HALLUX
Server Details
Verify that packages, images, repos and DOIs an AI recalled exist before an agent uses them.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 6 tools
The three check variants (hallux_check for a single identifier, hallux_check_command for a raw install command, hallux_check_manifest for a dependency file) could initially look interchangeable, but each description clearly scopes its input type. hallux_account, hallux_report, and hallux_watch are unmistakably distinct. Minor residual risk that an agent picks check vs check_command for the same intent.
Consistent hallux_ prefix and snake_case throughout, with predictable verb-based suffixes (check, check_command, check_manifest, report, watch). The only deviation is hallux_account, which is a noun rather than an action verb, slightly breaking the pattern.
Six tools is well-scoped for a dependency-verification service: account info, three graded check entry points matching the three ways dependencies appear, plus report and watch for the ledger lifecycle. Nothing feels padded or missing.
Covers the core lifecycle: check a name, a command, or a whole manifest, then report hallucinations and watch for verdict changes. Gaps are minor — no way to list or remove existing watches, no way to query the public ledger, and no batch check of loose identifiers outside a manifest file.
Available Tools
6 toolshallux_accountARead-onlyIdempotentInspect
Show remaining credits for the API key in use (or free-tier status), pricing, and where to buy credits with PayPal.
Inputs: no named parameters. Returns: buy, note, tier, status, +2 more
hallux_checkARead-onlyIdempotentInspect
Does this identifier actually exist, and is it safe? Call before acting on any name you recalled rather than read: a package to install, a module to import, a Docker image, a GitHub Action or repo, a DOI to cite.
Verdicts: exists (proceed, but read risk), deprecated (use successor), absent (not in the registry; do not proceed), phantom (absent AND models repeatedly invent it), squat (a name models invent that someone has since registered; treat as hostile), unknown (could not verify; never treat as permission).
For names that exist, risk flags typosquats, LLM-style name conflations, brand-new packages and names registered after agents looked them up.
Inputs: identifiers (required), model. Returns: buy, error, billing, message, +8 more
hallux_check_commandARead-onlyIdempotentInspect
Call this BEFORE running any command that installs or runs a dependency: npm/yarn/pnpm/bun install, npx, pip/uv/poetry/pipx, cargo add, go get, dotnet add package, gem install, composer require, dart pub add, docker pull/run, git clone.
Language models invent plausible package names that have never existed, and attackers register those names because they can predict them (slopsquatting). Installing one runs attacker code. You cannot tell by looking at the name.
Pass the command exactly as you intend to run it. Decision: ALLOW (run it), REVIEW (tell the user about the risk signals first), BLOCK (do not run; use successor if given, otherwise tell the user), UNVERIFIED (registry unreachable; do not treat as safe).
Inputs: command (required), model. Returns: buy, error, billing, message, +8 more
hallux_check_manifestARead-onlyIdempotentInspect
Call after writing or editing a dependency file and before committing or installing. Checks every dependency in one pass, including dev and optional groups, where an invented name usually arrives. Exact pinned versions are verified too. Supported: package.json, requirements.txt, pyproject.toml, Pipfile, Cargo.toml, go.mod, Gemfile, composer.json, .csproj / packages.config, pubspec.yaml, mix.exs, Dockerfile, .github/workflows/.yml.
Inputs: content (required), filename (required), model. Returns: buy, error, billing, message, +8 more
hallux_reportBIdempotentInspect
Report identifiers a model produced that turned out not to exist. HALLUX verifies each against its registry and records only absent ones as attestations in the public hallucination ledger, which is how names graduate to phantom and get watched for squatting. Requires an API key.
Inputs: model (required), identifiers (required), promptClass. Returns: buy, note, error, billing, +4 more
hallux_watchAInspect
Register identifiers for a signed webhook when their verdict changes: phantom -> squat (someone registered a name models invent) or absent -> exists. Use for a name that came back absent/phantom which the user still intends to use, or a dependency set worth monitoring. Requires an API key; costs 25 credits ($0.02) per identifier per 30 days.
Inputs: callbackUrl (required), identifiers (required). Returns: buy, error, renews, secret, +7 more
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Verify before you act: deps-check, x402-preflight, json-repair & url-read for agents.
Verifies AI agent work end to end: real artifacts and outcomes checked, not self-reported success.
Real-time fact-check, citation verification, and source-freshness for AI agents.
Verify npm packages before your AI agent installs them: hallucinations, advisories, API drift.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceEnables AI coding agents to scan projects or changed files for risky leftovers like hallucinated packages, exposed secrets, truncated code, and unfinished stubs, and to verify that packages exist before installing them.17 npmMIT
- AlicenseNot gradedqualityDmaintenanceValidates and checks packages across 19 ecosystems to prevent AI agents from installing hallucinated, deprecated, or malicious packages.60 npmAGPL 3.0
- AlicenseAqualityBmaintenanceEnables agents to verify checkable claims in markdown context files—such as paths, ports, systemd units, and Forgejo repositories—against the live system through a single read-only tool before acting.1MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to fact-check claims, verify citations, and check source freshness using Wikipedia, Wikidata, Crossref, and Wayback Machine.1MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.