Sandbox
@AtomGraph/Web-Algebra

MCP server for RDF and SPARQL operations

Web-Algebra exposes RDF and SPARQL operations as MCP tools and as executable JSON workflows. Instead of calling many tools one by one, an agent can build a whole RDF workflow and run it through the execution engine. It also includes LinkedDataHub-specific operations for creating and managing portal content.

45 stars4 forksPythonUpdated 2mo ago
Agentic Content Management with Web-Algebra MCP
AtomGraph377 views • 1 year ago
Who it's for

Builders who want an agent to work with RDF Linked Data, SPARQL, or LinkedDataHub.

What it delivers

You can turn natural-language requests into RDF workflows that run as one executable JSON operation set.

What it does

JSON operation DSL

Uses `@op` and `args` to describe nested RDF operations in JSON.

MCP tool server

Exposes the operations through Model Context Protocol over stdio or HTTP.

Linked Data operations

Includes `GET`, `POST`, `PUT`, `PATCH`, and other read-write Linked Data actions.

SPARQL operations

Supports `SELECT`, `CONSTRUCT`, `DESCRIBE`, `VALUES`, and `SPARQLString`.

Schema extraction

Provides `ExtractClasses`, `ExtractDatatypeProperties`, `ExtractObjectProperties`, and `ExtractOntology`.

LinkedDataHub helpers

Adds portal and resource creation operations such as `ldh-CreateItem`, `ldh-GeneratePortal`, and `ldh-AddView`.

Prompt and semantics spec

Defines the operation catalog and JSON format in `prompts/system.md` and `formal-semantics.md`.

How to get it

  1. 1Install uv
    uv venv
    uv sync
  2. 2Run
    uv run python src/web_algebra/main.py
  3. 3Run
    uv run python src/web_algebra/main.py --from-json ./examples/united-kingdom-cities.json
  4. 4Execute src/web_algebra/main.py, it expects the path to your LDH's owner certificate and…
    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 **********
  5. 5Run
    uv run python -m web_algebra
  6. 6Run
    uv run uvicorn web_algebra.server:app --reload

README

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:

  1. Executable JSON format: Operations are composed into JSON structures and executed by the provided execution engine
  2. 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

 Agentic Content Management with Web-Algebra MCP

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 @op key with args for parameters, supporting nested operation calls
  • RDFLib Type System: Uses URIRef, Literal, Graph, and Result types 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 ResolveURI operation

Key Components

Operations

The operations cover read-write Linked Data, SPARQL queries, URI manipulation, and LinkedDataHub-specific resource creation. Non-exhaustive list:

  • Linked Data
    • GET
    • PATCH
    • POST
    • PUT
  • SPARQL
    • CONSTRUCT
    • DESCRIBE
    • SELECT
    • Substitute
    • Values
    • SPARQLString
  • Schema
    • ExtractClasses
    • ExtractDatatypeProperties
    • ExtractObjectProperties
    • ExtractOntology
  • URI & String Operations
    • ResolveURI
    • EncodeForURI
    • Concat
    • Replace
    • Str
    • STRUUID
    • URI
  • Control Flow & Variables
    • Value
    • Variable
    • ForEach
    • Filter
    • Bindings
    • Current
    • Execute
    • Merge
  • LinkedDataHub-specific
    • ldh-CreateContainer
    • ldh-CreateItem
    • ldh-List
    • ldh-AddFile
    • ldh-AddGenericService
    • ldh-AddResultSetChart
    • ldh-AddSelect
    • ldh-AddView
    • ldh-AddObjectBlock
    • ldh-AddXHTMLBlock
    • ldh-RemoveBlock
    • ldh-GeneratePortal
    • ldh-GenerateClassContainers
    • ldh-GenerateOntologyViews

Usage

Pre-requisites

  1. Install uv
  2. 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

  1. Run LinkedDataHub v5
  2. 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.

Files in the repo

Repository payload13 top-level entries
  • .github
  • examples
  • prompts
  • src
  • tests
  • .gitignore
  • CLAUDE.md
  • examples.md
  • formal-semantics.md
  • LICENSE
  • pyproject.toml
  • README.md
  • uv.lock

Discussion (0)

Ask about usage, or say what you built with it

Sign in to join the discussion.

No comments yet. Be the first to say what this is good for.

More connectors

Real-time global intelligence dashboard. AI-powered news aggregation, geopolitical monitoring, and infrastructure tracking in a unified situational awareness interface

86k

High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 158 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies.

43k

Universal provider proxy for OpenAI Codex & Claude Code — use any LLM (Claude, Gemini, Grok, DeepSeek, Ollama…) with Codex CLI, App, SDK, and Claude Code

14k
okf-memory/
okf-agent-memory

Git-native persistent memory for AI coding agents. Implements Google OKF v0.2 with sub-300µs in-memory BM25 search, embedded MCP server, and progressive disclosure. Slashes token bloat by 80% with zero external databases or dependencies. Built in pure Go.

547
tirth8205/
code-review-graph

Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, with benchmarked context reductions on reviews and large-repo workflows.

31k
2akouwu/
reverify

Stop your AI from making things up — it proposes, deterministic tools decide, every claim checked against ground truth with evidence. Grounded facts and context survive resets. Reverse engineering is the proving ground. MCP server + CLI.

1.1k