# BotKelp (remote · www.botkelp.com)

Verified component catalog over remote MCP: agents pick ids and get a project that builds.

- Trust score: 87/100 (high trust)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- remote · `www.botkelp.com`: 87/100 (this document), [markdown](https://verifymcp.io/servers/aiscimi-code-botkelp/www.md), [page](https://verifymcp.io/servers/aiscimi-code-botkelp/www)

## Channel facts

- Endpoint: `https://www.botkelp.com/mcp`
- Transports: `streamable-http`
- Auth: `required`
- Version: `1.1.0`

## 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 2026-11-05.

- **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**: 83/100
  - 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 1710 tokens (~100/item across 17 items; 16 tools + 1 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 47/100
  - Stability observed for 14 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 99/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 97% 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 16 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 18 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 BotKelp MCP server?

BotKelp is a hosted endpoint at https://www.botkelp.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 aiscimi-code-botkelp 'https://www.botkelp.com/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "aiscimi-code-botkelp": {
      "url": "https://www.botkelp.com/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "aiscimi-code-botkelp": {
      "type": "http",
      "url": "https://www.botkelp.com/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.aiscimi-code-botkelp]
url = "https://www.botkelp.com/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "aiscimi-code-botkelp": {
      "type": "remote",
      "url": "https://www.botkelp.com/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add aiscimi-code-botkelp --url 'https://www.botkelp.com/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  aiscimi-code-botkelp:
    url: "https://www.botkelp.com/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "aiscimi-code-botkelp": {
      "Transport": "http",
      "Url": "https://www.botkelp.com/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add aiscimi-code-botkelp -t streamable-http -u 'https://www.botkelp.com/mcp'
```

### Other

```json
{
  "mcpServers": {
    "aiscimi-code-botkelp": {
      "type": "http",
      "url": "https://www.botkelp.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.

### 2026-11-05 (score 87, +1)

No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-02 (score 86, +1)

No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-31 (score 85, +1)

No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-29 (score 84, +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.

### 2026-10-27 (score 83, +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.

### 2026-10-25 (score 82, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-23 (score 81, +1)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “purchase_scaffold” rewrote its description, which is the text the model reads
- [security] Tool “get_siteprofile” rewrote its description, which is the text the model reads
- [security] Tool “get_scaffold” rewrote its description, which is the text the model reads
- [security] Tool “get_help” rewrote its description, which is the text the model reads
- [security] Tool “get_component” rewrote its description, which is the text the model reads
- [security] Tool “get_account_status” rewrote its description, which is the text the model reads
- [security] Tool “verify_scaffold” rewrote its description, which is the text the model reads
- [security] Tool “set_projects” rewrote its description, which is the text the model reads
- [security] Tool “report_issue” rewrote its description, which is the text the model reads
- [functional improvement] Stability: unverified → 0.03
- [functional improvement] Schema quality: fail → pass
- [functional] Schema quality: excellent → good
- [functional] New tool “search_components”
- [cosmetic] “purchase_scaffold” reworded the description of “delivery”
- [cosmetic] “purchase_scaffold” reworded the description of “components”
- [cosmetic] “purchase_scaffold” reworded the description of “admin_page_set”
- [cosmetic] “get_scaffold” reworded the description of “delivery”
- [cosmetic] “purchase_scaffold” reworded the description of “template_files”
- [cosmetic] “purchase_scaffold” reworded the description of “site_profile”
- [cosmetic] “purchase_scaffold” reworded the description of “project”
- [cosmetic] “purchase_scaffold” reworded the description of “maintain”

### 2026-10-22 (score 80)

First indexed and scored.

## MCP tools (16)

### `get_help` (~21 tokens)

Get help

Free. Short usage index. Then search_components to pick ids.

### `search_components` (~66 tokens)

Search components

Free. Compact catalog TSV: id, provides, requires, conflictsWith. Omit args for all.

Input parameters:

- `detail` (boolean): Add short descriptions.
- `provides` (array): Required capability tags.
- `query` (string): Words to match, e.g. "auth stripe".

### `get_component` (~76 tokens)

Get component source

One component's source files, UNRENDERED (EJS markers, not build-ready): inspect only; use purchase_scaffold for real files. Free, 32/day, signed-in account.

Input parameters:

- `component` (string, required): Component id, or id@version, e.g. "supabase-client@2.0.0".

### `purchase_scaffold` (~171 tokens)

Purchase scaffold

Buys a CI-green starter repo for component ids (credits via your signed-in account, or x402). Returns a git clone command and projectid. Red builds are refused and not charged. delivery "inline" returns files instead (more tokens).

Input parameters:

- `admin_page_set` (string): Extra file-set name.
- `components` (array, required): Component ids, e.g. ["nextjs-base","tailwind"].
- `delivery` (string): "clone" (default) or "inline".
- `maintain` (boolean): Renewable repeat access (default true).
- `project` (object): Saved project metadata.
- `site_profile` (boolean|string): true or a profile name: bake legal pages in.
- `template_files`: Extra files: true, or [{name}|{source,dest}].

### `get_scaffold` (~128 tokens)

Get scaffold

Refetches a scaffold you purchased (fresh clone command), no extra credits. Credit-flow projects need Maintain on. Same site_profile/delivery options as purchase_scaffold.

Input parameters:

- `delivery` (string): "clone" (default) or "inline".
- `projectid` (string, required): The project id from a previous purchase_scaffold result. Required — your project is resolved from your authenticated account.
- `site_profile` (boolean|string): false/omit: skip. true: attach this account's one site profile (errors if 0 or >1). A string: attach that named profile.

### `get_projects` (~54 tokens)

Get projects

Lists this account's saved scaffold projects (id, name, description, repo, components, maintain state). Use the projectid with get_scaffold to re-fetch a scaffold — no project_api_key is needed as a tool argument.

### `set_projects` (~89 tokens)

Set projects

Turn Maintain on/off for a project and/or rotate its project key. Off keeps existing clones; it stops future get_scaffold access.

Input parameters:

- `maintain` (boolean)
- `projectid` (string, required): The project id to change (from get_projects). Required — scoped to your authenticated account.
- `rotate` (boolean): If true, mints a new project key and invalidates the old one.

### `get_siteprofile` (~144 tokens)

Get site profile

Your site profiles (privacy, terms, cookies, licence, custom_field) as JSON. list: true for names, or siteprofilename for one; field filters. Use next.arguments when a purchase reply says incomplete: true.

Input parameters:

- `cursor` (string): Resume token from a previous incomplete result, e.g. "doc:terms".
- `field`: "all" (default), or an array from: privacy, terms, cookies, license, custom_field.
- `list` (boolean): If true, return this account's profile names instead of a profile's content.
- `siteprofilename` (string): The profile to fetch. Required unless list: true.

### `set_siteprofile` (~116 tokens)

Set site profile

Creates or updates one named site profile for this account. Fields omitted from `field` keep their current saved value (or blank, if the profile is new); pass only what changed. custom_field entries are merged key-by-key. An account may keep more than one named profile (e.g. one per brand/site).

Input parameters:

- `field` (object, required): Fields to change. Omitted fields keep their current value.
- `siteprofilename` (string, required): Name for this profile, e.g. "default" or "acme-co".

### `get_adminpageset` (~85 tokens)

Get admin page set

Lists this account's admin page set names (omit name), or returns one set's exact files (pass name). These are the file trees purchase_scaffold's admin_page_set param bakes into a dedicated forked repo. Requires a linked account (transport auth).

Input parameters:

- `name` (string): The set to fetch. Omit to list this account's set names instead.

### `set_adminpageset` (~121 tokens)

Set admin page set

Creates or fully replaces one named admin page set for this account — real file source (React/Next.js), not text config. purchase_scaffold's admin_page_set param bakes a chosen set into a brand-new, dedicated repo. An account may keep more than one named set.

Input parameters:

- `files` (array, required): The full set of files, e.g. [{ path: "app/admin/page.tsx", content: "..." }].
- `name` (string, required): Name for this set, e.g. "default" or "acme-admin".

### `verify_scaffold` (~192 tokens)

Verify scaffold

Remote `npm install && npm run build` of your edited files (send every file). Call with files -> WAIT + jobId; call again with jobId -> OK or FAIL with the error tail. Needs a purchased projectid.

Input parameters:

- `envVariables` (array): Env var names to write placeholder values for before building (typically get_component's `envVariables` output) — needed for components that read process.env at build time (e.g. a Supabase client).
- `files` (array): The full project to verify — a scaffold's files with your edits applied. Omit when polling with jobId.
- `jobId` (string): Poll a previously started verification. Omit on the first call (pass files), pass the returned jobId on subsequent calls.
- `projectid` (string, required): The project id from a previous purchase_scaffold result — must be owned by this account. Required.

### `report_issue` (~76 tokens)

Report an issue

Report a catalog/code bug or request a component (files an issue on botkelp/components). Signed-in account, 10/day. No secrets.

Input parameters:

- `description` (string, required): What is wrong or what you want. Include enough detail to reproduce. No secrets.
- `projectid` (string): Optional project id this report relates to.

### `get_github` (~97 tokens)

Get GitHub connection

Shows whether this account has a GitHub repo connected, or lists files under a path in that repo. If not connected, the result includes installUrl — open it (GitHub App) to grant read access to one repo. Sign in on botkelp.com with GitHub first so the install is tied to your account.

Input parameters:

- `path` (string): Folder or file in the connected repo to list. Omit for connection status.

### `set_github` (~107 tokens)

Connect or disconnect GitHub

Returns a GitHub App install URL so the user can grant BotKelp read access to one of their repos. Open the URL, pick a single repo, approve. Then purchase_scaffold template_files: [{ source: "app/legal/" }] copies those pages into the clone. disconnect: true drops the connection. Prefer signing in with GitHub on botkelp.com first.

Input parameters:

- `disconnect` (boolean): true: drop the connected repo. Omit to mint a fresh install URL.

### `get_account_status` (~35 tokens)

Get account status

No params. Says whether you are signed in (authenticated) and account tools work (accountToolsReady). Never returns a key.

## Diagnostics

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

## Score history

- 2026-11-05: 87
- 2026-11-04: 86
- 2026-11-03: 86
- 2026-11-02: 86
- 2026-11-01: 85
- 2026-10-31: 85
- 2026-10-30: 84
- 2026-10-29: 84
- 2026-10-28: 83
- 2026-10-27: 83
- 2026-10-26: 82
- 2026-10-25: 82
- 2026-10-24: 81
- 2026-10-23: 81
- 2026-10-22: 80

## Common questions

### What is the BotKelp MCP server?

BotKelp is an MCP server listed in the public MCP registry as io.github.aiscimi-code/botkelp. Verified component catalog over remote MCP: agents pick ids and get a project that builds. This page covers its hosted endpoint (https://www.botkelp.com/mcp).

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

BotKelp scores 87 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 BotKelp MCP server expose?

BotKelp exposes 16 tools: get_help, search_components, get_component, purchase_scaffold, get_scaffold, and 11 more. Their descriptions and schemas cost roughly 1,578 tokens of context every time the server is loaded.

### Does the BotKelp MCP server require authentication?

Yes. BotKelp 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 BotKelp MCP server still maintained?

BotKelp is still listed as active in the MCP registry. We last reached this channel on 5 November 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.botkelp.com/mcp
- Repository: https://github.com/botkelp/components
- Website: https://www.botkelp.com/
- Changelog RSS feed: https://verifymcp.io/servers/aiscimi-code-botkelp/www.xml
- Changelog JSON feed: https://verifymcp.io/servers/aiscimi-code-botkelp/www.json
- HTML version of this page: https://verifymcp.io/servers/aiscimi-code-botkelp/www