Power your agent
URL ของผู้เผยแพร่เอง ไม่ใช่เอนด์พอยต์ของ PlugMCP
Host a copy with our keys and logs.
https://polymnemo.purpleground-26f6d744.westus2.azurecontainerapps.io/mcpปุ่ม Claude ด้านบนจะเปิด Claude พร้อมกรอกชื่อและ URL ให้แล้ว คุณยังต้องยืนยันที่นั่นเอง
claude mcp add --transport http io.github.pcbz-polymnemo https://polymnemo.purpleground-26f6d744.westus2.azurecontainerapps.io/mcpRun in a terminal.
{ "mcpServers": { "io.github.pcbz-polymnemo": { "command": "npx", "args": [ "-y", "mcp-remote", "https://polymnemo.purpleground-26f6d744.westus2.azurecontainerapps.io/mcp" ] } }}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.
เปิดจากผู้เผยแพร่
A shared long-term memory across any LLM, over MCP.
Shared cross-LLM long-term memory over MCP: semantic recall, sessions, and media (pgvector).
Point Claude Desktop, an MCP-capable IDE, or any MCP client at one polymnemo endpoint and they share the same memories — stored in your own Postgres. Store a fact with one assistant, recall it from another; save whole sessions and reload them; even attach files, images, or video. Embeddings run locally (no embedding API key), and the server makes no generative-LLM calls.
Status: active development. Semantic memory + pgvector store, session save/reload, and multimedia memories all work; deployable to Azure Container Apps (or Cloud Run) via Terraform. Wiki · Issues
Protocols.flowchart LR
Clients["MCP clients<br/>(Claude Desktop, IDEs, …)"] -->|"/mcp · Bearer key"| P["polymnemo<br/>(MCP server)"]
P --> DB[("Postgres + pgvector<br/>text + pointers")]
P -. "large files<br/>(presigned URLs)" .-> OS[("Object storage<br/>S3 / R2")]
A request carries a bearer key (which resolves to a user_id); the tool passes
the rate-limit gate, then delegates to a MemoryService that chunks + embeds
text and stores the vectors in pgvector — large files go to object storage via
presigned URLs, with only a searchable description embedded.
Every layer is a typing.Protocol, wired together by a composition root
(context.py), so you can swap an implementation
without touching the tools:
The ping tool returns the active layers, so you can see how a running server is
wired.
Requires Python 3.11+.
python -m venv .venv
source .venv/bin/activate # Windows: .venv\Scripts\activate
pip install -e . # add ".[dev]" for the test + lint tooling
The durable store is Postgres + pgvector; the easiest hosted option is Neon (use the pooled connection string). Apply the schema once:
psql "<your-connection-string>" -f scripts/schema.sql
Copy .env.example to .env and set the database URL and at least one API key:
POLYMNEMO_DATABASE_URL=postgresql://user:pass@host/db?sslmode=require
POLYMNEMO_API_KEYS=sk-alice-secret:alice,sk-bob-secret:bob # "key:user_id" pairs
Each key maps a bearer token to a user_id; writes are scoped to that user.
polymnemo # Streamable HTTP at http://127.0.0.1:8000/mcp
Or with Docker:
docker build -t polymnemo .
docker run -e POLYMNEMO_DATABASE_URL="..." -e POLYMNEMO_API_KEYS="sk-alice-secret:alice" \
-e PORT=8080 -p 8080:8080 polymnemo
Any client that supports remote (HTTP) MCP servers with custom headers needs two things:
http://<host>:<port>/mcpAuthorization: Bearer <your-key>For clients that read an mcpServers config:
{
"mcpServers": {
"polymnemo": {
"url": "http://127.0.0.1:8000/mcp",
"headers": { "Authorization": "Bearer sk-alice-secret" }
}
}
}
Or verify with the inspector:
npx @modelcontextprotocol/inspector
# Transport: Streamable HTTP · URL: http://127.0.0.1:8000/mcp
# Header: Authorization: Bearer sk-alice-secret → call ping / remember / recall
user_id, and writes are owner-scoped (you can only
edit or delete your own memories).<server>/tokens to create, list and revoke them; a new token is shown
once and stored only as a SHA-256 hash. Deliberately not MCP tools — a
secret must never travel an LLM channel.shared) is readable by everyone ("born shared"); everything else is private
to its owner. Sessions and media default to private namespaces.remember may return several ids and recall returns the closest chunks.remember,
save_session, update and a media memory's description.
The contents of uploaded files are not scanned and are stored as you sent
them: the bytes go straight to object storage under a presigned URL and never
pass through this server. A file's description is scanned; the file is not.polymnemo exposes MCP tools for storing, searching, and managing memories:
remember, recall, list_memories, get_memory, update, forgetsave_session, load_sessioncreate_upload, confirm_upload, get_download_urlPlus a ping health check and a memory://{namespace} resource for
auto-injecting a collection. Media bytes go to object storage via presigned URLs
— never through the MCP channel — with only a searchable description embedded
(needs the blob extra).
Full arguments and return shapes live in the dedicated MCP tools reference (coming soon). See Concepts for how keys, namespaces, and chunking work.
POLYMNEMO_* environment variables (or .env) — full list in
.env.example. The essentials:
pip install -e ".[dev]"
pytest # fast, offline (stub embedder, in-memory store)
ruff check . && ruff format --check . # lint + format (enforced in CI)
Postgres tests run when TEST_DATABASE_URL points at a pgvector Postgres. CI
(.github/workflows/ci.yml) runs lint + the suite with coverage and posts a
pass/fail/coverage table to each run's summary.
polymnemo is stateless (all state in Neon + object storage), so it runs on
Azure Container Apps (primary) or Google Cloud Run with scale-to-zero.
Everything is Terraform in deploy/terraform/: shared
neon/ (Postgres) and r2/
(media bucket) roots own the durable state, and a compute root deploys a service
that reads both — so memories and media are shared across clouds.
The Azure path deploys from CI in one click: set the GitHub secrets
(scripts/setup-github-secrets.sh), bootstrap the state backend
(scripts/bootstrap-tfstate-azure.sh), then run the deploy (azure) workflow
(neon → schema → r2 → build → app). GCP is a manual failover. Full walkthrough
in docs/deploy.md.
MIT — see LICENSE.
Shared cross-LLM long-term memory over MCP: semantic recall, sessions, and media (pgvector).
{ "mcpServers": { "io.github.pcbz-polymnemo": { "url": "https://polymnemo.purpleground-26f6d744.westus2.azurecontainerapps.io/mcp", "headers": {} } }}เครื่องมือ
ยังไม่มีรายการเครื่องมือ เซิร์ฟเวอร์แบบรีโมตจะได้รายการหลังการตรวจสอบสถานะครั้งแรก
FAQ
คัดลอกคอนฟิก http สำหรับ Cursor, Claude Desktop, Claude Code หรือ VS Code ได้ในหน้านี้ คอนฟิกนี้ใช้การติดตั้งของผู้เผยแพร่ ไม่ใช่พร็อกซีของ PlugMCP
ระเบียนนี้ไม่ได้ระบุตัวแปรสภาพแวดล้อมที่จำเป็น
Polymnemo เข้าถึงได้ผ่าน HTTP
ตรวจสอบล่าสุดเมื่อ 2026-11-09 Shared cross-LLM long-term memory over MCP: semantic recall, sessions, and media (pgvector).