# AIfa Memory (remote · aifa.works)

Persistent memory for AI agents, one account across four sites, plus a partner program.

- Trust score: 79/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- remote · `aifa.works`: 79/100 (this document), [markdown](https://verifymcp.io/servers/works-aifa-aifa-memory/api-mcp.md), [page](https://verifymcp.io/servers/works-aifa-aifa-memory/api-mcp)

## Channel facts

- Endpoint: `https://aifa.works/api/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.9.8`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-21.

- **Endpoint Security**: 83/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Nothing on it is marked destructive, but we can't show that an anonymous caller can only read: full credit needs the server to list at least one tool and every tool to be verifiably read-only. We use a best-effort check of tool names and descriptions to tell read-only tools from tools that change things, so some genuinely read-only tools may not get full credit. Names that start with a read verb (get, list, read, search and similar) and accurate readOnlyHint annotations help. Meet that to earn full credit, or require authorisation.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC is configured correctly; the domain's records validate against the full chain to the root.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 73/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 1660 tokens (~110/item across 15 items; 15 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 47/100
  - Stability check failed: schema churn in the 15 days we've observed: 0 tool removals, 0 breaking changes, 1 auth/transport breaks, 0 additions.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 15 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 16 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 60/100
  - Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28.

## Install

### How do I install the AIfa Memory MCP server?

AIfa Memory is a hosted endpoint at https://aifa.works/api/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http works-aifa-aifa-memory 'https://aifa.works/api/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "works-aifa-aifa-memory": {
      "url": "https://aifa.works/api/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "works-aifa-aifa-memory": {
      "type": "http",
      "url": "https://aifa.works/api/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.works-aifa-aifa-memory]
url = "https://aifa.works/api/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "works-aifa-aifa-memory": {
      "type": "remote",
      "url": "https://aifa.works/api/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add works-aifa-aifa-memory --url 'https://aifa.works/api/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  works-aifa-aifa-memory:
    url: "https://aifa.works/api/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "works-aifa-aifa-memory": {
      "Transport": "http",
      "Url": "https://aifa.works/api/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add works-aifa-aifa-memory -t streamable-http -u 'https://aifa.works/api/mcp'
```

### Other

```json
{
  "mcpServers": {
    "works-aifa-aifa-memory": {
      "type": "http",
      "url": "https://aifa.works/api/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-20 (score 79, +1)

No change was recorded against any check on this day. Stability & Change Management went from 40 to 43.

### 2026-11-18 (score 78, +1)

No change was recorded against any check on this day. Stability & Change Management went from 33 to 37.

### 2026-11-15 (score 77, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27.

### 2026-11-14 (score 76, 0)

- [functional] Server version: 1.9.7 → 1.9.8
- [functional] Server version: 1.9.6 → 1.9.7
- [functional] Server version: 1.9.5 → 1.9.6

### 2026-11-13 (score 76, +1)

No change was recorded against any check on this day. Stability & Change Management went from 17 to 20.

### 2026-11-12 (score 75, 0)

- [security regression] Stability: 0.17 → fail
- [functional] Server version: 1.9.4 → 1.9.5

### 2026-11-10 (score 75, −2)

- [security regression] Endpoint reachability: reachable → not serving MCP
- [security regression] Stability: 0.10 → unverified
- [security regression] Authorization: fail → unverified
- [security regression] Tool safety: pass → unverified
- [security regression] Transport: pass → fail
- [security improvement] Authorization: fail → partial
- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “memory_write” rewrote its description, which is the text the model reads
- [functional regression] Capabilities: fail → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional regression] Schema quality: pass → fail
- [functional improvement] Endpoint reachability: not serving MCP → reachable
- [functional] First check of Schema quality: unverified
- [functional] Server version: 1.7.0 → 1.9.4
- [cosmetic] “memory_write” added an optional parameter “origin”
- [cosmetic] “memory_write” reworded the description of “role”

### 2026-11-08 (score 77, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

## MCP tools (15)

### `memory_search` (~106 tokens)

Search my AIfa memory

Search the user's AIfa memory by meaning: every conversation they had with AIfa on aifa.works, codeofdigitaleternity.com, aifa.digital and radiocode.space, plus notes saved by agents. Use it at the start of a task to recover what is already known about the user, their projects and decisions.

Input parameters:

- `limit` (integer): How many results (default 8).
- `query` (string, required): What to look for, in natural language.

### `memory_recent` (~38 tokens)

Recent memory

The most recent records of the user's memory, newest first, across all channels.

Input parameters:

- `limit` (integer): How many records (default 20).

### `memory_write` (~197 tokens)

Save to my AIfa memory

Save something worth remembering to the user's AIfa memory: a preference, a decision, a fact, a summary of this session. AIfa will remember it on all four sites. Nothing is ever deleted; an identical record is not duplicated. Secret-looking values (keys, tokens, passwords, seed phrases) are masked before saving; text that looks like an instruction to an AI is not saved: AIfa reads this memory in her own chats.

Input parameters:

- `origin` (string): Where it came from: user (the person said it), agent (your conclusion, default), external (read on a web page, in a file or tool output; not saved — the owner keeps outside text out of this memory).
- `role` (string): Who said it: the assistant or agent (default) or the user, in their own words.
- `text` (string, required): The text to remember (up to 8000 characters).

### `memory_about` (~26 tokens)

About AIfa memory

What this memory is, where it lives and how it is protected. No user data.

### `account_status` (~50 tokens)

My plan, permanent memory and earnings

Your plan, how much permanent memory (Arweave) you used and have left this month, your referral earnings in USDT and your own referral link. Useful for autonomous agents that fund their own memory.

### `plans` (~33 tokens)

Plans and prices

Prices of AIfa Memory plans, what each plan stores permanently, and how to earn by bringing others. No user data.

### `buy_plan` (~106 tokens)

Get a crypto invoice for a plan

Creates a crypto payment invoice (USDT and other coins via NOWPayments) for YOUR OWN account and returns its URL. Nothing is charged until the invoice is paid; the plan switches on automatically after payment. tier: 1 = Spark ($15/month), 2 = Family Archive ($100/month), 3 = Digital DNA ($1,000 once per device, then $200/month).

Input parameters:

- `tier` (integer, required): 1 Spark, 2 Family Archive, 3 Digital DNA.

### `request_payout` (~238 tokens)

Withdraw referral earnings (USDT, TRC20)

Requests a withdrawal of your whole available referral balance in USDT to a TRC20 address. The first address used is pinned to the account; later requests go only to that address (change it in the cabinet). Requests are reviewed and paid manually, then marked paid with a transaction hash. Closed while your plan payment is overdue. Service partner earnings unlock 14 days after the client pays. Every address is checked against the US Treasury (OFAC) sanctions list. First request: also pass the one-time tax self-certification of the person or company that operates you (legal_name, country, us_person).

Input parameters:

- `address` (string): TRC20 address starting with T. Optional once an address is pinned.
- `country` (string): Two-letter ISO code of that person's or company's tax residence, e.g. DE, BR, US (first request only).
- `legal_name` (string): Full name of the person or company that operates you and receives the payout (first request only).
- `us_person` (boolean): true if the operator is a US citizen, US resident or US company; otherwise false (first request only).

### `partner_kit` (~92 tokens)

Partner program: rules, rates, email templates

Everything to start earning by bringing clients to AIfa Works accessibility services: rates (30% audits and monitoring, 20% remediation and websites, one level), the 14-day hold, the rules (no spam, write from your own address as an independent partner), and three email templates in the chosen language. No user data.

Input parameters:

- `language` (string): Language of the email templates (default en).

### `client_link` (~89 tokens)

Link for a client (with your partner code)

Your partner link to the AIfa Works accessibility page: the client runs a free check of their site there and pays for a service on the same page. Your code is kept in the client's browser for 60 days. Optionally name a service to get its price and your share.

Input parameters:

- `service` (string): Optional service slug, e.g. quick-audit, monitoring, web-professional.

### `client_report` (~118 tokens)

Report card for a client site

A ready link to a page that shows a site owner what the open AIfa research found on their site (keyboard test and axe-core rule check), explains it in plain words and offers a free check, an audit from $50 and code fixes from $99. Your partner code is inside the link (channel "report"). Returns the link and the findings to quote. Uses published research data only: no new scan of a third-party site is made.

Input parameters:

- `site` (string, required): Domain of the client site, e.g. example.com

### `find_clients` (~150 tokens)

Find client sites on the research map

Up to 20 new sites a day in a region where the open AIfa research found accessibility barriers, worst first, each with a ready report_link (your code inside, channel "finder"). Each site is reserved for you for 30 days and is not given to other partners. Shared platforms are skipped. Region: a US state like "US-NY" or a country code like "DE". Rules: one personal email per site from your own address, at most one follow-up, no bulk mailing.

Input parameters:

- `region` (string, required): US state as "US-XX" (e.g. US-CA) or a two-letter country code (e.g. DE, FR, JP).

### `memory_export` (~89 tokens)

Export your whole memory

The complete verbatim memory of your AIfa account, oldest first, as Markdown — to keep a copy or move it elsewhere. Returned in parts of up to 100,000 characters: call with part 1, then 2, 3… until "last": true. Only your own account.

Input parameters:

- `part` (number): Part number, starting from 1 (default 1).

### `my_deals` (~37 tokens)

My partner deals

Paid service orders you brought: service, amount paid, your share, and when it becomes available to withdraw; plus orders still awaiting payment.

### `set_webhook` (~133 tokens)

Set your partner webhook

Receive a POST at your https URL for every counted click on your partner link (event "click") and every commission (event "commission"). Body: {event, at, data}; no client emails. Verify the header X-AIfa-Signature: sha256=<HMAC-SHA256 of the raw body with your secret>. The secret is returned once. Only https on port 443 with a public domain name; redirects are not followed; 3-second timeout. Pass an empty url to switch off.

Input parameters:

- `url` (string, required): https URL of your endpoint, or "" to switch the webhook off.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/works-aifa-aifa-memory/api-mcp#diagnostics

## Score history

- 2026-11-21: 79
- 2026-11-20: 79
- 2026-11-19: 78
- 2026-11-18: 78
- 2026-11-17: 77
- 2026-11-16: 77
- 2026-11-15: 77
- 2026-11-14: 76
- 2026-11-13: 76
- 2026-11-12: 75
- 2026-11-11: 75
- 2026-11-10: 75
- 2026-11-09: 77
- 2026-11-08: 77
- 2026-11-07: 76
- 2026-11-06: 76

## Common questions

### What is the AIfa Memory MCP server?

AIfa Memory is an MCP server listed in the public MCP registry as works.aifa/aifa-memory. Persistent memory for AI agents, one account across four sites, plus a partner program. This page covers its hosted endpoint (https://aifa.works/api/mcp).

### Is the AIfa Memory MCP server safe to use?

AIfa Memory scores 79 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the AIfa Memory MCP server expose?

AIfa Memory exposes 15 tools: memory_search, memory_recent, memory_write, memory_about, account_status, and 10 more. Their descriptions and schemas cost roughly 1,502 tokens of context every time the server is loaded.

### Does the AIfa Memory MCP server require authentication?

No. We connected to AIfa Memory without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the AIfa Memory MCP server still maintained?

AIfa Memory is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What did VerifyMCP test on the AIfa Memory MCP server?

VerifyMCP ran 13 checks on AIfa Memory, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- Remote endpoint: https://aifa.works/api/mcp
- Authorisation metadata: https://aifa.works/.well-known/oauth-protected-resource/api/mcp
- Repository: https://github.com/MaksimGalatin/aifa-memory-mcp
- Website: https://aifa.works/mcp
- Changelog RSS feed: https://verifymcp.io/servers/works-aifa-aifa-memory/api-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/works-aifa-aifa-memory/api-mcp/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/works-aifa-aifa-memory/api-mcp.json
- HTML version of this page: https://verifymcp.io/servers/works-aifa-aifa-memory/api-mcp
