mcpbeat Sign in

polymnemo MCP Server

by pcbz Your server? Claim it
answering

polymnemo is answering right now. Last checked 5 min ago. It exposes 12 tools. Last commit 17 Sep 2026.

Shared cross-LLM long-term memory over MCP: semantic recall, sessions, and media (pgvector).

Uptime history 9 days of history
9 days agonow
100.0%
Uptime 24h
92 of 92 checks
12
Tools
read from the server
2564 ms
Response time
average over 24h
0
Stars
last commit 17 Sep 2026

What changed 6

Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 11 September 2026. No other catalogue keeps this.

13 Sep a tool changed version2 times that day
12 Sep a tool changed version2 times that day
11 Sep a tool changed version2 times that day
and 3 more, back to 11 September 2026

Nothing serious here today

Today is the operative word: we check polymnemo every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Three servers free · no card

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 5 min ago.

run in your terminal
claude mcp add polymnemo --transport http https://polymnemo.purpleground-26f6d744.westus2.azurecontainerapps.io/mcp
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "polymnemo": {
      "url": "https://polymnemo.purpleground-26f6d744.westus2.azurecontainerapps.io/mcp"
    }
  }
}
~/.codex/config.toml
[mcp_servers.polymnemo]
url = "https://polymnemo.purpleground-26f6d744.westus2.azurecontainerapps.io/mcp"
.cursor/mcp.json
{
  "mcpServers": {
    "polymnemo": {
      "url": "https://polymnemo.purpleground-26f6d744.westus2.azurecontainerapps.io/mcp"
    }
  }
}
.vscode/mcp.json
{
  "mcpServers": {
    "polymnemo": {
      "url": "https://polymnemo.purpleground-26f6d744.westus2.azurecontainerapps.io/mcp"
    }
  }
}

This endpoint answered with an authorization challenge. The server is running, and it signs you in through your browser: there is no API key to paste.

Available tools 12

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

confirm
confirm_upload
Confirm a media upload after you've PUT the bytes. Verifies the object exists, records its real size + checksum (and rejects an over-limit upload), then makes the memory findable via `recall` / downloadable. `id` is from `create_upload`. Returns `{memory_id, confirmed, size_bytes, content_type}`.
download
get_download_url
Get a short-lived URL to download a media memory's bytes. `id` is the media memory's id (from `create_upload` / `recall`). Returns `{memory_id, url, content_type}`.
forget
forget
Delete a memory by id. Returns `{id, deleted}` (deleted=false if absent).
load
load_session
Reload a saved session's content, one character page at a time. Page with `page` (0-based) while `has_more` is true. Returns `{session_id, content, page, page_size, total_chars, has_more}`.
memories
list_memories
List stored memories newest-first (no search query). `namespace` selects the collection (defaults to the shared namespace). Page with `next_cursor` / `has_more`. Returns `{items, total, has_more, next_cursor}`.
memory
get_memory
Fetch a single memory by its id (from `remember`/`recall`/`list_memories`).
ping
ping
Health / connectivity check. Returns server identity plus the active pluggable layers, so a client (or MCP Inspector) can confirm the connection and see how the server is wired.
recall
recall
Search memories by meaning and return the closest matches. Results are ranked by similarity and bounded by `limit` (default 8). Use the returned `next_cursor` with `has_more` to page further — you decide whether the results are enough. `namespace` selects the collection (defaults to the shared namespace). Returns `{items, total, has_more, next_cursor}`.
remember
remember
Store a memory for later semantic recall. Large content is split into smaller chunks on write (one vector each), so this may create several ids. `namespace` groups memories (defaults to the shared namespace); `tags`/`source` are optional metadata. Returns `{ids, chunks, namespace}`.
save
save_session
Persist a session's full content under `session_id` for later reload. Content is stored as ordered, losslessly-reassemblable chunks (also embedded, so it's searchable via `recall`). Re-saving the same `session_id` replaces it. Returns `{session_id, chunks, chars, namespace}`.
update
update
Replace a memory's content (re-embeds it). Returns the updated memory.
upload
create_upload
Register a file / image / video memory and get a URL to upload its bytes. The bytes never go through this channel: `description` is embedded so the file is findable via `recall`. **PUT** the raw bytes to `upload_url` sending `upload_headers` (the signed Content-Type). **Then call `confirm_upload`** — the memory stays hidden from `recall` (and the size cap is enforced) until you do. Media defaults to a private namespace. Returns `{memory_id, object_key, upload_url, upload_headers, content_type, namespace}`.

Endpoints

URLTransportStateLatencyChecked
https://polymnemo.purpleground-26f6d744.westus2.azurecontainerapps.io/mcp streamable-http sign-in 736 ms 5 min ago

Alternatives to polymnemo

same job, measured the same way
Hindsight MemPalace
by holetron

Self-hosted long-term memory for AI agents over MCP — hierarchical recall backed by pgvector

23 installs/wk local only
garnet-mcp
by tarazou9

RAG memory for LLM agents over Garnet Vector Sets: store text as embeddings, recall by meaning.

local only
I
Memforge Memory
by volsier

Team engineering memory for AI coding assistants. 47 MCP tools, pgvector semantic search.

14 installs/wk local only
I
Vector Memory
by neerajg03

Semantic document memory using Redis vector store. Save and recall files with natural language.

205 installs/wk local only
Wso2 Docs MCP Server
by iamvirul

Semantic search over WSO2 docs (APIM, MI, Choreo, Ballerina) via RAG and pgvector.

246 installs/wk local only
loci
by ivenkoolab

Cross-session memory and hybrid RAG over your notes and docs. Local-first, with cited answers.

local only
Continuum
by pouyahasanamreji

Shared memory + orchestration for your coding agents. Local-first MCP, vector RAG.

local only
Mem Context
by turbyho

Temporal memory MCP server with LanceDB vector search, weight-decay scoring, and LLM consolidation

176 installs/wk local only

polymnemo — questions

Answers built from our own checks of this server.

What can polymnemo do?
It exposes 12 tools, read directly from the server on our last check. Among them: confirm_upload, create_upload, forget, get_download_url, get_memory, list_memories and 6 more. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →
Is polymnemo working right now?
We send a real MCP handshake every 15 minutes. Over the last 24 hours 92 of 92 checks got a reply (100.0%), average response time 2564 ms. The bar chart above shows every period we have measured.
How do I connect polymnemo?
Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address. You sign in through your browser once and the client keeps the session: no key to copy, and it refuses anonymous clients.
How do you sign in to polymnemo?
No API key is involved. polymnemo answers our knock with an OAuth challenge, so you authorise it once in your browser and the client keeps the session. That is also why we see no tool list: it will not describe itself to an anonymous client, and that is the server working as intended, not a fault.
Is polymnemo open source?
Yes — it is published under the MIT licence, written in Python, 0 stars on GitHub and 4 open issues. The source link is on this page, so you can read exactly what it does with your data before you connect it.