# CortexPlus (remote · mcp.cortexplus.io)

Personal memory layer: files, notes, messages, tasks and email, semantically indexed.

- Trust score: 70/100 (medium)
- Change this week: 0
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

> **Recent critical change**: Authorization (2026-10-07). See the changelog below before you install this server.

## Components

- remote · `mcp.cortexplus.io`: 70/100 (this document), [markdown](https://verifymcp.io/servers/io-cortexplus-cortexplus/mcp.md), [page](https://verifymcp.io/servers/io-cortexplus-cortexplus/mcp)

## Channel facts

- Endpoint: `https://mcp.cortexplus.io/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.1.0`

## 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**: 46/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation check failed: no authorisation is required to call this server, and it exposes a tool marked destructive (save_context).
  - HTTPS enforcement could not be verified: the plaintext port answered with HTTP 405, which proves neither a plaintext path nor enforcement.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - 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**: 71/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 1160 tokens (~105/item across 11 items; 11 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 100/100
  - No destabilizing schema changes in the last 30 days.
- **Tool Coverage**: 85/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 49% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 11 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 12 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 CortexPlus MCP server?

CortexPlus is a hosted endpoint at https://mcp.cortexplus.io/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 io-cortexplus-cortexplus 'https://mcp.cortexplus.io/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "io-cortexplus-cortexplus": {
      "url": "https://mcp.cortexplus.io/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "io-cortexplus-cortexplus": {
      "type": "http",
      "url": "https://mcp.cortexplus.io/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.io-cortexplus-cortexplus]
url = "https://mcp.cortexplus.io/mcp"
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add io-cortexplus-cortexplus --url 'https://mcp.cortexplus.io/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  io-cortexplus-cortexplus:
    url: "https://mcp.cortexplus.io/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "io-cortexplus-cortexplus": {
      "Transport": "http",
      "Url": "https://mcp.cortexplus.io/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add io-cortexplus-cortexplus -t streamable-http -u 'https://mcp.cortexplus.io/mcp'
```

### Other

```json
{
  "mcpServers": {
    "io-cortexplus-cortexplus": {
      "type": "http",
      "url": "https://mcp.cortexplus.io/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.

### 2026-11-13 (score 70, 0)

- [security improvement] Stability: fail → pass

### 2026-11-11 (score 70, +1)

No change was recorded against any check on this day. Stability & Change Management went from 91 to 94.

### 2026-11-10 (score 69, −1)

No change was recorded against any check on this day. Stability & Change Management went from 94 to 91.

### 2026-11-08 (score 70, +1)

No change was recorded against any check on this day. Stability & Change Management went from 91 to 94.

### 2026-11-07 (score 69, −1)

No change was recorded against any check on this day. Stability & Change Management went from 94 to 91.

### 2026-11-06 (score 70, 0)

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

### 2026-10-28 (score 70, +1)

No change was recorded against any check on this day. Stability & Change Management went from 92 to 94.

### 2026-10-14 (score 0)

- [security regression] Stability: 0.70 → fail
- [security regression] A breaking change shipped without a version bump: still 0.1.0
- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “connect” rewrote its description, which is the text the model reads
- [security] Tool “signup” rewrote its description, which is the text the model reads
- [functional regression] “connect” added a required parameter “email”, so existing callers break
- [cosmetic] “connect” reworded the description of “key”

## MCP tools (11)

### `search` (~80 tokens)

Search the user's CortexPlus memory and return ranked matches. Use this to find what the user has stored before answering from memory. Health data (`saude` tag) is only included when the user has enabled sharing it with AI assistants in CortexPlus settings.

Input parameters:

- `limit` (integer)
- `query` (string, required): What to look for, in natural language.

Output parameters:

- `results` (array)

### `fetch` (~64 tokens)

Retrieve the full content of one CortexPlus memory item by id, as returned by search. Health data (`saude` tag) is only included when the user has enabled sharing it with AI assistants in CortexPlus settings.

Input parameters:

- `id` (string, required): Item id from a search result.

Output parameters:

- `id` (string)
- `metadata` (object)
- `text` (string)
- `title` (string)
- `url` (string)

### `recall` (~103 tokens)

Build a context block from the user's CortexPlus memory: the passages that answer a question plus their graph neighbours, already formatted as text. Prefer this over search when you intend to answer from the user's memory. Health data (`saude` tag) is only included when the user has enabled sharing it with AI assistants in CortexPlus settings.

Input parameters:

- `depth` (integer)
- `limit` (integer)
- `maxChars` (integer)
- `query` (string, required)

Output parameters:

- `matches` (integer)
- `text` (string)

### `remember` (~80 tokens)

Store a note in the user's CortexPlus memory so future conversations can recall it.

Input parameters:

- `content` (string, required)
- `parentId` (string): Optional id of an existing memory to nest this one under.
- `tags` (array)
- `title` (string)
- `type` (string): Node type, e.g. note or meeting-note.

Output parameters:

- `id` (string)
- `title` (string)

### `memory` (~51 tokens)

Save a memory in CortexPlus. CortexPlus decides whether it is a note, task, or reminder and extracts the client.

Input parameters:

- `tags` (array)
- `text` (string, required): Text to classify and save.

Output parameters:

- `client` (string|null)
- `id` (string)
- `memory` (string|null)
- `resolved` (boolean|null)
- `review` (string|null)
- `status` (string|null)
- `title` (string)
- `type` (string)
- `url` (string)

### `tasks` (~41 tokens)

List open CortexPlus tasks and reminders, optionally filtered by client.

Input parameters:

- `client` (string)
- `limit` (integer)
- `status` (string)

Output parameters:

- `tasks` (array)

### `save_context` (~174 tokens)

Save a handoff summary of this conversation to the user's CortexPlus memory so it can be resumed later in another AI platform. Write the summary yourself, in Markdown, covering: objective, decisions taken, current state, artifacts, next steps and constraints. Do not paste the raw transcript. Never include passwords, API keys or tokens.

Input parameters:

- `content` (string, required): Handoff summary in Markdown.
- `key` (string, required): Short stable slug for the topic, e.g. context-pack-design. Sending the same key again updates the pack instead of creating another.
- `messageCount` (integer)
- `model` (string)
- `platform` (string, required): The AI platform you are running on, e.g. ChatGPT, Claude, Gemini, Cursor.
- `tags` (array)
- `title` (string)

Output parameters:

- `created` (boolean)
- `id` (string)
- `redactions` (array)
- `title` (string)
- `url` (string)

### `resume` (~65 tokens)

Load a previously saved CortexPlus context pack to resume work started in another AI conversation.

Input parameters:

- `id` (string): Pack id, as returned by context_packs.
- `maxChars` (integer)
- `query` (string): Topic to find the pack by, in natural language.

Output parameters:

- `matches` (integer)
- `pack` (object|null)
- `text` (string)

### `context_packs` (~48 tokens)

List saved CortexPlus context packs, optionally filtered by AI platform.

Input parameters:

- `limit` (integer)
- `platform` (string): Platform filter, e.g. chatgpt or claude.

Output parameters:

- `packs` (array)

### `signup` (~165 tokens)

Create a CortexPlus account, or begin signing in to an existing one, so this conversation can use CortexPlus as the user's long-term memory and knowledge base. Ask the user for their email address, and for their name if you do not already have it, then call this tool. CortexPlus sends them a 6-digit code by email; ask the user for that code and call connect with it and the same email. Never guess or invent the email address.

Input parameters:

- `client` (string): The name of the AI platform you are running on, e.g. ChatGPT, Claude, Cursor.
- `email` (string, required): The user's email address. Ask the user; never guess or invent it.
- `name` (string): The user's name, if it is not already known.

Output parameters:

- `sent` (boolean)

### `connect` (~128 tokens)

Complete the CortexPlus connection with the 6-digit code the user received by email after signup. Ask the user for the code, then call this tool with the same email used in signup; never guess or invent the code. The response includes an API key that the AI platform should save in its CortexPlus connector configuration.

Input parameters:

- `client` (string): The name of the AI platform you are running on, e.g. ChatGPT, Claude, Cursor.
- `email` (string, required): The email address used in signup.
- `key` (string, required): The 6-digit code from the CortexPlus email.

Output parameters:

- `apiKey` (string)
- `email` (string)
- `name` (string)

## Diagnostics

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

## Score history

- 2026-11-21: 70
- 2026-11-20: 70
- 2026-11-19: 70
- 2026-11-18: 70
- 2026-11-17: 70
- 2026-11-16: 70
- 2026-11-15: 70
- 2026-11-14: 70
- 2026-11-13: 70
- 2026-11-12: 70
- 2026-11-11: 70
- 2026-11-10: 69
- 2026-11-09: 70
- 2026-11-08: 70
- 2026-11-07: 69
- 2026-11-06: 70
- 2026-11-05: 70
- 2026-11-04: 70
- 2026-11-03: 70
- 2026-11-02: 70
- 2026-11-01: 70
- 2026-10-31: 70
- 2026-10-30: 70
- 2026-10-29: 70
- 2026-10-28: 70
- 2026-10-27: 69
- 2026-10-26: 69
- 2026-10-25: 69
- 2026-10-24: 69
- 2026-10-23: 69

## Common questions

### What is the CortexPlus MCP server?

CortexPlus is an MCP server listed in the public MCP registry as io.cortexplus/cortexplus. Personal memory layer: files, notes, messages, tasks and email, semantically indexed. This page covers its hosted endpoint (https://mcp.cortexplus.io/mcp).

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

CortexPlus scores 70 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 CortexPlus MCP server expose?

CortexPlus exposes 11 tools: search, fetch, recall, remember, memory, and 6 more. Their descriptions and schemas cost roughly 999 tokens of context every time the server is loaded.

### Does the CortexPlus MCP server require authentication?

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

### Is the CortexPlus MCP server still maintained?

CortexPlus 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 CortexPlus MCP server?

VerifyMCP ran 12 checks on CortexPlus, covering TLS certificate, Authorization, HSTS header, DNSSEC and 8 more. One item could not be completed, a gap on our side rather than a finding about CortexPlus: HTTPS. 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://mcp.cortexplus.io/mcp
- Website: https://cortexplus.io/connect
- Changelog RSS feed: https://verifymcp.io/servers/io-cortexplus-cortexplus/mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/io-cortexplus-cortexplus/mcp/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/io-cortexplus-cortexplus/mcp.json
- HTML version of this page: https://verifymcp.io/servers/io-cortexplus-cortexplus/mcp
