# Context Link (remote · www.context-link.ai)

One semantic search across your sites, Drive, Notion, email, files and Basecamp.

- Trust score: 83/100 (high trust)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-20

## Components

- remote · `www.context-link.ai`: 83/100 (this document), [markdown](https://verifymcp.io/servers/ai-context-link-context-link/www.md), [page](https://verifymcp.io/servers/ai-context-link-context-link/www)

## Channel facts

- Endpoint: `https://www.context-link.ai/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.0`

## 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 2026-09-20.

- **Endpoint Security**: 94/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation is enforced on tool calls, advertised via RFC 9728 protected-resource metadata. Discovery is public, which costs nothing: no tool can be invoked without a token.
  - 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.
  - The authorisation server offers only Dynamic Client Registration (RFC 7591), which MCP 2026-07-28 deprecated in favour of Client ID Metadata Documents.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 80/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 560 tokens (~112/item across 5 items; 4 tools + 1 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 94/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 78% 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 4 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 6 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).
  - Supports UI / widget rendering.

## Install

### How do I install the Context Link MCP server?

Context Link is a hosted endpoint at https://www.context-link.ai/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 ai-context-link-context-link 'https://www.context-link.ai/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "ai-context-link-context-link": {
      "url": "https://www.context-link.ai/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "ai-context-link-context-link": {
      "type": "http",
      "url": "https://www.context-link.ai/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.ai-context-link-context-link]
url = "https://www.context-link.ai/mcp"
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add ai-context-link-context-link --url 'https://www.context-link.ai/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  ai-context-link-context-link:
    url: "https://www.context-link.ai/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "ai-context-link-context-link": {
      "Transport": "http",
      "Url": "https://www.context-link.ai/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add ai-context-link-context-link -t streamable-http -u 'https://www.context-link.ai/mcp'
```

### Other

```json
{
  "mcpServers": {
    "ai-context-link-context-link": {
      "type": "http",
      "url": "https://www.context-link.ai/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.

### 2026-09-19 (score 83, +1)

No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-17 (score 82, +1)

No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-14 (score 81, +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.

### 2026-09-13 (score 80, +1)

- [functional regression] Schema quality: 86 → 112
- [functional improvement] Tool coverage: 71% → 78%
- [functional improvement] Stability: unverified → 0.03
- [cosmetic] “ask_question” added an optional parameter “connection_type”
- [cosmetic] “get_context” added an optional parameter “connection_type”

### 2026-09-12 (score 79)

First indexed and scored.

## MCP tools (4)

### `get_context` (~140 tokens)

Get Context

Get context from the user's connected workspaces and websites. The attached widget displays only the list of sources consulted — it does not show the retrieved content, so use the returned context to answer the user directly.

Input parameters:

- `connection_type` (string): Optional comma-separated list of connection types to restrict retrieval to (e.g. "site,email"). Only content from those sources is considered. Valid types: basecamp, custom, email, files, google_doc,…
- `mode` (string): Optional mode to weight results (e.g. 'customer-support')
- `query` (string, required)

Output parameters:

- `context` (string|null)
- `sources` (array)

### `ask_question` (~146 tokens)

Ask Question

Ask a question about the user's connected workspaces and websites and receive a concise answer with citations. The attached widget displays only the list of sources consulted — it does not show the answer, so always relay the answer text in your reply.

Input parameters:

- `connection_type` (string): Optional comma-separated list of connection types to restrict retrieval to (e.g. "site,email"). Only content from those sources is considered. Valid types: basecamp, custom, email, files, google_doc,…
- `mode` (string): Optional mode to weight results (e.g. 'customer-support')
- `query` (string, required)

Output parameters:

- `answer` (string): Concise paragraph answer; empty string when success is false
- `citations` (array)
- `reason` (string)
- `sources` (array)
- `success` (boolean)

### `save_memory` (~87 tokens)

Save Memory

Save content to the user's memory for later retrieval. Use this when the user wants to save information, notes, or conversation content.

Input parameters:

- `content` (string, required): The content to save. Can be plain text, markdown, or structured content.
- `namespace` (string): A name/label for this memory (use-dashes-for-spaces). If omitted, a timestamped name is generated.

Output parameters:

- `message` (string)
- `namespace` (string)

### `get_memory` (~44 tokens)

Get Memory

Retrieve previously saved memory content by its namespace. Use this when the user wants to recall saved content.

Input parameters:

- `namespace` (string, required): The namespace/name of the saved memory to retrieve

Output parameters:

- `content` (string)
- `found` (boolean)
- `namespace` (string)

## Diagnostics

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

## Score history

- 2026-09-20: 83
- 2026-09-19: 83
- 2026-09-18: 82
- 2026-09-17: 82
- 2026-09-16: 81
- 2026-09-15: 81
- 2026-09-14: 81
- 2026-09-13: 80
- 2026-09-12: 79

## Common questions

### What is the Context Link MCP server?

Context Link is an MCP server listed in the public MCP registry as ai.context-link/context-link. One semantic search across your sites, Drive, Notion, email, files and Basecamp. This page covers its hosted endpoint (https://www.context-link.ai/mcp).

### Is the Context Link MCP server safe to use?

Context Link scores 83 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 Context Link MCP server expose?

Context Link exposes 4 tools: get_context, ask_question, save_memory, get_memory. Their descriptions and schemas cost roughly 417 tokens of context every time the server is loaded.

### Does the Context Link MCP server require authentication?

Yes. Context Link asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.

### Is the Context Link MCP server still maintained?

Context Link is still listed as active in the MCP registry. We last reached this channel on 20 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://www.context-link.ai/mcp
- Website: https://www.context-link.ai/
- Changelog RSS feed: https://verifymcp.io/servers/ai-context-link-context-link/www.xml
- Changelog JSON feed: https://verifymcp.io/servers/ai-context-link-context-link/www.json
- HTML version of this page: https://verifymcp.io/servers/ai-context-link-context-link/www