ZTL Judge
Server Details
Zero-trust logic judge: ZFL claims, algebra derivation steps, sets defined by a property.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- Repository
- inventor1975/ztlstudio
- GitHub Stars
- 0
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 6 tools
The main judging kernels are clearly distinct: judge handles ZFL documents, check_steps checks algebra derivations, and judge_naive handles property-defined sets with self-reference. The only soft overlaps are examples vs. checker_examples and judge vs. judge_naive, but their descriptions make the intended targets reasonably clear.
All names use lowercase snake_case, but there is no consistent verb_noun convention: check_steps is verb_noun, judge is a bare verb, examples and language are nouns, and checker_examples and judge_naive use different modifier patterns. The names remain readable, but the pattern is mixed.
Six tools is a compact and appropriate surface for a specialized judging engine with two additional kernels plus language and example helpers. Each tool maps to a recognizable use case, even if the two example helpers could theoretically be consolidated.
The surface covers the core lifecycle: learn the ZFL language, fetch worked examples and ready-made requests, judge ZFL documents, check algebra derivations, and judge naive set definitions. No obvious operational gap exists for the stated purpose, and the judge tools return detailed verdicts rather than leaving dead ends.
Available Tools
6 toolschecker_examplesBInspect
Ready requests for check_steps and judge_naive (the kernels' own examples).
Inputs: no named parameters. Returns: object
check_stepsAInspect
Check an algebra derivation step by step: does each step keep exactly the same solutions?
Args:
request: {"equations": ["x^2 = x", "x = 1"], "var": "x", "domain": [lo, hi] or null,
"domain_verified": true}. Each equation is the next step; one unknown; + - * / ^ with whole powers.
Returns:
The chain's verdict (its weakest step) and each step's: EARNED = same solutions on the domain;
ON CREDIT = the same, on an unverified domain; REFUTED = a solution is lost (e.g. cancelling a factor that
can be 0) or gained (e.g. clearing a denominator where the original was undefined), with the witness and
the cause; E = the step divides by an expression that is 0 for every value. A request above the public
limits is refused with the reason (ok: false, refused).
Inputs: request (required). Returns: object
examplesBInspect
Worked examples: questions already written as ZFL documents, ready to judge.
Inputs: no named parameters. Returns: object
judgeAInspect
Judge a ZFL document with ZTL, a zero-trust logic: three values, two-valued connectives.
Args:
document: The ZFL document, as an object or as JSON text:
{"rows": [{"name": ..., "means": ..., "status": ..., "ground": ...}], "claim": ...}.
Returns:
The verdict with its disposition and grade, the receipt, the
instruments that applied, the issues found, and what the core read.
Read the verdict WITH its disposition: T EARNED = established; F REFUTED = false; F OPEN or Z OPEN = NOT ESTABLISHED, it could still turn either way (do not report it as false) — `why` and `unverified` say what to check; ON CREDIT = holds only on an unverified ground. A compound claim gets T or F; a claim that is a single name gets that name's own value, Z while unverified.
The full report is returned whatever `ask` says.
Inputs: document (required). Returns: object
judge_naiveAInspect
Judge sets defined by a property, self-reference allowed (Russell's set, a web of trust, a policy rule).
Args:
universe: {"sets": {name: {"list": [...]} | {"data": {name: "T"|"F"|"Z"}} | {"abs": formula}},
"claims": [formula, ...]}. Formulas: ["in", a, S], ["not", f], ["and"|"or"|"imp"|"iff", f, g],
["all"|"ex", "y", f], ["eq", S, T]; an abs set's own variable is "x". Every name is also an object.
Returns:
Per set: the members and non-members the definitions ground, and a passport for each membership they
leave undecided — PARADOX (no stipulation can repair it), UNDERDETERMINED (consistent; a decision is
owed), INTRINSIC, INPUT (verify the given cell), DOWNSTREAM (inherits a quarantine). Per claim: EARNED /
REFUTED / EARNED IF STABLE / REFUTED IF STABLE / OPEN, the cells it rests on with their passports, and for
a universal claim the instances left undecided. Oversized requests are refused with the reason.
Inputs: universe (required). Returns: object
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Deterministic sealed verdicts on public claims and startup ideas (0-LLM claim-safety guardian).
Deterministic signed verification of numeric & financial claims for AI agents & spreadsheets.
Jailbreak-proof AI guardrails. Automated Reasoning SMT solver, not an LLM. ZK proofs included.
Lean4 formal proof, delivered per API call as an atom service on Conduit Atoms.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceEnables rigorous, machine-checked mathematical proving and proof review through 23 local tools that formalize propositions, verify each inference step with SMT and symbolic solvers, search for counterexamples, and run exact number-theoretic and high-precision arithmetic. Verdicts are strictly separated into proven, refuted, inconclusive, verified, sound_with_gaps, and flawed, so unproven steps are disclosed rather than hidden.MIT
- AlicenseNot gradedqualityCmaintenanceEnables LLMs and agents to verify multi-hop relational claims before asserting them, using zero-token relation-algebra proofs with precision guarantees. It supports opt-in calibration guards for entity normalization and relation transitivity.1MIT
- FlicenseAqualityDmaintenanceA calibrated faithfulness screen for informal↔Lean 4 statement pairs, served over MCP. It provides deterministic checks and deep LLM-based analysis to help draft Lean statements.27-
- 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
Glama MCP Gateway
Add one secure layer between your agents and this server.