# PERSONAIZER (remote · sessions.personaizer.com)

Free MCP API to create AI chat personas for websites — upload knowledge, search, and chat

- Trust score: 74/100 (medium)
- Change this week: −6
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-26

## Components

- remote · `sessions.personaizer.com`: 74/100 (this document), [markdown](https://verifymcp.io/servers/personaizer-mcp/sessions.md), [page](https://verifymcp.io/servers/personaizer-mcp/sessions)

## Channel facts

- Endpoint: `https://sessions.personaizer.com/mcp`
- Transports: `streamable-http`
- Auth: `required`
- Version: `1.0.1`

## 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 2026-09-26.

- **Endpoint Security**: 63/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 5 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 79/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 638 tokens (~127/item across 5 items; 5 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 57/100
  - Stability check failed: schema churn in the 30 days we've observed: 1 tool removals, 2 breaking changes, 0 auth/transport breaks, 1 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**: 75/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "chat" implies "send" and declares no destructiveHint at all, which the MCP spec reads as destructive by default.
  - An AI judge read all 5 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### How do I install the PERSONAIZER MCP server?

PERSONAIZER is a hosted endpoint at https://sessions.personaizer.com/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 personaizer-mcp 'https://sessions.personaizer.com/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "personaizer-mcp": {
      "url": "https://sessions.personaizer.com/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "personaizer-mcp": {
      "type": "http",
      "url": "https://sessions.personaizer.com/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.personaizer-mcp]
url = "https://sessions.personaizer.com/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "personaizer-mcp": {
      "type": "remote",
      "url": "https://sessions.personaizer.com/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add personaizer-mcp --url 'https://sessions.personaizer.com/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  personaizer-mcp:
    url: "https://sessions.personaizer.com/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "personaizer-mcp": {
      "Transport": "http",
      "Url": "https://sessions.personaizer.com/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add personaizer-mcp -t streamable-http -u 'https://sessions.personaizer.com/mcp'
```

### Other

```json
{
  "mcpServers": {
    "personaizer-mcp": {
      "type": "http",
      "url": "https://sessions.personaizer.com/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.

### 2026-09-26 (score 74, 0)

- [security regression] Stability: unverified → fail
- [security improvement] Injection markers: unverified → pass
- [security improvement] TLS certificate: unverified → pass
- [security improvement] HSTS header: unverified → pass
- [security improvement] Transport: fail → pass
- [security] Authorization: Authorisation not fully verified: no authorisation is required to call this server, and 5 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] MCP protocol: unverified → pass

### 2026-09-25 (score 74, 0)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-09-21 (score 74, −6)

- [security regression] Stability: pass → fail
- [security regression] A breaking change shipped without a version bump: still 0.0.0.0
- [security regression] Tool “search_knowledge” was removed
- [security] Tool “chat” rewrote its description, which is the text the model reads
- [security] Tool “create_persona” rewrote its description, which is the text the model reads
- [security] Tool “upload_knowledge_docs” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: pass → fail
- [functional regression] “upload_knowledge_docs” added a required parameter “source”, so existing callers break
- [functional regression] “chat” made “personaId” required, so existing callers break
- [functional regression] “chat” changed the type of “personaId”: string|null → string
- [functional] New tool “upload_knowledge_text”
- [cosmetic] “chat” reworded the description of “personaId”
- [cosmetic] “create_persona” reworded the description of “harvestContent”
- [cosmetic] “upload_knowledge_docs” reworded the description of “items”

### 2026-09-20 (score 80, 0)

- [security] Stability: 0.97 → pass

### 2026-09-19 (score 80, +1)

No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-17 (score 79, +1)

No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-15 (score 78, +1)

No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-12 (score 77, +1)

No change was recorded against any check on this day. Stability & Change Management went from 70 to 73. That category is still filling its 30-day observation window: 21 days of observed history at the previous scan, 22 at this one. The score rises as the window fills, whether or not the server changes.

## MCP tools (5)

### `upload_knowledge_text` (~194 tokens)

Add a piece of text — an FAQ, policy, guide, article or notes — to a knowledge source as a plain-text document. Uploading again with the same id replaces that document's text. For products (price, stock, attributes, variants) use upload_knowledge_docs. Requires your account API key and the source to write to; every persona speaking for that source's brand answers from it.

Input parameters:

- `content` (string, required): The full text of the document.
- `id` (string|null): Optional stable identifier. Uploading again with the same id replaces that document's text; omit it to create a new document.
- `source` (string, required): The knowledge source this belongs to — its name, e.g. my-shop.ge.
- `title` (string, required): Document title.
- `url` (string|null): Optional URL where this content lives — shown as the document's link when the persona cites it.

### `create_persona` (~139 tokens)

Start building a new PersonAIzer persona from a website URL — reads the site's brand facts, makes the brand, synthesizes the persona's identity and avatar, and (by default) crawls the site into the brand's knowledge; the persona and the crawl run in parallel. Asynchronous (~1 minute for the persona) — returns jobId, brandId and personaId; poll check_persona_status. Requires an account-level API key.

Input parameters:

- `harvestContent` (boolean): Whether to crawl the site into the brand's knowledge alongside the persona build (default true).
- `websiteUrl` (string, required): The website URL to build the persona from.

### `chat` (~102 tokens)

Send a message to a PersonAIzer persona and get its reply, including any knowledge-base cards it surfaces. Requires your account API key and the persona_id to speak as.

Input parameters:

- `message` (string, required): The message to send.
- `personaId` (string, required): Which persona to chat with (its Persona ID).
- `sessionId` (string|null): Continue an existing conversation by passing back the session_id from a previous chat call. Omit to start a new conversation.

### `upload_knowledge_docs` (~157 tokens)

Upsert up to 100 PRODUCTS (including services and unpriced catalog entries) into a knowledge source. For plain text (FAQs, policies, guides, articles, notes) use upload_knowledge_text instead. Requires your account API key; the source must exist (POST /v1/knowledge/sources).

Input parameters:

- `items` (array, required): The products to upsert. Each needs title and categories (e.g. [["phones"]]); id, description, price, in_stock, attributes, variants, images and links are optional — see PersonAIzer's /v1/knowledge AP…
- `source` (string, required): The knowledge source the products belong to — its name, e.g. my-shop.ge.

### `check_persona_status` (~46 tokens)

Poll the status of a persona build started by create_persona. Requires an account-level API key.

Input parameters:

- `jobId` (string, required): The job_id returned by create_persona.

## Diagnostics

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

## Score history

- 2026-09-26: 74
- 2026-09-25: 74
- 2026-09-24: 74
- 2026-09-23: 74
- 2026-09-22: 74
- 2026-09-21: 74
- 2026-09-20: 80
- 2026-09-19: 80
- 2026-09-18: 79
- 2026-09-17: 79
- 2026-09-16: 78
- 2026-09-15: 78
- 2026-09-14: 77
- 2026-09-13: 77
- 2026-09-12: 77
- 2026-09-11: 76
- 2026-09-10: 76
- 2026-09-09: 75
- 2026-09-08: 75
- 2026-09-07: 74
- 2026-09-06: 74
- 2026-09-05: 73
- 2026-09-04: 73
- 2026-09-03: 72
- 2026-09-02: 72
- 2026-09-01: 71
- 2026-08-31: 71
- 2026-08-30: 70
- 2026-08-29: 70
- 2026-08-28: 70

## Common questions

### What is the PERSONAIZER MCP server?

PERSONAIZER is an MCP server listed in the public MCP registry as io.github.PersonAIzer/mcp. Free MCP API to create AI chat personas for websites, upload knowledge, search, and chat. This page covers its hosted endpoint (https://sessions.personaizer.com/mcp).

### Is the PERSONAIZER MCP server safe to use?

PERSONAIZER scores 74 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 PERSONAIZER MCP server expose?

PERSONAIZER exposes 5 tools: upload_knowledge_text, create_persona, chat, upload_knowledge_docs, check_persona_status. Their descriptions and schemas cost roughly 638 tokens of context every time the server is loaded.

### Does the PERSONAIZER MCP server require authentication?

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

### Is the PERSONAIZER MCP server still maintained?

PERSONAIZER is still listed as active in the MCP registry. We last reached this channel on 26 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://sessions.personaizer.com/mcp
- Authorisation metadata: https://sessions.personaizer.com/.well-known/oauth-protected-resource/mcp
- Repository: https://github.com/PersonAIzer/mcp
- Website: https://personaizer.com/developers/mcp
- Changelog RSS feed: https://verifymcp.io/servers/personaizer-mcp/sessions.xml
- Changelog JSON feed: https://verifymcp.io/servers/personaizer-mcp/sessions.json
- HTML version of this page: https://verifymcp.io/servers/personaizer-mcp/sessions