Engee documentation

Tools

A tool is a separate operation that the agent calls through Engee MIND with formal arguments. The user usually formulates the task in text; the agent selects a tool, passes the parameters, and analyzes the response.

There are currently 17 tools available. The LLM client can add a server prefix to the technical names.

Tool Reference

The table shows the subject arguments. For the first check, send the PAT to the chat with the agent; the issue is described in external API documentation Engee.

The tool Task Arguments Result and purpose

engee_status

No

The state of the environment; without PAT prompts for authorization and built—in skills. Called first

engee_start

No

Launches the environment and waits for it to be ready; returns information about the found user skills

engee_stop

No

Stops the work environment, frees up computing resources

eval_code

code

Executes the Julia code in the session; returns a string representation of the last expression

job_create

code, optional name

Creates a long-running independent background task and returns job_id

job_status

job_id

Returns the state IN_PROGRESS, DONE or ERROR and the available result

job_list

No

Shows the background tasks of the current user session

file_list

Optional path, by default /user

List of files and directories in the session

file_upload

remote_path, content_base64

Uploads the contents of the file to the session using the absolute path

file_download

remote_path

Returns the name, size, and contents of a file from the session for saving or displaying by the client

engee_diagnose

model_name

Model status, logs, blocks, port connections, and the model script

engee_screenshot

model_name

Creates a PNG of the canvas in the session and returns its path; the model should be open

block_categories

No

Block library categories and their contents

block_search

query, optional offset

Searches for blocks by name, category, or keyword; returns up to 30 matches per call

block_info

block_path from the search

Exact parameters, acceptable values, ports, and a sign of direct signal transmission

skill_list

No

A list of available skills and their sources; takes into account user skills in the session

skill_load

skill_path

The text of the skill or its help file

How the tools are combined

engee mind 2

Not every task needs all the steps. To view the help, you can download a common skill without running a custom environment.

Examples of arguments

Block Search:

{
  "query": "integrator",
  "offset": 0
}

Uploading a basic skill:

{
  "skill_path": "engee_model"
}

Diagnostics of an already open model in an authorized environment:

{
  "model_name": "MyModel",
  "server": "https://engee.com",
  "token": "<PAT_ENGEE>"
}

<PAT_ENGEE> — a placeholder, not a valid token. These fragments describe the arguments for invoking the tool, not the configuration of the MCP client.

Features of execution and files

  • engee_stop stops the entire work environment. Unsaved models and variables in memory are lost; files saved in /user/, remain available. Challenge engee.stop() inside, Julia stops the simulation, not the session.

  • job_create it is executed in a separate context. Variables from eval_code they are not automatically transferred there. A long-running task should load the inputs itself, perform the calculation, and save the results.

  • file_download downloads a file, not a directory. The Base64 content must be decoded by the client into a file; a long Base64 string in a chat is not a convenient output.

  • engee_screenshot creates a snapshot of the circuit; to transfer the image to the user, then you need file_download on the way back.

  • eval_code modifies the model and files depending on the transmitted code. The permission for this tool actually allows the agent to perform calculations in the user environment; keep this in mind when configuring client rights.

The current list of a particular server takes precedence over the fixed number in this edition.