engine
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@engine get system information"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
engine
A self-owned, model-agnostic AI agent client whose core is a native, host-agnostic plugin
system. Adding a tool — from a tiny helper to the full scribe transcriber — is one small act,
and the same tool works for both you (a REPL command) and the agent (a model tool). Plain
line-REPL by design: no fullscreen TUI, so Polish input, trackpad scroll and text selection just
work. Runtime is stdlib-only and portable (macOS now, Linux/3090 later).
Layout
engine/— core:config,backends(the model interface),plugins(contract + discovery),agent(the loop),repl(the client),cli(bare-shell host adapter).plugins/— drop-in plugins:sysinfo(tiny),scribe(big). Add one = add a file here.tests/— pytest suite (deterministic, no network).smoke/— live checks against a real model (Ollama).tools/check_polish_input.py— a Polish-keyboard input check.
Related MCP server: cc-plugin-mcp
Run
# REPL (talks to qwen3:8b via Ollama by default):
PYTHONPATH=. .venv/bin/python -m engine.repl
# force the deterministic mock model instead:
ENGINE_BACKEND=mock PYTHONPATH=. .venv/bin/python -m engine.repl
# run a plugin straight from the shell (no model):
PYTHONPATH=. .venv/bin/python -m engine.cli sysinfo
PYTHONPATH=. .venv/bin/python -m engine.cli scribe --helpAdd a plugin (zero core edits)
Create plugins/hello.py:
from engine.plugins import SimplePlugin
PLUGIN = SimplePlugin("hello", "say hi",
{"type": "object", "properties": {"input": {"type": "string"}}},
lambda a: "hi " + str(a.get("input", "")))It is now a REPL command (/hello), a CLI command, and a tool the agent can call.
Swap the model (one value)
ENGINE_BACKEND=ollama|mock|anthropic (+ ENGINE_OLLAMA_MODEL / ENGINE_ANTHROPIC_MODEL). A new
provider is one branch in engine/backends.py:get_backend. (anthropic is code-complete + unit-tested
for wire format; going live needs ANTHROPIC_API_KEY.)
Use the plugins inside Claude Code (MCP)
The same plugins are exposed to Claude Code via a hand-rolled MCP stdio server (stdlib, zero deps):
# from the repo root:
claude mcp add engine -- "$PWD/.venv/bin/python" -m engine.hosts.mcp_serverThen Claude Code can call sysinfo / calc / scribe as tools — the identical plugins your REPL uses.
Tests
.venv/bin/python -m pytest . # 36 deterministic tests
.venv/bin/python smoke/ollama_agent_smoke.py # live: a real model calls a plugin
.venv/bin/python smoke/filter_spike.py # Phase-2 taste: bge-m3 separates real vs junk (toy)Available Tools
3 toolscalcB
Evaluate an exact arithmetic expression (+, -, *, /, **, %). Use for any calculation.
Inputs: expression.
scribeA
Run the scribe CLI (video -> transcript for AI). Pass CLI arguments, e.g. args=['--help'] or args=['', '--dry-run', '--json'].
Inputs: args.
sysinfoB
Report this machine's OS, CPU count and RAM. No arguments needed.
Inputs: verbose.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 3 tools
Each tool has a clearly distinct purpose: calc for arithmetic, scribe for video transcription, sysinfo for system information. There is no overlap or ambiguity between them.
All tool names are lowercase single words (calc, scribe, sysinfo), which is consistent in style. However, they don't follow a strict verb_noun pattern, and one is an abbreviation (calc) while another is a concatenation (sysinfo).
Having three tools is borderline appropriate given the server name 'engine' implies a broad utility scope. The count feels thin but not extreme, and each tool seems self-contained.
The tools cover a calculator, a video transcriber, and system info, which are unrelated domains. There are obvious gaps if this is meant as a general-purpose engine (e.g., no file operations, no networking). The set feels incomplete for any coherent purpose.
Related MCP Connectors
Shared memory MCP server for Claude Code, Codex, Gemini CLI and Cursor. Cited, editable.
Nifty's MCP server — exposes tasks, projects, messages, and files as tools for AI agents.
MCP server for your apps' tools and custom tools, plus hosted AI agents and approval-gated workflows
Connect ChatGPT and Claude to your Mac, Windows or Linux with secure MCP remote access.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceA transport-agnostic MCP server that integrates multiple AI coding agents (Claude Code, Gemini, and Codex) with built-in tools for command execution, calculations, and streaming capabilities. Supports both STDIO and HTTP transports for flexible deployment.18 npm1MIT
- AlicenseBqualityDmaintenanceMCP server for accessing Claude Code plugins. Enables retrieving plugin lists and detailed information via MCP clients like Claude Desktop, Cursor.227 PyPIMIT
- AlicenseAqualityFmaintenanceMCP server for running external coding agents as background tasks inside Claude Code. Supports multiple backends including Codex, Grok, GLM, DeepSeek, and more.7MIT
- AlicenseAqualityCmaintenanceA local stdio MCP service that unifies coding agents like Codex and Claude into cs_agent_* tools, enabling the root agent to create, invoke, and manage child agents with recursive delegation.1456 npm2MIT