQLite+WAL确保安全，FTS5搜索功能完整。代码量小，但星数偏低，需更多社区验证。

📚 实用指南（长尾问题）
适合谁
  • 需要让 Claude / Cursor 操作本地工具的 AI 工程师
  • 构建多智能体协作系统的 Agent 开发者
  • 构建企业知识库 / RAG 检索应用的团队
最佳实践
  • 配置 MCP 服务器时建议使用 stdio 传输 + JSON-RPC，避免暴露公网
  • 生产部署优先使用 Docker Compose 隔离依赖，并挂载 volume 持久化数据
  • Agent 任务先做 dry-run 验证工具调用链，再开启自主执行
常见错误
  • API key 直接提交到 git 仓库（请用 .env 并加入 .gitignore）
  • MCP 配置路径拼错或权限不足，重启 Claude Desktop 才生效
  • 容器内无法访问宿主机 localhost — 使用 host.docker.internal
  • Python 依赖冲突：建议用 venv / uv 隔离环境
部署方案
  • Docker：sqlite-memory-mcp 提供官方镜像，docker compose up 一键启动
  • 云端托管：可放在 Vercel / Railway / Fly.io 等 PaaS 平台
相关搜索
sqlite-memory-mcp 中文教程sqlite-memory-mcp 安装报错怎么办sqlite-memory-mcp MCP 配置sqlite-memory-mcp Docker 部署sqlite-memory-mcp Agent 工作流sqlite-memory-mcp 与同类工具对比sqlite-memory-mcp 最佳实践sqlite-memory-mcp 适合谁用
⚡ 核心功能
👥 适合谁
  • 需要让 Claude / Cursor 操作本地工具的 AI 工程师
  • 构建多智能体协作系统的 Agent 开发者
  • 构建企业知识库 / RAG 检索应用的团队
⭐ 最佳实践
  • 配置 MCP 服务器时建议使用 stdio 传输 + JSON-RPC，避免暴露公网
  • 生产部署优先使用 Docker Compose 隔离依赖，并挂载 volume 持久化数据
  • Agent 任务先做 dry-run 验证工具调用链，再开启自主执行
⚠️ 常见错误
  • API key 直接提交到 git 仓库（请用 .env 并加入 .gitignore）
  • MCP 配置路径拼错或权限不足，重启 Claude Desktop 才生效
  • 容器内无法访问宿主机 localhost — 使用 host.docker.internal
  • Python 依赖冲突：建议用 venv / uv 隔离环境
👥 适合人群
Claude Desktop / Claude Code 用户AI 工具开发者需要扩展 AI 能力的专业人士自动化工程师
🎯 使用场景
  • 在 Claude Desktop 对话中直接调用本地工具，实现 AI 与系统的深度联动
  • 通过自然语言驱动复杂的多步骤自动化任务，代替繁琐手动操作
  • 将多个 MCP 工具组合使用，构建个人专属 AI 工作站
⚖️ 优点与不足
✅ 优点
  • +MIT 协议，可免费商用
  • +标准化 MCP 协议，生态互联性强
  • +与 Claude 官方生态无缝对接
  • +即插即用，配置简单快捷
⚠️ 不足
  • −依赖 Claude 客户端，非 Claude 用户无法使用
  • −MCP 协议仍在持续演进，接口可能变更
  • −需要一定的配置步骤
⚠️ 使用须知

AI Skill Hub 为第三方内容聚合平台，本页面信息基于公开数据整理，不对工具功能和质量作任何法律背书。

建议在沙箱或测试环境中充分验证后，再部署至生产环境，并做好必要的安全评估。

📄 License 说明

✅ MIT 协议 — 最宽松的开源协议之一，可自由商用、修改、分发，仅需保留版权声明。

🔗 相关工具推荐
github-mcp-server MCP工具
GitHub官方MCP服务器实现，使AI助手能直接操作GitHub仓库、问题、拉取请求等资源。采用Go语言开发，高性能稳
全市场股票行情MCP接口
一个基于MCP协议的开源股票数据接口工具，支持A股、美股及港股的实时行情与基金数据查询。它允许AI助手直接获取金融市场数
MCP 服务器资源汇总
汇集开源MCP（模型上下文协议）服务器的权威目录库。为开发者提供丰富的MCP服务器实现和集成方案，支持AI应用快速扩展功
playwright-mcp MCP工具
基于Playwright的MCP协议服务器实现，提供浏览器自动化能力。支持网页交互、截图、数据采集等功能，适合开发者集成
📰 相关 AI 新闻
OpenAI 最新产品与研究动态
AI 资讯 · 知识关联
Claude Code 最新功能与使用技巧
AI 资讯 · 知识关联
AI Agent 自主化能力最新进展
AI 资讯 · 知识关联
Claude Code 最新功能与使用技巧
AI 资讯 · 知识关联
🍿 AI 圈相关吃瓜
AutoGPT 自主完成了任务：把我的文件夹全部重命名了
AI 圈观察
配了5个 MCP 工具，Claude 一个都没用
AI 圈观察
Filesystem MCP 帮 Claude 找文件，找了整个 node_modules
AI 圈观察
🗺️ 相关解决方案
mcp
mcp-server-setup
agent
ai-agent-workflow
workflow
ai-workflow-templates
docker
docker-deploy
🧩 你可能还需要
基于当前 Skill 的能力图谱，自动补全的工具组合
技能寻求者
MCP · Agent · 工作流
natively-cluely-ai-assistant — Claude Skill 中文使用文档
免费开源的AI面试助手，实时转录，隐蔽模式，局部RAG，BYOK。无订阅，防止数据泄露。
gptme Agent工作流
MCP · Agent · 工作流
LEANN AI技能包
MCP · Agent · 工作流
total-agent-memory MCP工具
为Claude Code和Codex CLI提供持久化记忆功能的开源MCP工具。自动提取知识图谱，支持多轮对话上下文保留，适合需要长期记忆和
MassGen多智能体系统
MCP · Agent · 工作流
❓ 常见问题 FAQ
支持，采用SQLite WAL模式确保并发安全
💡 AI Skill Hub 点评

AI Skill Hub 点评：SQLite内存MCP服务器 的核心功能完整，质量良好。对于Claude Desktop / Claude Code 用户来说，这是一个值得纳入个人工具库的选择。建议先在非生产环境试用，再逐步推广。

⬇️ 获取与下载
⬇ 下载源码 ZIP

✅ MIT 协议 · 可免费商用 · 直接从 aiskill88 服务器下载，无需跳转 GitHub

📚 深入学习 SQLite内存MCP服务器
查看分步骤安装教程和完整使用指南，快速上手这款工具
⚙️ 安装教程 📚 使用教程
🌐 原始信息
原始名称 sqlite-memory-mcp
原始描述 开源MCP工具：SQLite-backed MCP Memory Server with WAL concurrent safety, FTS5 search, session。⭐10 · Python
Topics MCP协议AI内存SQLite并发安全全文搜索
GitHub https://github.com/RMANOV/sqlite-memory-mcp
License MIT
语言 Python
🔗 原始来源
🐙 GitHub 仓库  https://github.com/RMANOV/sqlite-memory-mcp

收录时间：2026-05-20 · 更新时间：2026-05-22 · License：MIT · AI Skill Hub 不对第三方内容的准确性作法律背书。