About Web Algebra
Web Algebra converts natural-language instructions into JSON DSL operations for loading, querying, and writing RDF Linked Data, and can execute those operations standalone. It is for agents building semantic data workflows, with composable operations that run together and additional LinkedDataHub-specific tools.
Key features
- 01RDF Linked Data read and write operations
- 02SPARQL querying and construction
- 03Nested JSON DSL composition
- 04Control flow, variables, and URI operations
- 05LinkedDataHub content operations
Use cases
- 01Compose multiple RDF data operations
- 02Query or update Linked Data
- 03Create LinkedDataHub resources and views
- 04Generate RDF operation plans from natural-language instructions
MCP support
Web Algebra exposes its operations as tools for MCP clients to use interactively. Multiple operations can also be composed as JSON DSL and executed atomically by its engine.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
uvx web-algebraCERT_PEM_PATHPath to the LinkedDataHub client certificate (PEM), for authenticated requestsCERT_PASSWORDSecretPassword of the client certificateOPENAI_API_KEYSecretOpenAI API key, used by SPARQLString to write queriesLocal servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.
Tools
33Saved tool list · updated 1w ago
| Parameter | Type | Required | Description |
|---|---|---|---|
| url | string | Yes | The URL to fetch RDF data from. This should be a valid URL pointing to RDF content. |
Details
From the project READMEWeb-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
- Examples: Real-world plans over live Linked Data, each with its result and checks
Operations
The operations cover read-write Linked Data, SPARQL queries, URI manipulation, and LinkedDataHub-specific resource creation. Non-exhaustive list:
- Linked Data
GETPATCHPOSTPUT
- SPARQL
CONSTRUCTDESCRIBESELECTSubstituteValuesSPARQLString
- Schema
ExtractClassesExtractDatatypePropertiesExtractObjectPropertiesExtractOntology
- URI & String Operations
ResolveURIEncodeForURIConcatReplaceStrStrUUIDURI
- Date/Time
Now
- Control Flow & Variables
ValueVariableForEachIterateFilterBindingsCurrentPositionLastMerge
- LinkedDataHub-specific
ldh-CreateContainerldh-CreateItemldh-Listldh-AddFileldh-AddGenericServiceldh-AddResultSetChartldh-AddSelectldh-AddConstructldh-AddViewldh-AddObjectBlockldh-AddXHTMLBlockldh-RemoveBlockldh-GeneratePortalldh-GenerateClassContainersldh-GenerateOntologyViews
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 the instructions of the examples.
Currently requires OpenAI API access. OPENAI_API_KEY env value has to be set.
Execute JSON
uv run web-algebra --from-json ./examples/city-profiles/plan.json
See the examples: each has the instruction it answers, its plan, the result of a run, and checks.
With LinkedDataHub
- Run LinkedDataHub v6
- Give
web-algebrayour LDH's owner certificate and its password in theCERT_PEM_PATHandCERT_PASSWORDenvironment variables (or the--cert_pem_pathand--cert_passwordoptions, which override them). For example:
export CERT_PEM_PATH=../LinkedDataHub/ssl/owner/cert.pem
export CERT_PASSWORD="$(cat ../LinkedDataHub/secrets/owner_cert_password.txt)"
uv run web-algebra --from-json ./examples/northwind-category-catalogue/plan.json
Here and throughout this guide, the client certificate and its password are only required for authentication with LinkedDataHub. You don't need them if you're not using LinkedDataHub with Web Algebra.
As MCP server
Install
Requires uv. Add this to your MCP client configuration (e.g. claude_desktop_config.json):
{
"mcpServers": {
"web-algebra": {
"command": "uvx",
"args": ["--from", "web-algebra", "web-algebra-mcp"],
"env": {
"CERT_PEM_PATH": "/path/to/LinkedDataHub/ssl/owner/cert.pem",
"CERT_PASSWORD": "********"
}
}
}
}
or with Claude Code:
claude mcp add web-algebra -e CERT_PEM_PATH=/path/to/LinkedDataHub/ssl/owner/cert.pem -e CERT_PASSWORD=******** -- uvx --from web-algebra web-algebra-mcp
uvx web-algebra mcp runs the same server.
Environment variables:
| Name | Required | Description |
|---|---|---|
CERT_PEM_PATH | No | Path to the LinkedDataHub owner certificate (PEM). Only needed for LinkedDataHub operations. |
CERT_PASSWORD | No | Password for the certificate above. |
OPENAI_API_KEY | No | OpenAI API key. Only needed for the SPARQLString tool, which asks a model to write the query. |
stdio transport
uv run web-algebra-mcp
Streamable HTTP transport
uv run uvicorn web_algebra.server:app --reload
with CERT_PEM_PATH and CERT_PASSWORD set, as above, for LinkedDataHub.
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 from a local checkout
To run the MCP server from a local checkout instead of the published package, add a Web Algebra entry (that uses stdio transport) to the mcpServer configuration your claude_desktop_config.json file:
{
"mcpServers": {
"Web Algebra": {
"command": "uv",
"args": [
"--directory",
"/path/to/Web-Algebra",
"run",
"web-algebra-mcp"
],
"env": {
"CERT_PEM_PATH": "/path/to/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.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.
