MCP Server Suite
Provides tools for web search and image search via a local SearXNG meta-search engine.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
MCP Server Suite
Five production-ready Model Context Protocol (MCP) servers built with the official Python SDK. Supports both stdio and HTTP/SSE transports.
This suite enables any MCP-compatible client (Claude Desktop, Cursor, OpenCode) to interact with restaurant data, web search, browser automation, and filesystem operations.
What is MCP?
MCP is an open standard that lets AI applications connect to external tools and data sources through a uniform interface. Think of it as USB-C for AI tools — write once, integrate everywhere.
Related MCP server: MCP Toolkit
Servers
1. restaurant_server (stdio)
Wraps restaurant ordering tools for MCP clients.
Tools: get_menu, check_dish_availability, check_quantity, add_item_to_cart, view_cart, get_suggestions, finalize_order
2. searxng_server (stdio)
Wraps a local SearXNG meta-search engine.
Tools: web_search, image_search
Supports categories, language, safesearch, time range, and result count
Uses
httpx.AsyncClientfor non-blocking requests
3. pinchtab_server (stdio)
Wraps a local PinchTab headless browser.
Tools: navigate, snapshot, click, fill, extract_text
Enables LLM-driven web browsing and form interaction
Communicates via PinchTab's REST API
4. filesystem_server (stdio)
Sandboxed filesystem operations with path traversal protection.
Tools: read_file, write_file, list_directory, search_files, file_stat, move_file, copy_file, delete_file
_resolve()enforces workspace sandboxing viaPath.relative_to()Binary files returned as base64
5. filesystem_server_sse (HTTP/SSE)
The same filesystem server exposed over Server-Sent Events on HTTP.
Built with Starlette + uvicorn + anyio memory streams
Per-session JSON-RPC message routing
Endpoints:
/(info),/sse(event stream),/messages(POST)
Quick Start
1. Install
pip install -r requirements.txt2. Configure MCP Client
Copy mcp.json.example to your client's config directory and update URLs:
cp mcp.json.example ~/.config/claude/mcp.json # Claude Desktop
cp mcp.json.example ~/.config/opencode/mcp.json # OpenCode3. Run Individual Servers
# stdio servers (spawned by MCP client)
python -m mcp_servers.restaurant_server
python -m mcp_servers.searxng_server
python -m mcp_servers.pinchtab_server
python -m mcp_servers.filesystem_server /path/to/workspace
# SSE server (runs as HTTP daemon)
python -m mcp_servers.filesystem_server_sse /path/to/workspace
# Then connect to http://localhost:3000/sseSSE Transport Deep Dive
The SSE server is the most technically interesting component:
# Per-session memory streams
rx_send, rx_recv = anyio.create_memory_object_stream(100)
tx_send, tx_recv = anyio.create_memory_object_stream(100)
# MCP server runs in background asyncio task
await server.run(rx_recv, tx_send, server.create_initialization_options())
# SSE handler serializes messages as JSON events
yield f"event: message\ndata: {message.model_dump_json()}\n\n"
# Client POSTs to /messages, injected into receive stream
await SESSIONS[session_id]["rx_send"].send(JSONRPCMessage.model_validate(data))Key design decisions:
Memory streams decouple HTTP I/O from MCP protocol logic
Session cleanup on disconnect prevents resource leaks
JSON-RPC message validation ensures protocol compliance
Environment Variables
Variable | Default | Description |
|
| SearXNG base URL |
|
| PinchTab API URL |
|
| Research report output directory |
|
| SSE server bind host |
|
| SSE server bind port |
Architecture
MCP Client (Claude Desktop / Cursor / OpenCode)
|
v
+-- stdio transport --+ +-- SSE transport --+
| python -m server | | http://host:3000 |
+--------------------+ +-------------------+
| |
v v
Restaurant Data Filesystem Ops
SearXNG Search (remote access)
PinchTab BrowserSecurity Notes
Filesystem sandboxing:
_resolve()prevents path traversal above workspace rootstdio transport: No open network ports — most secure option
SSE transport: Bind to
127.0.0.1or use reverse proxy with TLS for remote accessPinchTab IDPI: Restricts browsing to allowed origins by default
Testing
Each server can be tested manually:
# Test SearXNG MCP server
python -m mcp_servers.searxng_server
# Then send JSON-RPC messages via stdin
# Test filesystem SSE server
curl http://localhost:3000/
curl http://localhost:3000/sseTech Stack
Component | Technology |
MCP Framework |
|
HTTP Client |
|
SSE Server |
|
Data Format | JSON / JSON-RPC |
License
MIT
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
One MCP server for the services your AI needs: memory, files, Microsoft 365, kanban and more.
MCP server for your apps' tools and custom tools, plus hosted AI agents and approval-gated workflows
Sample shop MCP server: paginated search, idempotent orders, guarded cancellation. Four languages.
Remote MCP server exposing your Node Command fleet (files, shell, processes, browser) to AI hosts.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceA production-grade MCP server and client implementation with comprehensive features including structured logging, health checks, metrics, authentication, and RAG capabilities with PostgreSQL vector search. Supports both stdio and SSE transports with containerization and security features for enterprise deployment.MIT
- AlicenseNot gradedqualityDmaintenanceA collection of production-ready MCP servers for PostgreSQL, SQLite, Redis, File System, and GitHub API, enabling database operations, file management, and GitHub interactions through natural language.2MIT
- FlicenseNot gradedqualityBmaintenanceA production-grade MCP server framework providing multiple specialized servers for tabular data, documents, calendars, markdown, prompt engineering, and general utilities.-
- AlicenseNot gradedqualityCmaintenanceA monorepo of five signed MCP servers (journal-companion, market-scout, meeting-distiller, research-reader, writing-editor) with offline verifiable proof chains, shared core, and cross-bot provenance.1Apache 2.0