MCEPTION - YOUR MCP AGENCY

by alihmaoubisco.huggingface.alihmaoubis/mception

Create and deploy MCP servers using natural language.

  • Remote endpoint
  • 15 tools
  • MIT

Uptime

Checked  · every day

0%from 4 days of checks

Up without downtime on 0 of 4 days with data; down 4714 minutes in all, the longest 1440 minutes on 1 November.

  • No downtime
  • Degraded
  • Down over 5 minutes
  • No data
  • Not checked yet

How far each check got

  • Reached the address 100%
  • Completed the handshake 0.0%
  • Listed its tools 0.0%
Every day
DayResultChecksMedian
3 Nov (today)Down 932 minutes1–
2 NovDown 1440 minutes1of 1–
1 NovDown 1440 minutes1of 1–
31 OctDown 902 minutes10–

A failure counts as down time only when a second check five minutes later fails too. How we check

Connect to the publisher's own endpoint

Add to ~/.config/goose/config.yaml:

extensions:
  "mception":
    type: streamable_http
    name: "mception"
    enabled: true
    uri: "https://alihmaoubis-mception.hf.space/gradio_api/mcp/sse"
    headers: {}
    env_keys: []
    envs: {}
    timeout: 300

This server's endpoint speaks only SSE, which this client's documentation does not list among its transports; use another client for it.

For agents: the install prompt

Every step above as one Markdown text, for an assistant installing it for you.

# Install the MCP server MCEPTION - YOUR MCP AGENCY (`co.huggingface.alihmaoubis/mception`)

Its page: https://plug.directory/servers/co.huggingface.alihmaoubis/mception

It runs on the publisher's servers; the client connects to its URL.

Use the section for the person's client.

## Claude Desktop

Paste into Settings › Connectors › Add custom connector:

```text
https://alihmaoubis-mception.hf.space/gradio_api/mcp/sse
```

## Claude Code

Run in a terminal:

```sh
claude mcp add --transport sse mception https://alihmaoubis-mception.hf.space/gradio_api/mcp/sse
```

## Cursor, Devin Desktop, LM Studio, Gemini CLI, oterm, ECA

Merge into the place for the person's client:

- Cursor: ~/.cursor/mcp.json
- Devin Desktop: ~/.config/devin/mcp_config.json
- LM Studio: mcp.json (Program › Install › Edit mcp.json)
- Gemini CLI: ~/.gemini/settings.json
- oterm: config.json in oterm's data folder (~/Library/Application Support/oterm on macOS, ~/.local/share/oterm on Linux, %APPDATA%\oterm on Windows)
- ECA: ~/.config/eca/config.json (global) or .eca/config.json in the project

```json
{
  "mcpServers": {
    "mception": {
      "url": "https://alihmaoubis-mception.hf.space/gradio_api/mcp/sse"
    }
  }
}
```

## VS Code

Merge into .vscode/mcp.json:

```json
{
  "servers": {
    "mception": {
      "type": "sse",
      "url": "https://alihmaoubis-mception.hf.space/gradio_api/mcp/sse"
    }
  }
}
```

## Zed

This server's endpoint speaks only SSE, which this client's documentation does not list among its transports; use another client for it.

## Cline, AnythingLLM, Augment Code

Merge into the place for the person's client:

- Cline: cline_mcp_settings.json (MCP Servers › Configure › Configure MCP Servers)
- AnythingLLM: anythingllm_mcp_servers.json in the AnythingLLM storage plugins directory
- Augment Code: Augment Settings Panel – MCP section – Import from JSON (VS Code extension)

```json
{
  "mcpServers": {
    "mception": {
      "type": "sse",
      "url": "https://alihmaoubis-mception.hf.space/gradio_api/mcp/sse"
    }
  }
}
```

## Continue

Merge into ~/.continue/config.yaml:

```yaml
mcpServers:
  - name: "mception"
    type: sse
    url: "https://alihmaoubis-mception.hf.space/gradio_api/mcp/sse"
```

## Goose

This server's endpoint speaks only SSE, which this client's documentation does not list among its transports; use another client for it.

## Codex

This server's endpoint speaks only SSE, which this client's documentation does not list among its transports; use another client for it.

## mcp-client-cli, TUUI, BoltAI, Bob Shell, Kiro, Kiro CLI

This server's endpoint speaks only SSE, which this client's documentation does not list among its transports; use another client for it.

## Agenvoy

This server's endpoint speaks only SSE, which this client's documentation does not list among its transports; use another client for it.

## Amp

Merge into ~/.config/amp/settings.json (user) or .amp/settings.json (workspace):

```json
{
  "amp.mcpServers": {
    "mception": {
      "url": "https://alihmaoubis-mception.hf.space/gradio_api/mcp/sse"
    }
  }
}
```

Then restart the client, or reload its MCP servers, and ask it to list the server's tools to confirm it started.

Tools 15

  • MCEPTION__lambda_
  • MCEPTION_auto_fill_playground
  • MCEPTION_chat_response
  • MCEPTION_expert_step1_propose_implementation [Expert Tool - Step 1] Generates a Python implementation proposal without initializing a UI draft. Use this tool if you are an AI agent wanting to generate code from a spec before deciding to create a draft.
  • MCEPTION_expert_step2_define_logic [Expert Tool - Step 2] Defines the logic for a tool using JSON strings for complex arguments. Use this tool instead of `step_2_logic_definition` to avoid schema validation issues with complex nested JSON inputs.
  • MCEPTION_reload_tools
  • MCEPTION_save_config_ui
  • MCEPTION_step_0_configuration STEP 0: Configures the MCEPTION server environment. This step is needed to set up the Hugging Face environment. After that follow steps 1, 2, 3 in this order and keep track of the draft_id that you will receive. The process for each tool finishes when step 3 is a success. You have to follow all the steps for a tool before handling the next tool.
  • MCEPTION_step_1_initialisation_and_proposal STEP 1: Starts a new tool project and uses AI to propose draft code. Call this AFTER `step_0...`. It initializes the project and sets the optional HF_TOKEN. This is the entry point for creating a new MCP tool. It returns a draft_id and a code proposal based on the description.
  • MCEPTION_step_2_logic_definition STEP 2: Validates and saves the tool code. Call this AFTER `step_1...`. It saves the Python implementation into the draft before deployment.
  • MCEPTION_step_3_deployment STEP 3: Deploys the tool to a Hugging Face Space. Call this AFTER `step_2...`. It creates a new public Space (or updates it) with the tool's code. It requires the draf_id that you got from previous steps. When success, it gives some info to give to the user to help him add the resulting MCP server in his clients.
  • MCEPTION_update_deployment_summary

From Hugging Face Spaces. Report a problem