analyze_code_fileLABSCO SUMMARY
Take the whole runtime, or just the server you needed.
The servers are separable, and that is the practical way in: any MCP client can be pointed straight at one server's server.py under servers/ for the one capability you want, with no obligation to adopt the client, the scheduler or the memory layer. Taken whole it is an ambitious local-first stack, and the honest reading is that ambition costs — Ollama, several pulled models and the RAM to hold them. The per-server key requirements are listed up front, which makes it easy to run only the parts you can actually authenticate.
What it is
A local MCP runtime with a set of tool servers behind it. You can run the whole thing — a web client, multi-agent orchestration, persistent memory and a job scheduler — or ignore that and point any MCP client at the individual servers in the repository. Inference runs through Ollama locally rather than a hosted model. The README counts 95 tools across 13 servers.
What you get
- Code work: analysis, generation and refactoring in
code_assistant(12 tools), review and bug fixing incode_review(3 tools), and a Python and bash execution sandbox incode_runner(4 tools) - Gmail and Google Calendar in
google(13 tools), reachable through either OAuth or an Apps Script deployment - A media library with ML-driven recommendations in
plex(18 tools), and notes intrilium(11 tools) - Vector search and management in
rag(8 tools), which needs Ollama withbge-largepulled, plussession_history_toolfor reading the current session's messages back in order - Text processing and web search in
text(8 tools), image search, analysis and generation inimage(6 tools) — image generation is free, search needsSERPER_API_KEY, and the Shashin photo-gallery tools (shashin_search,shashin_random,shashin_analyze) need a running Shashin server withSHASHIN_BASE_URLandSHASHIN_API_KEY - Weather, time and location in
location(3 tools), using Open-Meteo with no key and falling back to OpenWeatherMap if one is set - Machine facts in
system(3 tools), GitHub repo clone, browse and cleanup ingithub(4 tools), and Discord webhook notifications indiscord(2 tools) - If you run the client too: persistent memory across sessions, RAG over your documents, a proactive job scheduler, and a web UI at
http://localhost:9000/client/ui/index.html
Requirements
Python 3.12+, Ollama installed, and 16GB or more of RAM recommended. Models are pulled per capability: a tool-calling model for inference, a small one for routing, bge-large for RAG embeddings and a vision model for image work; local GGUF files work too. Individual servers need only their own keys — SERPER_API_KEY for image search, PLEX_URL and PLEX_TOKEN for the media library, TRILIUM_URL and TRILIUM_TOKEN for notes, DISCORD_WEBHOOK_URL for notifications — and Google works through Apps Script as an alternative to OAuth. Setup is a virtualenv and pip install -r requirements.txt; on WSL2 create the venv in the Linux filesystem, since NTFS cannot hold the symlinks a venv needs. The client package is mcp-client-ui (1.0.0). The project describes itself as experimental and for personal use rather than production.
Setup effort
Build from source — git clone https://github.com/MichaelYagi/mcp-platform.git
USE CASES
01
Running an assistant with no hosted model
Point everything at a local Ollama install so inference, embeddings and vision all stay on your own machine.
02
Taking just one capability into your existing client
Add a single server — the code sandbox, the RAG search, the location tools — to a client you already use, and skip the rest.
03
Searching your own documents
Pull bge-large, ingest into the RAG server, and query your material as vector search from the assistant.
04
Wiring email and calendar in without an OAuth project
Deploy the bundled Apps Script as a web app and point the Google tools at that URL instead of setting up OAuth credentials.
95 tools
Listed in project code.
fix_code_filesuggest_improvementsexplain_codegenerate_testsrefactor_codegenerate_codeanalyze_projectextend_codedetect_inconsistenciesexplain_architectureexplain_change_impactreview_codesearch_code_in_directorydebug_fixrun_pythonrun_python_filerun_bashpip_installdiscord_notifydiscord_list_webhooksgithub_clone_repogithub_list_filesgithub_get_file_contentgithub_cleanup_repogmail_get_unreadgmail_get_recentgmail_get_emailgmail_send_emailcalendar_get_todaycalendar_get_this_weekcalendar_create_eventgmail_reply_toolgmail_searchgmail_check_repliedget_day_briefinggoogle_reauth_startgoogle_reauth_completeanalyze_image_toolshashin_search_toolshashin_random_toolshashin_analyze_toolweb_image_search_toolgenerate_image_toolget_location_toolget_time_toolget_weather_toolrag_diagnose_plex_toolsemantic_media_search_textscene_locator_toolfind_scene_by_titleplex_find_unprocessedplex_ingest_itemsplex_ingest_singleplex_ingest_batchrag_rescan_no_subtitlesplex_get_statsimport_plex_historyauto_train_from_plexrecord_viewingtrain_recommenderrecommend_contentget_recommender_statsreset_recommenderauto_recommend_from_plexsession_history_toolrag_add_toolrag_search_toolrag_status_toolrag_browse_toolrag_list_sources_toolrag_delete_source_toolrag_delete_document_toolget_hardware_specs_toolget_system_infolist_system_processessummarize_text_toolexplain_simplified_toolconcept_contextualizer_toolread_file_tool_handlerimprove_text_toolweb_search_toolweb_fetch_toolsummarize_url_toolsearch_notessearch_by_labelget_note_by_idcreate_noteupdate_note_contentupdate_note_titledelete_noteadd_label_to_noteget_note_labelsget_note_childrenget_recent_notesBEFORE YOU INSTALL
What to know first
Tools you get
95 tools registered in the project's code.
Requires
- Python 3.12+
- 16GB+ RAM recommended
- Ollama installed
Where it runs
Both documented clients run the server on your machine.
INSTALLATION
Connect your client
You clone this one yourself.
Server setup
TERMINAL
git clone https://github.com/MichaelYagi/mcp-platform.git
cd mcp-platform
python3 -m venv .venv
source .venv/bin/activate # Linux/macOS (.venv\Scripts\activate on Windows PowerShell)
pip install -r requirements.txt
curl -fsSL https://ollama.com/install.sh | shStart Ollama in a separate terminal and leave it running (ollama serve stays in the foreground):
TERMINAL
OLLAMA_HOST=0.0.0.0:11434 ollama serveThen, back in the first terminal, pull the models:
TERMINAL
ollama pull qwen2.5:14b-instruct-q4_K_M
ollama pull qwen2.5:0.5b
ollama pull bge-large
ollama pull qwen3-vl:8b-instructCreate .env in the project root. These are the README's minimal .env lines; OLLAMA_TOKEN and SERPER_API_KEY are your own Ollama and Serper keys.
FILE · .env
OLLAMA_VISION_MODEL=qwen3-vl:8b-instruct
DISABLED_TOOLS=plex:*,image_tools:shashin_analyze,shashin_random,shashin_search
OLLAMA_TOKEN=<YOUR_OLLAMA_TOKEN>
SERPER_API_KEY=<YOUR_SERPER_API_KEY>Then start the client.
TERMINAL
python client.pyMCP Clients
Claude Desktop, Any MCP client
JSON
{
"mcpServers": {
"code_assistant": {
"command": "<YOUR_PATH_TO_MCP_PLATFORM>/.venv/bin/python",
"args": [
"<YOUR_PATH_TO_MCP_PLATFORM>/servers/code_assistant/server.py"
]
}
}
}
