Kael MCP Server

Server Details

16 AI-native tools with dual SSE + streamable-http transport. Free tier available.

Status: Healthy
Last Tested: 2026-03-27 13:31
Transport: Streamable HTTP
URL
Repository: dreamingms/kael-mcp-server
GitHub Stars: 1
Server Listing: Kael MCP Server

See and control every tool call

Log every tool call with full inputs and outputs

Control which tools are enabled per connector

Manage credentials once, use from any MCP client

Monitor uptime and get alerted when servers go down

Available Tools

8 tools

cancel_taskInspect

Cancel a queued or running background task.

ParametersJSON Schema

Name	Required	Description	Default
`task_id`	Yes	Task ID to cancel

check_taskInspect

Check the status and results of a background task. Returns output when completed, error details when failed.

ParametersJSON Schema

Name	Required	Description	Default
`task_id`	Yes	Task ID returned by run_task

code_runInspect

Execute code in a sandboxed environment and return stdout/stderr. Supports JavaScript (Node.js), Python 3, and Bash. 5-second timeout, 50KB output limit.

ParametersJSON Schema

Name	Required	Description	Default
`code`	Yes	Code to execute
`language`	No	Language: javascript, python, bash	javascript

pdf_extractInspect

Extract text content from a PDF at a given URL. Returns page count, metadata, and full extracted text. Handles the heavy lifting of PDF parsing.

ParametersJSON Schema

Name	Required	Description	Default
`url`	Yes	URL of the PDF to extract text from

run_taskInspect

Submit a background task for async execution. Returns immediately with a task_id. Use check_task to poll for results. Ideal for long-running operations (data processing, web scraping, builds) that would waste tokens if done synchronously.

ParametersJSON Schema

Name	Required	Description
`env`	No	Environment variables as {KEY: VALUE}
`name`	No	Human-readable task name for identification
`script`	Yes	Bash script or command to execute
`timeout`	No	Max execution time in seconds (default: 300, max depends on tier)
`callback_url`	No	URL to POST results when task completes

screenshotInspect

Take a screenshot of any webpage. Returns a PNG image as base64. Uses headless Chromium/Playwright. Useful when the AI needs to see what a page looks like.

ParametersJSON Schema

Name	Required	Description
`url`	Yes	URL to screenshot
`width`	No	Viewport width (320-1920)
`height`	No	Viewport height (200-1080)
`fullPage`	No	Capture full page scroll

web_fetchInspect

Fetch a web page and extract its readable content as clean text/markdown. Handles redirects, strips ads/nav/scripts, extracts main content, title, description, and top links. Much cheaper than having the LLM process raw HTML.

ParametersJSON Schema

Name	Required	Description
`raw`	No	Return raw HTML instead of extracted text
`url`	Yes	URL to fetch
`maxChars`	No	Maximum characters to return

web_searchInspect

Search the web and return structured results with titles, URLs, and snippets. Returns real-time search results the LLM cannot access from training data.

ParametersJSON Schema

Name	Required	Description	Default
`count`	No	Number of results (1-10)
`query`	Yes	Search query

Verify Ownership

Claim this connector by publishing a /.well-known/glama.json file on your server's domain with the following structure:

{
  "$schema": "https://glama.ai/mcp/schemas/connector.json",
  "maintainers": [
    {
      "email": "your-email@example.com"
    }
  ]
}

The email address must match the email associated with your Glama account. Once verified, the connector will appear as claimed by you.

Server Details

Available Tools

Verify Ownership

Discussions

Your Connectors

Resources