Power your agent
คำสั่งของผู้เผยแพร่เอง ไม่ใช่เอนด์พอยต์ของ PlugMCP
Host a copy with our keys and logs.
npx -y @j0hanz/[email protected]Claude Code ไม่มีลิงก์ติดตั้งสำหรับคำสั่งแบบโลคัล ให้คัดลอกคำสั่งด้านล่างแล้วรันในเทอร์มินัล
claude mcp add io.github.j0hanz-memory-mcp -- npx -y @j0hanz/memory-mcp@1.7.0รันในเทอร์มินัล
{ "mcpServers": { "io.github.j0hanz-memory-mcp": { "command": "npx", "args": [ "-y", "@j0hanz/[email protected]" ] } }}claude_desktop_config.json
URL แบบรีโมตหรือคำสั่งบนเครื่องของคุณ? การติดตั้งสองแบบต่างกันอย่างไร
รันบน PlugMCP
A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.
เปิดA SQLite-backed MCP server for persistent memory storage, full-text retrieval, and relationship graph traversal.
Memory MCP provides a local, persistent memory layer for MCP-enabled assistants. It stores SHA-256-addressed memory items in SQLite with FTS5-powered full-text search, a directed relationship graph, BFS recall traversal, and token-budget-aware context retrieval — all accessible over stdio transport with no external dependencies.
retrieve_context) selects memories that fit a caller-specified token budget — no manual pagination needed.internal://instructions (Markdown guide) and memory://memories/{hash} URI template with hash auto-completion.SIGINT, SIGTERM) and no HTTP endpoints. |>=24.Use the npm package directly with npx — no installation required:
{
"mcpServers": {
"memory-mcp": {
"command": "npx",
"args": ["-y", "@j0hanz/memory-mcp@latest"]
}
}
}
[!TIP] The server uses stdio transport only; no HTTP endpoint is exposed. Stdout must not be polluted by custom logging.
Or run with Docker:
docker run --rm -i ghcr.io/j0hanz/memory-mcp:latest
Workspace file .vscode/mcp.json:
{
"servers": {
"memory-mcp": {
"command": "npx",
"args": ["-y", "@j0hanz/memory-mcp@latest"]
}
}
}
CLI:
code --add-mcp '{"name":"memory-mcp","command":"npx","args":["-y","@j0hanz/memory-mcp@latest"]}'
CLI:
code-insiders --add-mcp '{"name":"memory-mcp","command":"npx","args":["-y","@j0hanz/memory-mcp@latest"]}'
~/.cursor/mcp.json:
{
"mcpServers": {
"memory-mcp": {
"command": "npx",
"args": ["-y", "@j0hanz/memory-mcp@latest"]
}
}
}
claude_desktop_config.json:
{
"mcpServers": {
"memory-mcp": {
"command": "npx",
"args": ["-y", "@j0hanz/memory-mcp@latest"]
}
}
}
CLI:
claude mcp add memory-mcp -- npx -y @j0hanz/memory-mcp@latest
MCP config:
{
"mcpServers": {
"memory-mcp": {
"command": "npx",
"args": ["-y", "@j0hanz/memory-mcp@latest"]
}
}
}
# Pull and run (stdio mode)
docker run --rm -i \
-e MEMORY_DB_PATH=/data/memory.db \
-v memory-data:/data \
ghcr.io/j0hanz/memory-mcp:latest
MCP client config:
{
"mcpServers": {
"memory-mcp": {
"command": "docker",
"args": [
"run",
"--rm",
"-i",
"-e",
"MEMORY_DB_PATH=/data/memory.db",
"-v",
"memory-data:/data",
"ghcr.io/j0hanz/memory-mcp:latest"
]
}
}
}
src/ must update README.md and affected mcp/ mirror pages in the same PR.https://modelcontextprotocol.io/specification/2025-11-25/... links for protocol references; avoid latest and mixed legacy targets.src/server.ts.src/tools/index.ts, src/resources/index.ts, and src/prompts/index.ts.src/instructions.md match runtime behavior.npm run type-check, npm run test:fast, npm run build.store_memoryStore a new memory with content, tags, and optional type/importance. Idempotent — storing the same content+tags returns the existing hash with created: false.
Returns: { hash, created }
store_memoriesStore multiple memories in one transaction (max 50 items).
Returns: { items, succeeded, failed }
get_memoryRetrieve one memory by its SHA-256 hash.
Returns: Memory or { ok: false, error } on E_NOT_FOUND.
update_memoryUpdate content and optionally tags for an existing memory. Returns both hashes.
Returns: { old_hash, new_hash }
delete_memoryDelete one memory by hash. Cascades to related relationship rows.
Returns: { hash, deleted }
delete_memoriesDelete multiple memories by hash in one transaction.
Returns: { items, succeeded, failed }
search_memoriesFull-text search over memory content and tags using FTS5. Supports importance and type filters with cursor pagination.
Returns: { memories, total_returned, nextCursor? }
create_relationshipCreate a directed relationship edge between two memories. Idempotent.
Suggested relation_type values: related_to, causes, depends_on, parent_of, child_of, supersedes, contradicts, supports, references.
Returns: { created }
delete_relationshipDelete one directed relationship edge.
Returns: { deleted } or { ok: false, error } on E_NOT_FOUND.
get_relationshipsRetrieve relationships for a memory, with optional direction filter.
Returns: { relationships, count }
Each relationship includes from_hash, to_hash, relation_type, created_at, linked_hash, linked_content, and linked_tags.
recallSearch memories by full-text query, then traverse the relationship graph up to depth hops via BFS. Emits MCP progress notifications per hop.
Returns: { memories, graph, depth_reached, aborted?, nextCursor? }
Each item in graph uses the shape:
{ "from_hash": "...", "to_hash": "...", "relation_type": "..." }
[!NOTE]
aborted: trueindicates the traversal hit a safety limit (RECALL_MAX_FRONTIER_SIZE,RECALL_MAX_EDGE_ROWS, orRECALL_MAX_VISITED_NODES). Partial results are still returned.
retrieve_contextSearch memories and return relevance-ranked results that fit within a caller-specified token budget. Eliminates manual pagination and token counting for context window management.
Returns: { memories, estimated_tokens, truncated }
[!TIP] Token estimation is approximate (content length ÷ 4).
truncated: truemeans the budget was reached before all candidates were included.
memory_statsReturn aggregate memory and relationship stats. Takes no input.
Returns:
{
"memories": {
"total": 0,
"oldest": null,
"newest": null,
"avg_importance": null
},
"relationships": { "total": 0 },
"by_type": {}
}
[!IMPORTANT] If
MEMORY_DB_PATHis relative (including the defaultmemory_db/memory.db), it resolves from the process working directory.
[!TIP] Add
memory_db/to your.gitignoreto keep the database out of version control — it contains local session data and should not be shared or committed.
[!NOTE] Cursor values are opaque base64url-encoded tokens. Treat them as opaque and do not parse them.
StdioServerTransport) — no HTTP endpoints.stderr; stdout must remain clean for the MCP protocol.MATCH execution (non-alphanumeric characters act as delimiters, preventing FTS injection).Install dependencies:
npm install
Core scripts:
Inspect with MCP Inspector:
npx @modelcontextprotocol/inspector node dist/index.js
GitHub Actions release workflow (.github/workflows/release.yml) handles versioning, validation, and publishing via a single workflow_dispatch trigger:
workflow_dispatch (patch / minor / major / custom)
│
▼
release — bump package.json + server.json → lint → type-check → test → build → tag → GitHub Release
│
├──► publish-npm ──► publish-mcp (npm Trusted Publishing OIDC → MCP Registry)
│
└──► publish-docker (GHCR, linux/amd64 + linux/arm64)
Trigger a release:
gh workflow run release.yml -f bump=patch
Or use the GitHub UI: Actions → Release → Run workflow.
[!NOTE] npm publishing uses OIDC Trusted Publishing — no
NPM_TOKENsecret required. MCP Registry uses GitHub OIDC. Docker uses the built-inGITHUB_TOKEN.
MIT
SQLite-backed MCP server for persistent memory, full-text retrieval, and graph traversal.
{ "mcpServers": { "io.github.j0hanz-memory-mcp": { "command": "npx", "args": [ "-y", "@j0hanz/[email protected]" ] } }}เครื่องมือ
ยังไม่มีรายการเครื่องมือ เซิร์ฟเวอร์แบบรีโมตจะได้รายการหลังการตรวจสอบสถานะครั้งแรก
FAQ
คัดลอกคอนฟิก stdio สำหรับ Cursor, Claude Desktop, Claude Code หรือ VS Code ได้ในหน้านี้ คอนฟิกนี้ใช้การติดตั้งของผู้เผยแพร่ ไม่ใช่พร็อกซีของ PlugMCP
ระเบียนนี้ไม่ได้ระบุตัวแปรสภาพแวดล้อมที่จำเป็น
Memory MCP Server ทำงานแบบโลคัลผ่าน stdio
ตรวจสอบล่าสุดเมื่อ 2026-11-09 SQLite-backed MCP server for persistent memory, full-text retrieval, and graph traversal.