Netcafe Memory

com.ainetcafePublished by ainetcafe.comOfficial publisherv1.1.0Updated Oct 27, 2026

Cross-session, cross-device memory for your agent: remember and recall notes. No key to start.

The publisher's own server: Ai Netcafe

VerifiedStreamable HTTPWeb executableProductivity & Workflow Knowledge & Memory

Server details

Identifier: com.ainetcafe/netcafe-memory
Transport: Streamable HTTP
Runtime: Web executable
Trust: Verified
Published: Sep 16, 2026

Security note

MCP servers receive tool arguments from a conversation and may perform external actions. Review what a server can do before you enable it, and give it only the access it needs.

The registry verified that this server's namespace belongs to ainetcafe.com, which also runs its endpoint. That identifies the publisher; it does not make the server's tools safe.

SourceWeft's checks cover whether the listing is complete and the endpoint answered; they do not review the server's code or what its tools do.

Add a badge to your README

Show readers this MCP server is listed on SourceWeft. The badge links to this page.

[![Listed on SourceWeft](https://sourceweft.com/badge/mcp/com.ainetcafe%2Fnetcafe-memory.svg)](https://sourceweft.com/mcp/com.ainetcafe%2Fnetcafe-memory?utm_source=readme&utm_medium=badge)

Overview

AI-generated overview

Hosted MCP endpoint for cross-session, cross-device agent memory: store notes with remember and retrieve them later with recall.

What you can do: Save notes to a hosted memory store keyed to an AllRouter key or an anonymous workspace token
Retrieve previously saved notes across sessions and devices
Share the same endpoint with other hosted tools such as invoice and statement extraction, SQL transpilation, résumé parsing and scheduled tasks
Call the same capabilities as plain HTTP GET requests without an MCP client
When to use it: Useful when an assistant should keep context between separate conversations or across machines without running its own storage. Also worth adding if you want a hosted, no-key memory service alongside other utility tools from the same provider.
Requirements: Remote streamable HTTP endpoint at ainetcafe.com; no package, key or environment variable is required to start. An anonymous free allowance applies, and an AllRouter key can be supplied for continued use.

Before you install

Notes are stored on a third-party hosted service, so avoid putting secrets or sensitive personal data in them. Anonymous usage is tied to a workspace token, and usage beyond the free allowance is paid; the provider states documents are processed in memory and not retained, but memory notes are the point of the service.

Installation

In SourceWeft

Open Netcafe Memory in the dashboard and add it to a workspace.
Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/com.ainetcafe%2Fnetcafe-memory/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "netcafe-memory": {
      "type": "http",
      "url": "https://ainetcafe.com/mcp/memory?s=registry"
    }
  }
}

README

ai-netcafe

[China: reachable]

Hosted tools your agent can call over MCP — and a claim you can check in one command:

json

{  "url": "https://github.com",  "tested_from": "mainland China (China Mobile backbone)",  "verdict": "unreachable: timeout (common signature of blocking or a very slow route)"}

{  "url": "https://github.com",  "tested_from": "mainland China (China Mobile backbone)",  "verdict": "unreachable: timeout (common signature of blocking or a very slow route)"}

That request was answered by a machine actually sitting on a Chinese backbone network. A monitor hosted anywhere else can only tell you GitHub is up where it is — which is not the question you were asking. That is the kind of thing we host: capabilities that are hard to get, rather than wrappers around ones that aren't.

Four focused servers

One agent profile rarely needs both spreadsheet cleanup and the Chinese lunar calendar, and every tool description costs tokens on every session. So the catalogue is served as four focused MCP endpoints — connect the one you need and pay the context cost of nothing else.

Pack	URL	What it is
Tables	`https://ainetcafe.com/mcp/table`	Messy CSV in, clean checkable table out. Dedupe, merge, transpose, wide→long, find what differs between two tables, reconcile two ledgers.
Dev kit	`https://ainetcafe.com/mcp/dev`	JSON↔YAML, validate JSON, line diff, regex test, JWT decode, SQL dialect transpile, timezone and unit conversion.
Doc flow	`https://ainetcafe.com/mcp/paper`	Markdown → PDF / Word / PowerPoint / EPUB / HTML. PDFs merged, split, rotated, watermarked.
China facts	`https://ainetcafe.com/mcp/cn`	Mainland reachability from a real backbone, statutory holidays including make-up workdays (调休), offline ID and mobile validation, lunar calendar.

All four are in the official MCP registry as com.ainetcafe/netcafe-tables, -devkit, -docflow and -china.

Nothing in these four calls a language model or a third-party API. They compute on our own servers, so results are deterministic and repeatable — and they cannot break because someone else changed their API.

Numbers come with their own proof

Anything involving counts or money returns an arithmetic check computed in code, not asserted by a model:

jsonc

// reconcile_ledger: your books vs the bank statement{  "total_a": 105.30, "total_b": 106.80, "gap": -1.50,  "only_in_a":  [{ "key": "B",  "amount": 5.00 }],  "only_in_b":  [{ "key": "C",  "amount": 7.00 }],  "mismatched": [{ "key": "A3", "a": 100.00, "b": 99.50, "diff": 0.50 }],  "arithmetic_check": {    "formula": "A 105.3 − B 106.8 = -1.5; differences explain -1.5",    "checks_out": true  }}

// reconcile_ledger: your books vs the bank statement{  "total_a": 105.30, "total_b": 106.80, "gap": -1.50,  "only_in_a":  [{ "key": "B",  "amount": 5.00 }],  "only_in_b":  [{ "key": "C",  "amount": 7.00 }],  "mismatched": [{ "key": "A3", "a": 100.00, "b": 99.50, "diff": 0.50 }],  "arithmetic_check": {    "formula": "A 105.3 − B 106.8 = -1.5; differences explain -1.5",    "checks_out": true  }}

If checks_out is false, the response says the result is untrustworthy instead of handing back a table that looks finished. Amounts are compared in integer cents, so 0.1 + 0.2 never invents a difference for someone to go chase.

Connect it

DeepSeek Harness:

Everything is also a plain GET — no MCP client, no SDK, no key:

bash

curl "https://ainetcafe.com/t/cn_holiday?date=2026-10-01"curl "https://ainetcafe.com/t/diff_text?a=one%0Atwo&b=one%0Athree"

curl "https://ainetcafe.com/t/cn_holiday?date=2026-10-01"curl "https://ainetcafe.com/t/diff_text?a=one%0Atwo&b=one%0Athree"

Charts come back as images you can paste straight into a README:

[live chart]

That image is rendered on request, right now, by the same service this page describes.

Model cost is measured, not quoted

MODEL              COST       LATENCYdeepseek-v4-flash  $0.00012    7.6sgemini-3.5-flash   $0.000341   10.0sGLM5.2             $0.001828   9.0s
cheapest: deepseek-v4-flash   fastest: deepseek-v4-flash15.2× between cheapest and priciest

MODEL              COST       LATENCYdeepseek-v4-flash  $0.00012    7.6sgemini-3.5-flash   $0.000341   10.0sGLM5.2             $0.001828   9.0s
cheapest: deepseek-v4-flash   fastest: deepseek-v4-flash15.2× between cheapest and priciest

Every number is read from the upstream usage response, not derived from a published price list. That distinction matters more than it sounds — while building this we found the obvious conversion formula was wrong for several models (one off by ~9×, another by ~3×), and only billing-delta measurement matched reality. Full method and data.

Heavier skills

The main endpoint (https://ainetcafe.com/mcp) also carries tools that do call a model, and say so:

Skill	What it does
`extract_invoices`	A batch of invoices → one ledger-ready table. Every row checked in code (net + tax = gross); the batch total re-added independently. Mixed currencies get no batch total on purpose — adding them would be an accounting error.
`extract_statement`	Bank statement PDF → transactions, with reconciliation (opening + credits − debits = closing). If it doesn't balance it says where the running total first breaks.
`transpile_sql`	SQL between dialects via a real parser, not a model — same input, same output, and syntax errors come back with line and column.
`check_resume`	Whether an ATS can actually parse a résumé. Rule-based and reproducible.
`remember` / `recall`	Cross-session memory, keyed to your AllRouter key or an anonymous workspace token.
`create_task`	Hand a recurring job to a hosted runner; it notifies you only when the result actually changes.

Full catalogue: https://ainetcafe.com/tools?s=github

Backed by open-source projects — PDFMathTranslate, GPT Academic, GPT Researcher, NextChat, LobeChat — hosted pre-configured so you can try them without installing Docker, Python, or supplying a key.

CLI

bash

npx ai-netcafe compare "<prompt>"   # multi-model comparison with real costsnpx ai-netcafe ask "<prompt>"       # single modelnpx ai-netcafe apps                 # hosted apps + source reposnpx ai-netcafe models               # models with per-million pricesnpx ai-netcafe install              # MCP config for your agent

npx ai-netcafe compare "<prompt>"   # multi-model comparison with real costsnpx ai-netcafe ask "<prompt>"       # single modelnpx ai-netcafe apps                 # hosted apps + source reposnpx ai-netcafe models               # models with per-million pricesnpx ai-netcafe install              # MCP config for your agent

Quota

Anonymous calls get a free allowance — enough to try everything here, no signup. When it runs out the response tells you how to continue; nothing fails silently. Bring your own AllRouter key and token cost is billed to your own account at direct rates with no markup:

Failed calls are not charged. Documents are processed in memory and not retained.

Disclosure

Built and run by the people behind ainetcafe.com. It is our own service, with a free tier and paid usage beyond it. Links here carry an s= tag so we can tell which channel produces real usage — it identifies the channel, not you.

MIT

Source: README.md at commit c14bb34

Tools

SourceWeft has not read this server's tools yet.

Version history

v1.1.0LatestSep 16, 2026

Score

75% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

Reached in the last 30 daysRequired25 pts
Auth declaredRequired10 pts
Tools listedRequired15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
DescriptionRequired15 pts
Logo10 pts
Documentation15 pts
License10 pts
Declare a license in the repository or the registry entry.