# Licklider agent-readable documentation

> Run the public verifier directly or through local MCP, decide when a bounded verification call applies, and interpret its returned evidence.

Website publication and update dates use UTC. Known times are recorded in UTC; historical date-only records do not imply midnight.

## Available now

- Anyone can install the public @licklider/nomue-verifier package from npm and run nomue verify locally to check a conforming Release 1 Record for independent two-group continuous outcomes under the two-sided Welch two-sample t procedure. It recomputes the covered numerical quantities and returns a machine-readable report of the scoped checks without calling a nomue server after installation.
- npm package: [@licklider/nomue-verifier](https://www.npmjs.com/package/@licklider/nomue-verifier/v/0.2.1-rc.1)
- CLI reference: [exact command surface](https://www.licklider.ai/docs/cli-reference.md), including the absence of help and version commands in 0.2.1-rc.1
- npm rc: 0.2.1-rc.1, a release candidate rather than a stable release
- Install: `npm install --global @licklider/nomue-verifier@0.2.1-rc.1`
- Verify: `nomue verify ./record.json --format json`
- No global install: `npx --yes @licklider/nomue-verifier@0.2.1-rc.1 verify ./record.json --format json`
- Tested package path: Linux, macOS, and Windows with Node.js 20 and 22
- [Run the verifier](https://www.licklider.ai/docs/record-verification.md)
- [Machine-readable examples](https://www.licklider.ai/docs/examples.json)
- Release 1 publishes source code together with public fixtures, a signed source archive, checksums, a snapshot manifest, detached signatures, and the public release key.
- MCP package: [@licklider/nomue-verifier-mcp@0.2.0-rc.1](https://www.npmjs.com/package/@licklider/nomue-verifier-mcp/v/0.2.0-rc.1)
- MCP client configuration: `{"mcpServers":{"nomue-verify":{"command":"npx","args":["--yes","@licklider/nomue-verifier-mcp@0.2.0-rc.1"]}}}`
- MCP start command: `npx --yes @licklider/nomue-verifier-mcp@0.2.0-rc.1`
- MCP tool: `verify_nomue_record`. Use when a Record declares urn:nomue:bundle:itgc-guarantee:0.2.1-draft.1, represents independent two-group continuous outcomes using the two-sided Welch two-sample t procedure, and needs scoped structural, digest, admissibility, computability, or recomputation checks.
- Do not use to calculate a Welch test from raw samples, select a method, judge scientific truth or causality, verify paired-t, Wilcoxon, Mann–Whitney, or interpret an unsupported bundle.
- [MCP installation and exact result contract](https://www.licklider.ai/docs/mcp-verification.md)
- [Official MCP Registry entry](https://registry.modelcontextprotocol.io/v0.1/servers?search=io.github.licklider-ai%2Fnomue-verifier-mcp): `io.github.licklider-ai/nomue-verifier-mcp`

## Research behind expansion

- [Keeping independent checks visible](https://www.licklider.ai/engineering/keeping-independent-checks-visible/): The unissued Holm candidate.5 preserves eligible Record-local checks when independent expected context differs and records the reasons that block dependent checks. Its context and helper-repair checkpoint is merged, but implementation, Research Gate review and public adoption remain open. This development path is not shipped in the public verifier.
- [Separating format checks from verification results](https://www.licklider.ai/engineering/separating-record-conformance-from-verification/): historical candidate.4 output separation; the successor link above explains changed dependencies.
- [When a verification call must discard its result](https://www.licklider.ai/engineering/when-a-verification-call-must-discard-its-result/): shared budgets, operating-system limits and cleanup evidence; draft candidate.4 retains these controls while separating returned checks.
- [Binding Holm corrections](https://www.licklider.ai/engineering/binding-holm-corrections-to-comparisons/): original declaration and supplied-p arithmetic experiment, updated with scoped source/numerical review and a deterministic sort bound; no added public support.
- [Checking factorial probability evidence](https://www.licklider.ai/engineering/checking-factorial-probability-evidence/): The unissued two-by-two candidate now connects Record checks, exact F ratios, bounded probability evidence, a completed report and controlled execution. Its frozen candidate and adoption-readiness packet have independent GO dispositions. Formal adoption, authoritative registration, public CLI treatment and support activation remain open.
- [Exact factorial arithmetic and tail bounds](https://www.licklider.ai/engineering/checking-factorial-statistics-and-tail-bounds/): updated September 11, 2026 to connect the original numerical findings and overlap-checker limitation to the successor experiments.
- [Power scaling and factorial F](https://www.licklider.ai/engineering/power-scaling-and-factorial-f-statistics/): accepted bounded SS/F and six-fixture numerical exploration; no numerical support established.
- [Unequal-variance comparisons](https://www.licklider.ai/engineering/games-howell-approximation-and-guarantees/): source-reviewed GH, T2/T2-prime, T3/C distinctions; simulations are not universal error guarantees.
- [Control or best](https://www.licklider.ai/engineering/comparing-with-control-or-best/): source-reviewed targets, ordered testing and interval boundaries.
- [Testing graphs](https://www.licklider.ai/engineering/implementing-multiple-testing-graphs/): source-reviewed closure, ordering, weights and endpoint conventions. Release 3 method adoption and public support remain separate decisions from the experiments.

## Start here

- [Documentation index](https://www.licklider.ai/docs/index.md): Run the public verifier directly or through local MCP, decide when a verification call applies, and interpret the returned evidence from one versioned documentation set.

## Verification calls and current public artifacts

- [What a verification call is](https://www.licklider.ai/docs/verification-call.md): A shared model for asking a separate capability to check one bounded part of AI-assisted research. Status: Conceptual guide for selecting a verification capability.
- [Verify a Release 1 nomue Record](https://www.licklider.ai/docs/record-verification.md): When and how to use the public local verifier for the exact Release 1 Public Draft support target. Status: Public npm release candidate — @licklider/nomue-verifier 0.2.1-rc.1.
- [Use nomue Record verification over MCP](https://www.licklider.ai/docs/mcp-verification.md): Install the public local stdio server, decide when its method-neutral Record tool applies, and replay the current Release 1 Welch result with the independent verifier. Status: Public local MCP release candidate — @licklider/nomue-verifier-mcp 0.2.0-rc.1.
- [nomue CLI reference](https://www.licklider.ai/docs/cli-reference.md): The exact public command surface shipped by @licklider/nomue-verifier 0.2.1-rc.1, including current help and version boundaries. Status: Public CLI reference — release candidate 0.2.1-rc.1.
- [Decision vocabulary](https://www.licklider.ai/docs/decision-vocabulary.md): Keep execution, clarification, unsupported scope, refusal, failed checks, and unasserted scientific validity separate. Status: Public explanatory vocabulary — upstream semantics remain authoritative.
- [Examples for agents and implementers](https://www.licklider.ai/docs/examples.md): Runnable verifier examples and selection examples showing execute, clarify, unsupported, and bounded interpretation behavior. Status: Public examples — executable examples use the Release 1 verifier fixtures.
- [Current capability and boundaries](https://www.licklider.ai/docs/limits.md): What can be used now, what comes next, how the platform expands, and how to interpret a successful result. Status: Current public capability map — September 17, 2026.

## Machine-readable examples

- [Examples JSON](https://www.licklider.ai/docs/examples.json): normalized executable verifier examples and call-selection boundaries

## Product access

- Approved recipients can submit data and required scientific declarations for a supported Welch calculation, or submit a claimed result with structured evidence for checking, through authenticated MCP and HTTP. The service returns scoped outcomes, reasons, evidence, and next actions.
- Use the npm-published Release 1 verifier, the local stdio MCP server, the Protocol, and their machine-readable documentation today. The agent-facing Welch capability is now available in limited Release 1 to approved recipients through authenticated MCP and HTTP interfaces; public self-registration is not available. The hosted capability does not yet emit public Records for replay through the local verifier.
- [Making verification results more useful to research agents](https://www.licklider.ai/engineering/making-verification-results-useful-to-agents/): Since limited Release 1, nomue development has expanded candidate calculation range, improved completion of difficult calculations, clarified what was checked, and added historical-result handling. Development update: integrated candidates and completed internal milestones are not a new hosted release or an expansion of public verifier support.
- Record assembly and emission has entered development. The adopted initial invite-free release plan targets Welch, independent multi-group and paired two-condition capabilities; delivery and scientific activation remain future gates, with no promised date.
- [Hosted limited Release 1](https://www.licklider.ai/news/nomue-welch-limited-release-1/)
- The exact @licklider/nomue-verifier-mcp@0.2.0-rc.1 release candidate is public on npm and in the official MCP Registry as nomue Record Verifier. It exposes the method-neutral verify_nomue_record tool over local stdio; the current supported scientific scope remains Release 1 Welch Record verification. It delegates to @licklider/nomue-verifier@0.2.1-rc.1 and has passing package-path CI across Linux, macOS, and Windows. It requires no account, API key, environment variable, or Licklider-hosted service. The first npx launch may download npm dependencies; after installation, verification runs locally. This release candidate supports stdio only: it is not a hosted HTTP endpoint and does not add paired-t, Wilcoxon, Mann–Whitney, method selection, raw-sample calculation, or an overall scientific verdict.
- [Public MCP source](https://github.com/licklider-ai/nomue-verifier-mcp), [npm package](https://www.npmjs.com/package/@licklider/nomue-verifier-mcp/v/0.2.0-rc.1), [official registry metadata](https://registry.modelcontextprotocol.io/v0.1/servers?search=io.github.licklider-ai%2Fnomue-verifier-mcp), and [passing CI](https://github.com/licklider-ai/nomue-verifier-mcp/actions)
- The Release 2 paired-t candidate now has an independently reviewed formal decision-readiness packet. It assembles the D1–D6 decision ledger, numerical and execution evidence, structural candidates, review dispositions, Release 1 safeguards, and the required coupled landing order. The Steward decisions, authoritative issuance, support activation, and release remain open.
- Release 4 public discussion is open for a balanced two-by-two fixed-factor proposal. Its unissued numerical, report and controlled-execution candidate has reached independently reviewed final readiness, without establishing Protocol support. A separate amendment discussion covers strict binary64 comparison and completed indeterminate results; it changes neither the current verifier nor the original RFC clock.
- Release 3 public discussion is open on independent groups and multiple comparisons. The proposal makes design, comparison families, result meaning, and error-control questions explicit across 49 catalogued procedures. Its evidence scope is limited to supplied originals; method adoption and numerical support remain separate decisions.
- [Release 3 public discussion](https://github.com/licklider-ai/nomue-protocol/issues/274); [scope and evidence](https://www.licklider.ai/news/nomue-protocol-release-3-public-discussion/)
- [Release 4 public discussion](https://github.com/licklider-ai/nomue-protocol/issues/261); [scope and evidence](https://www.licklider.ai/news/nomue-protocol-release-4-public-discussion/)
- Release 5 public discussion is open on a common evidence view for declared study design and selection timing across analysis families. The proposal covers versioned mappings, timing declarations, explicit limits on what a passing check means, and a shared report view. All three candidate families require separately accepted successors; no new verification capability is available.
- [Release 5 public discussion](https://github.com/licklider-ai/nomue-protocol/issues/346); [scope and evidence](https://www.licklider.ai/news/nomue-protocol-release-5-public-discussion/)
- Welch is the first working, publicly checkable vertical slice, not the product boundary. The adopted product sequence expands both the platform beneath each call and the scientific methods available through it.
- Planned scientific capability families: Independent multi-group; Paired two-group; Repeated measures; Factorial and interaction; Nonlinear and dose response; Nonparametric rank-based; Categorical outcomes; Correlation and linear models; Survival time-to-event; Count outcomes.
- [Full roadmap](https://www.licklider.ai/roadmap/)

## Research finding that informs call selection

- A statistical method name is not a verification contract. A useful guarantee also depends on the comparison family, error criterion, assumptions, sidedness, balance conditions, and exact procedure variant.
- This is a source-bounded Research finding. It does not add or change Protocol support.