deterministic-logic
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@deterministic-logic Check if (A => B) => (!B => !A) is a tautology"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Deterministic Logic Evaluation MCP Toolkit (deterministic-logic-mcp)
A Model Context Protocol (MCP) server providing high-performance, deterministic logic evaluation tools for AI assistants and automated systems.
Features & Logic Engines
Propositional Logic & AST Evaluator: Parse and evaluate boolean expressions with full variable mapping. Supports
&&,||,!,^(XOR),=>(IMPLIES),<=>(IFF), and custom operator notation.Truth Table Generator: Compute complete $2^N$ truth tables, check tautologies, contradictions, and satisfiability.
DPLL SAT Solver: Convert formulas to Conjunctive Normal Form (CNF) and find satisfying variable assignments or prove UNSAT.
JSON Logic Rule Engine: Deterministic evaluation of structured rules (boolean, arithmetic, comparison, array filters/maps, conditional branching) against JSON datasets.
Decision Table Engine: Grid-based rule evaluation with support for wildcards,
first_match,all_matches, andstrict_single_match(determinism verification).State Machine Analyzer & Verifier: Check Finite State Machines (FSMs) for determinism, deadlocks, unreachable states, and state reachability path extraction.
Related MCP server: Logic-Thinking MCP Server
π οΈ MCP Tools Reference
Tool Name | Description | Key Arguments |
| Evaluates a boolean logic expression with variable values |
|
| Generates full truth table & computes Tautology / Contradiction |
|
| DPLL SAT solver returning satisfying variable assignment or UNSAT |
|
| Evaluates JSON logic rules against context JSON data |
|
| Evaluates matrix decision table rules with determinism checks |
|
| Checks FSM for determinism, deadlocks, and unreachable states |
|
| Finds shortest execution path to target state in FSM |
|
| Simulates an input sequence through an FSM step-by-step |
|
π Quickstart & Setup
Building Locally
npm install
npm run build
npm testConfiguring in MCP Clients (e.g. Claude Desktop, Cursor, AGY)
Add the following to your mcpServers configuration file (e.g. claude_desktop_config.json):
{
"mcpServers": {
"deterministic-logic": {
"command": "node",
"args": ["/home/mrovkill/Projects/deterministic-logic/dist/index.js"]
}
}
}Or run directly via npx / tsx:
{
"mcpServers": {
"deterministic-logic": {
"command": "npx",
"args": ["tsx", "/home/mrovkill/Projects/deterministic-logic/src/index.ts"]
}
}
}π‘ Example Tool Usage
1. Truth Table Generation
Input: expression = "A => (B => A)"
Output: isTautology = true, isSatisfiable = true, truthTable rows showing all evaluated combinations.
2. DPLL SAT Solving
Input: expression = "(A || B) && (!A || B) && (!B)"
Output: satisfiable = false (UNSAT).
3. JSON Logic Rule Execution
Input:
{
"rule": {
"and": [
{ ">": [{ "var": "user.age" }, 18] },
{ "in": [{ "var": "user.role" }, ["admin", "editor"]] }
]
},
"data": { "user": { "age": 25, "role": "admin" } }
}Output: result = true.
π License
MIT
Available Tools
8 toolsanalyze_state_machineA
Formally analyzes a Finite State Machine (FSM) for determinism, unreachable states, and deadlock states.
Inputs: transitions (required), initialState (required), states, terminalStates.
evaluate_booleanA
Evaluates a boolean logic expression given a variable assignment map. Operators: &&, ||, !, ^ (XOR), => (IMPLIES), <=> (IFF).
Inputs: env (required), expression (required).
evaluate_decision_tableB
Evaluates a matrix of decision rules against input context. Checks table for completeness and determinism.
Inputs: rows (required), inputs (required), mode.
evaluate_json_logicA
Evaluates deterministic JSON Logic rules against a context dataset. Supports boolean, comparisons, math, conditionals, and array rules.
Inputs: rule (required), data.
generate_truth_tableA
Generates a complete truth table for a boolean logic expression and analyzes whether it is a Tautology, Contradiction, or Satisfiable.
Inputs: expression (required), maxVariables.
simulate_state_machineC
Simulates a sequence of inputs step-by-step through a state machine deterministically.
Inputs: transitions (required), initialState (required), inputSequence (required).
solve_satA
DPLL SAT solver for boolean satisfiability. Converts expression to Conjunctive Normal Form (CNF) and finds satisfying assignments or proves UNSAT.
Inputs: expression (required).
verify_state_reachabilityA
Checks whether a target state can be reached from the initial state in a state machine, returning the shortest path execution sequence.
Inputs: targetState (required), transitions (required), initialState (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelogβ¦
TDQS
Scored across 8 tools
Each tool targets a distinct aspect of logic and state machine analysis: boolean logic evaluation, truth table generation, SAT solving, JSON logic evaluation, decision table analysis, FSM analysis, reachability, and simulation. No significant overlap.
All tools follow a consistent verb_noun pattern (evaluate_boolean, generate_truth_table, solve_sat, etc.), with clear verbs and specific nouns. The naming is predictable and easy to understand.
Eight tools is well-scoped for the domain, covering boolean logic, SAT, JSON logic, decision tables, and state machines without being too few or too many. Each tool serves a clear purpose.
The tool surface covers core operations for boolean logic (evaluate, truth table, SAT) and state machines (analysis, reachability, simulation). Minor gaps exist (e.g., no JSON logic validation, no state machine minimization) but do not hinder primary workflows.
Maintenance
Related MCP Connectors
Free deterministic tools for math, data transforms, dates, text, statistics, finance, and units.
Create and evaluate versioned decision models with reproducible results and declared assumptions.
Deterministic reasoning stack for AI agents: simulate, decide & compute, plus cross-domain tools.
26 deterministic tools: PDF, image, QR, CSV/Excel, HTML to PDF, DNS/RDAP, FX rates, time zones.
Related MCP Servers
- AlicenseAqualityDmaintenanceEnables first-order logic reasoning including theorem proving, model finding, counterexample detection, and category theory diagram verification using pure TypeScript with no external dependencies.134MIT
- AlicenseNot gradedqualityDmaintenanceEnables formal logical reasoning, mathematical problem-solving, and proof construction across 11 logic systems including propositional, predicate, modal, fuzzy, and probabilistic logic. Integrates external solvers (Z3, ProbLog, Clingo) for advanced reasoning, with support for proof storage, argument scoring, and cross-system translation.1MIT
- AlicenseNot gradedqualityDmaintenanceProvides deterministic tools for symbolic math, equation solving, relation verification, reasoning structure audits, and validated CAD primitives, returning evidence artifacts for every result.MIT
- AlicenseNot gradedqualityBmaintenanceProvides deterministic decision and constraint evaluation for AI agents. Supports ruleset validation, fact evaluation, and constraint checking via MCP tools.Apache 2.0