# chartlink (remote · chartlink.app)

Charts and tables for AI agents with live-updating embed links. No account: signup returns a key.

- Trust score: 66/100 (medium)
- Change this week: −3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-26

## Components

- remote · `chartlink.app`: 66/100 (this document), [markdown](https://verifymcp.io/servers/oscarleoo-chartlink/chartlink.md), [page](https://verifymcp.io/servers/oscarleoo-chartlink/chartlink)
- npm · `chartlink-mcp`: 38/100, [markdown](https://verifymcp.io/servers/oscarleoo-chartlink/chartlink-mcp.md), [page](https://verifymcp.io/servers/oscarleoo-chartlink/chartlink-mcp)

## Channel facts

- Endpoint: `https://chartlink.app/mcp`
- Transports: `streamable-http`
- Auth: `required`
- Version: `0.1.2`

## 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 check failed: no authorisation is required to call this server, and it exposes a tool marked destructive (check_template_data).
  - 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**: 78/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 2058 tokens (~187/item across 11 items; 10 tools + 1 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability check failed: schema churn in the 11 days we've observed: 19 tool removals, 0 breaking changes, 0 auth/transport breaks, 4 additions.
- **Tool Coverage**: 90/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 69% 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.
  - All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.
  - An AI judge read all 12 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

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

chartlink is a hosted endpoint at https://chartlink.app/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 oscarleoo-chartlink 'https://chartlink.app/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "oscarleoo-chartlink": {
      "url": "https://chartlink.app/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "oscarleoo-chartlink": {
      "type": "http",
      "url": "https://chartlink.app/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.oscarleoo-chartlink]
url = "https://chartlink.app/mcp"
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add oscarleoo-chartlink --url 'https://chartlink.app/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  oscarleoo-chartlink:
    url: "https://chartlink.app/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "oscarleoo-chartlink": {
      "Transport": "http",
      "Url": "https://chartlink.app/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add oscarleoo-chartlink -t streamable-http -u 'https://chartlink.app/mcp'
```

### Other

```json
{
  "mcpServers": {
    "oscarleoo-chartlink": {
      "type": "http",
      "url": "https://chartlink.app/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.

### 2026-09-25 (score 66, 0)

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

### 2026-09-24 (score 66, −1)

- [security] Tool “get_template” rewrote its description, which is the text the model reads
- [security] Tool “create_from_template” rewrote its description, which is the text the model reads
- [cosmetic] “get_template” reworded the description of “id”
- [cosmetic] “create_from_template” reworded the description of “template”
- [cosmetic] “check_template_data” reworded the description of “template”

### 2026-09-23 (score 67, −3)

- [security regression] Stability: 0.23 → fail
- [security regression] A breaking change shipped without a version bump: still 0.1.0
- [security regression] Tool “create_checkout_link” was removed
- [security regression] Tool “delete_asset” was removed
- [security regression] Tool “duplicate_asset” was removed
- [security regression] Tool “fetch_data_source” was removed
- [security regression] Tool “get_asset” was removed
- [security regression] Tool “get_billing” was removed
- [security regression] Tool “get_spec_schema” was removed
- [security regression] Tool “list_asset_types” was removed
- [security regression] Tool “list_assets” was removed
- [security regression] Tool “list_brands” was removed
- [security regression] Tool “list_geographies” was removed
- [security regression] Tool “replace_asset_data” was removed
- [security regression] Tool “revoke_edit_link” was removed
- [security regression] Tool “set_data_source” was removed
- [security regression] Tool “unpublish_asset” was removed
- [security regression] Tool “update_brand” was removed
- [security regression] Tool “upgrade_to_premium” was removed
- [security regression] Tool “clear_data_source” was removed
- [security regression] Tool “create_asset” was removed
- [security regression] Tool “create_brand” was removed
- [security] The server rewrote its instructions, which are the text every model session reads
- [security] New tool “check_template_data”, which the server declares destructive
- [functional regression] Schema quality: 120 → 174
- [functional improvement] Tool coverage: 53% → 69%
- [functional] Schema quality: good → excellent
- [functional] New tool “create_from_template”
- [functional] New tool “get_template”
- [cosmetic] “list_templates” added an optional parameter “limit”
- [cosmetic] “list_templates” added an optional parameter “tags”

### 2026-09-22 (score 70, +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.

### 2026-09-19 (score 69, +4)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “list_geographies” rewrote its description, which is the text the model reads
- [security] Tool “list_templates” rewrote its description, which is the text the model reads
- [security] Tool “set_data_source” is now declared destructive
- [security] Tool “clear_data_source” is now declared destructive
- [security] Tool “fetch_data_source” is now declared destructive
- [security] Tool “publish_asset” is now declared destructive
- [security] Tool “replace_asset_data” is now declared destructive
- [security] Tool “revoke_edit_link” is now declared destructive
- [security] Tool “update_asset” is now declared destructive
- [security] Tool “update_brand” is now declared destructive
- [security] Tool “upgrade_to_premium” is now declared destructive
- [functional] The server now declares the “prompts” capability
- [functional] The server now declares the “resources” capability
- [functional] First check of Schema quality: 100
- [functional] Destructive annotations: All 3 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.
- [functional] New prompt “make-a-chart”
- [functional] New resource “manual”
- [cosmetic] “list_templates” added an optional parameter “q”
- [cosmetic] “replace_asset_data” added an optional parameter “config”
- [cosmetic] Tool “list_templates” changed its title: Charts offered as templates — start a new chart from one → Templates by need — search, then start a chart from the best match

### 2026-09-18 (score 65, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [cosmetic] “update_brand” reworded the description of “tokens”
- [cosmetic] “create_brand” reworded the description of “tokens”

### 2026-09-17 (score 65, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “create_asset” rewrote its description, which is the text the model reads
- [security] Tool “create_edit_link” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: pass → fail
- [functional improvement] Tool coverage: 47% → 52%
- [functional] New tool “signup”
- [cosmetic] “replace_asset_data” reworded the description of “data”
- [cosmetic] “update_asset” reworded the description of “data”

### 2026-09-16 (score 65, 0)

- [functional improvement] Stability: unverified → 0.03
- [functional] New tool “list_geographies”

## MCP tools (10)

### `signup` (~106 tokens)

Get an API key — no account, one call

Creates a workspace and returns its API key (shown ONCE — keep it). Works on a keyless connection; every other tool needs the key. Then put the key where your client keeps it (plugin api_key setting, the Authorization header, or CHARTLINK_API_KEY for the npx bridge) and reconnect.

Input parameters:

- `name` (string): A name for the workspace (the project, the newsletter…)
- `ref` (string): Where you heard of chartlink — free text

### `whoami` (~38 tokens)

Verify your API key

Returns key name + workspace. Call this first — non-destructive auth check. Everything you write is stamped createdBy/updatedBy = key name.

### `list_templates` (~197 tokens)

Templates by need — search, then start a chart from the best match

Templates are named by the NEED they answer (need, asks, tags), each with urls.png (show it to your human) and `columns`: the column ids your data must supply. Pass q with what the person asked for — "map of brazil's states", "ranked bars with flags", "change between two years" — and the list comes back ranked; take the first. Then create_asset with template: <id> and your data — the whole design comes along. Any chart id you were shown works as a template too, not only these.

Input parameters:

- `limit` (integer): At most this many, best first (default 20)
- `q` (string): What is needed, in the person's words
- `tags` (string): Comma-separated tags every result must carry, e.g. map,united-states
- `type` (string): Only this asset type, e.g. "bar"

### `get_template` (~147 tokens)

One template's contract: knobs, columns, region codes, an example call

Read this before create_from_template. Returns the template with `contract`: its looks (theme × dataType × surroundings), the knobs JSON Schema, the columns with their roles, the region-code convention with three real codes and a lookup URL, what each dataType expects of the value column, and a complete example call whose shape you copy. Takes an id, the page slug, or the page address as on chartlink.app/maps — sweden/municipalities, us/texas/counties, london/wards — so you can skip list_templates when you know the place.

Input parameters:

- `id` (string, required): Template id (ast_…), slug, or page address (place/level)

### `check_template_data` (~108 tokens)

Dry run: would this data and these knobs work with the template? Creates nothing

Matches every region value against the template's geography and reports unmatched values with the closest real codes, how many regions would stay grey, and the scale the map would use. No key needed. Use it when unsure of the codes; then create_from_template with the same data and knobs.

Input parameters:

- `data` (object, required): The data you intend to send
- `knobs` (object)
- `template` (string, required): Template id, slug, or page address (sweden/municipalities)

### `create_from_template` (~341 tokens)

Create a chart from a template with your data and a few knobs — returns an inline preview

The template's design, your data, your words. `knobs` are the template's settings (get_template shows the schema): theme light|dark|editorial, dataType gradient|buckets|categories and surroundings true|false (then waterColor, landColor) for maps, title/description/source/brand {text, fontFamily, fontSize, color}, backgroundColor, and the scale knobs for the dataType (colormap and direction, range, breaks or classes, categoryColors/categoryOrder). data = {columns: [{id, type}], rows: [[…]]}: use the template's column ids, or exactly two columns (region first, value second) for a map. publish: true makes the URLs live in the same call. A success means it validated AND rendered — look at the preview. Region values that match nothing come back as a 400 listing each with its closest real codes, before anything is made — no separate check needed. `config` is the advanced path: the engine's settings, merged after the knobs.

Input parameters:

- `config` (object): ADVANCED: engine settings deep-merged after the knobs
- `data` (object, required): Typed columns + row-major rows, shaped like the template's example
- `knobs` (object): The template's knobs — get_template returns their schema
- `publish` (boolean): true = published and live in this call; omit while you iterate
- `template` (string, required): Template id or slug from list_templates, or the page address (sweden/municipalities, us/texas/counties, london/wards) when you know the place

### `update_asset` (~280 tokens)

Update a draft (deep-merge patch, or replace the config) — returns an inline preview image

configPatch is DEEP-MERGED: objects merge recursively, arrays replace wholesale, null clears a key — send only what changes. To REMOVE keys (drop document.aspect, delete one of texts[]) pass `config` instead: it REPLACES the whole config (get_asset returns the current one to edit). `data` (if given) replaces rows wholesale. Requires expectedVersion from the last envelope; on 409 re-merge onto the returned `current`. Updating does NOT publish by default — pass publish: true to publish in the same call, or call publish_asset separately.

Input parameters:

- `brand`
- `config` (object): REPLACES the whole config — the way to remove keys; applied before configPatch if both are given
- `configPatch` (object): Deep-merged onto the current config
- `data` (object): Typed columns + row-major rows. A date column whose strings are not ISO-ish takes dateFormat (e.g. "%d/%m/%Y").
- `expectedVersion` (integer, required)
- `id` (string, required)
- `publish` (boolean): true = publish immediately after this update succeeds (one call instead of two)
- `showcase` (boolean): Offer this chart as a template in the public gallery and list_templates (once published). Workspace keys only.
- `title` (string)

### `publish_asset` (~96 tokens)

Publish — snapshot a version and update every embed

Makes the draft live. Returns urls: paste urls.embedIframe on iframe platforms; on Substack insert urls.png as an image and link it to urls.page. Pinned history: urls.png + '?v=N'.

Input parameters:

- `id` (string, required)
- `note` (string)
- `premium` (boolean): Spend one paid credit to publish as premium (2400px, SVG, your branding, no badge) in this call

### `create_edit_link` (~137 tokens)

Mint a no-login tweak link — hand it to your human

Returns a URL opening the visual tweak panel for ONE chart (text, colors, spacing, label nudges) with no login. PUBLISH FIRST: the editor saves and republishes a published chart, it cannot publish a draft. Scope: view, tweak, and republish that chart only — never delete, never spend credits, nothing else in the workspace. OFFER THIS whenever the human's request is aesthetic fine-tuning: handing over the wheel beats a nudge-by-nudge back-and-forth. The secret is shown once; links don't expire and can be revoked with revoke_edit_link.

Input parameters:

- `id` (string, required): ast_...

### `submit_feedback` (~122 tokens)

Report a gap — don't silently give up

If a capability is missing, a schema fights you, or docs are wrong: record it here so the owner can fix it. One report per distinct issue, with a real description — reports get fixed same-day when they say what you tried, what you expected, and what happened (title-only reports can't be acted on).

Input parameters:

- `assetId` (string)
- `description` (string, required): What you tried, what you expected, what happened instead — include the asset id if one is involved
- `title` (string, required)
- `type` (string, required)

## Diagnostics

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

## Score history

- 2026-09-26: 66
- 2026-09-25: 66
- 2026-09-24: 66
- 2026-09-23: 67
- 2026-09-22: 70
- 2026-09-21: 69
- 2026-09-20: 69
- 2026-09-19: 69
- 2026-09-18: 65
- 2026-09-17: 65
- 2026-09-16: 65
- 2026-09-15: 65

## Common questions

### What is the chartlink MCP server?

chartlink is an MCP server listed in the public MCP registry as io.github.oscarleoo/chartlink. Charts and tables for AI agents with live-updating embed links. No account: signup returns a key. This page covers its hosted endpoint (https://chartlink.app/mcp).

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

chartlink scores 66 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 chartlink MCP server expose?

chartlink exposes 10 tools: signup, whoami, list_templates, get_template, check_template_data, and 5 more. Their descriptions and schemas cost roughly 1,572 tokens of context every time the server is loaded.

### Does the chartlink MCP server require authentication?

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

### Is the chartlink MCP server still maintained?

chartlink 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://chartlink.app/mcp
- Authorisation metadata: https://chartlink.app/.well-known/oauth-protected-resource/mcp
- Repository: https://github.com/oscarleoo/chartlink-agents
- Website: https://chartlink.app/
- Changelog RSS feed: https://verifymcp.io/servers/oscarleoo-chartlink/chartlink.xml
- Changelog JSON feed: https://verifymcp.io/servers/oscarleoo-chartlink/chartlink.json
- HTML version of this page: https://verifymcp.io/servers/oscarleoo-chartlink/chartlink