Web-Algebra
Suite of generic Linked Data/SPARQL as well as LinkedDataHub-specific MCP tools
Web-Algebra
A composable RDF operations system that translates natural language instructions into JSON-formatted domain-specific language operations for loading, querying, and writing RDF Linked Data.
Overview
This system implements generic operations for RDF Linked Data and SPARQL management, as well as some LinkedDataHub-specific operations. Operations can be consumed in two ways:
- Executable JSON format: Operations are composed into JSON structures and executed by the provided execution engine
- Model Context Protocol (MCP): Operations are exposed as tools for AI agents to use interactively
Instead of agents executing semantic workflows step-by-step through individual MCP tool calls, Web-Algebra enables agents to compile entire workflows into optimized JSON "bytecode" that executes atomically - enabling complex multi-operation compositions.
Demo
See WebAlgebra in action - translating natural language into RDF operations.
Architecture
The system is built around the Operation abstract base class that provides:
- Registry System: Auto-discovery of operations from
src/web_algebra/operations/ - JSON DSL: Operations use
@opkey withargsfor parameters, supporting nested operation calls - RDFLib Type System: Uses
URIRef,Literal,Graph, andResulttypes internally for proper RDF handling - Execution Engine: Both standalone execution and MCP server integration
- Context System: ForEach operations set row context for inner operations to access via
Value - URI Resolution: Proper semantic URI construction with
ResolveURIoperation
Key Components
- System Prompt: Complete operation definitions and JSON format specification
- Formal Semantics: Complete type system and operation catalog
- Operation Interface: Base class and JSON interpreter
- Operation Implementations: Directory containing all available operations
- JSON Examples: Sample operation compositions
Operations
The operations cover read-write Linked Data, SPARQL queries, URI manipulation, and LinkedDataHub-specific resource creation. Non-exhaustive list:
- Linked Data
GETPATCHPOSTPUT
- SPARQL
CONSTRUCTDESCRIBESELECTSubstitute
- URI & String Operations
ResolveURIEncodeForURIConcatReplaceStrURI
- Control Flow & Variables
ValueVariableForEach
- LinkedDataHub-specific
ldh-CreateContainerldh-CreateItemldh-Listldh-AddGenericServiceldh-AddResultSetChartldh-AddSelectldh-AddViewldh-AddObjectBlockldh-AddXHTMLBlockldh-RemoveBlock
Usage
Pre-requisites
- Install uv
-
uv venv uv sync
Standalone
Natural language instruction
uv run python src/web_algebra/main.py
Then enter instruction, for example:
Select random 10 UK cities from DBpedia
See more examples
Currently requires OpenAI API access. OPENAI_API_KEY env value has to be set.
Execute JSON
uv run python src/web_algebra/main.py --from-json ./examples/united-kingdom-cities.json
See JSON examples.
With LinkedDataHub
- Run LinkedDataHub v5
- Execute
src/web_algebra/main.py, it expects the path to your LDH's owner certificate and its password as arguments. For example:
uv run python src/web_algebra/main.py --from-json ./examples/united-kingdom-cities.json \
--cert_pem_path ../LinkedDataHub/ssl/owner/cert.pem \
--cert_password **********
Here and throughout this guide, the client certificate/password arguments are only required for authentication with LinkedDataHub. You don't need them if you're not using LinkedDataHub with Web Algebra.
As MCP server
stdio transport
uv run python -m web_algebra
Streamable HTTP transport
uv run uvicorn web_algebra.server:app --reload
or with LinkedDataHub certificate credentials (change the path and password to yours):
CERT_PEM_PATH="/Users/Martynas.Jusevicius/WebRoot/LinkedDataHub/ssl/owner/cert.pem" CERT_PASSWORD="********" uv run uvicorn web_algebra.server:app --reload
MCP Inspector config
You can the inspector like this:
npx @modelcontextprotocol/inspector
and then open on the URL printed in its console output, for example:
http://localhost:6274/?MCP_PROXY_AUTH_TOKEN=b31e4b3d852b5a2445f45032c484e54e319bf16359585858cf88fe9a90816744
The MCP_PROXY_AUTH_TOKEN is required. If the link does not appear, you need to copy the session token from the console and paste it into inspector's Proxy Session Token config.
Web Algebra's settings:
- Transport Type
- Streamable HTTP
- URL
- http://127.0.0.1:8000/mcp
Claude Desktop tool config
Add Web Algebra entry (that uses stdio transport) to the mcpServer configuration your claude_desktop_config.json file:
{
"mcpServers": {
"Web Algebra": {
"command": "uv",
"args": [
"--directory",
"/Users/Martynas.Jusevicius/WebRoot/Web-Algebra/src",
"run",
"--with",
"mcp[cli]",
"--with",
"rdflib",
"--with",
"openai",
"python",
"-m",
"web_algebra"
],
"env": {
"CERT_PEM_PATH": "/Users/Martynas.Jusevicius/WebRoot/LinkedDataHub/ssl/owner/cert.pem",
"CERT_PASSWORD": "********"
}
}
}
}
Leave the command as it is. Those uv run --with arguments are important, otherwise 3rd party packages cannot be found.
On my Mac, the path to uv has to be absolute, otherwise it doesn't work in Claude Desktop 🤷♂️.
CERT_PEM_PATH and CERT_PASSWORD env values are optional.
相關伺服器
AsusWRT MCP Server
Model Context Protocol server for secure AsusWRT router administration via SSH. Provides 42+ read-only monitoring tools and guarded mutation tools for managing AsusWRT/Merlin routers.
Simtheory
MCP client with model switching, assistants and agentic mode.
AgentBazaar
A2A marketplace with 1800+ AI agents. Search, invoke, trade capabilities, datasets, prompts.
Revelata deepKPI
Deep fundamental data from SEC filings, including operational KPIs not found on Bloomberg, built for your financial AI agents.
Upstox MCP Server
A Model Context Protocol (MCP) server that integrates with the Upstox Trading API, enabling AI agents like Claude to securely access Indian stock market data, perform technical analysis, and view account information in read-only mode.
Geneva Forecasting MCP
MCP server that gives Claude and other AI assistants enterprise-grade time series forecasting powered by the Geneva Forecasting engine - the same forecasting engine shipped in Oracle products for 25+ years.
USDV Capital — Your Real Estate CFO
Real estate market intelligence, financial calculators, investment screening, and capital advisory for US investors. 86K+ locations, 23 tools.
mcp-datadog-server
Datadog MCP Server
Aegntic MCP Servers
A collection of Model Context Protocol (MCP) servers for various tasks and integrations, supporting both Python and Node.js environments.
Cycling Coach AI
AI-powered cycling training coach: personalized training plans, daily workouts, nutrition, strength training, fitness metrics (FTP, VO2Max), and Strava, Garmin, Wahoo, MyWhoosh, and Rouvy integrations.
