Ext Ops Panel
Open dashboard
Comparison

prompt-fidelity vs HallucC — Hallucination & Safety Guardian

prompt-fidelity is no longer listed on any marketplace we read: these are its last known data, as of 2026‑10‑15.

prompt-fidelity is a plugin bundle for AI coding tools published by James Barney. No marketplace we read lists it any more. HallucC — Hallucination & Safety Guardian is an MCP server published by fredyee. Marketplaces we read that list it: 1 (Official MCP Registry). As of our marketplace pass on 2026-10-28. A plugin in this pair is no longer listed on any marketplace we read, so search engines are asked not to index the page.

Where each is published

Where each is published
Marketplaceprompt-fidelityHallucC — Hallucination & Safety Guardian
Community marketplace barneyjm/prompt-fidelity Removed on 2026-10-15
Version: 0.1.0
Forks (GitHub): 0
Stars (GitHub): 1
Not marked · First seen
Not listed
Official MCP Registry Not listed Listed
Version: 0.1.10
Forks (GitHub): 0
Stars (GitHub): 0
Not marked · First seen

Each figure is the marketplace's own and is never added up across marketplaces. A marketplace that publishes no figure shows none: no number is not zero.

The facts side by side

prompt-fidelity vs HallucC — Hallucination & Safety Guardian
Factprompt-fidelityno longer listed · HallucC — Hallucination & Safety Guardian
Marketplaces that list it (differs)01
Stars (GitHub) (differs)10
Forks (GitHub)00
Last release (differs)Not published2026-10-15
Where it runs (differs)Installs as a plugin bundleRemote server (aihcc.cloud/mcp)
Transport (differs)Not statedStreamable HTTP
Tools it declaresNot publishedNot published
Environment variables it asks forNot publishedNot published
Parts of the bundle (differs)1Not a bundle
Licence (differs)MITNot stated
Repository (differs)github.com/barneyjm/prompt-fidelitygithub.com/fredyee/hallucc-mcp
Changes in the last 7 days00
First seen (differs)2026-10-142026-10-11
Endpoint at the last check (differs)no remote endpoint we checkResponded 6 days ago

Lines where the two differ have a tinted background and bold values. No value is marked better or worse: a plugin no marketplace lists any more is shown with its last known data, which we do not rank against current figures.

What to use instead of prompt-fidelity

Plugins still listed whose own names, descriptions, tools and skills are closest in meaning to it. Comparable, not endorsed.

  • doublecheck

    Three-layer verification pipeline for AI output. Extracts claims, finds sources, and flags hallucination risks so humans can verify before acting.

    by Awesome Copilot Community · Plugin bundle

    Listed on: Copilot CLI: github/awesome-copilot · Describes nearly the same job

  • doublecheck

    Three-layer verification pipeline for AI output. Extracts claims, finds sources, and flags hallucination risks so humans can verify before acting.

    by Awesome Copilot Community · Plugin bundle

    Listed on: Community GitHub marketplaces · Describes nearly the same job

  • VeriGhost-Clarity

    Hallucination validator and factual grounding checker for LLM outputs.

    by Evozim · MCP server

    Listed on: Official MCP Registry · Describes nearly the same job

  • Spectral — verified-knowledge oracle

    Cross-check a factual claim against a verified knowledge graph before you assert it. Never guesses.

    by seespectral.com · MCP server

    Listed on: Official MCP Registry · Describes nearly the same job

  • Fidenta Verify

    Independent fact-checking for AI answers: a verdict and sources for every claim.

    by noevant.ai · MCP server

    Listed on: Official MCP Registry · Describes nearly the same job

  • Eval Engine API

    Pay-per-call AI evaluation MCP server. Score LLM outputs against benchmark rubrics via Workers AI.

    by invertedhoologan · MCP server

    Listed on: Official MCP Registry · Describes nearly the same job

Its card, with similar plugins by marketplace

What each says it does

prompt-fidelity

In its own words, on Community GitHub marketplaces:

Self-check skill: decompose a request into verified vs inferred constraints, compute a fidelity score, and report which parts of an answer are auditable vs judgment calls.

HallucC — Hallucination & Safety Guardian

In its own words, on Official MCP Registry:

Fact-check LLM outputs with cited sources. API key: aihcc.cloud/keys.

How to run each

prompt-fidelity

No data for an automatic command: what its marketplaces declare does not say unambiguously how to connect it.

HallucC — Hallucination & Safety Guardian As a remote MCP server

Claude Code
claude mcp add --transport http hallucc https://aihcc.cloud/mcp --header "Authorization: Bearer <YOUR_TOKEN>"

Requires: Authorization header

Commands built only from what the marketplaces declare; the full set for every client is on each card.

Only HallucC — Hallucination & Safety Guardian has a remote endpoint we check. How we check endpoints

Tools each declares

Neither one's marketplaces publish a list of tools, so there is nothing to compare.

Settings each asks for

Neither one's marketplaces publish the settings it asks for.

What it can do: prompt-fidelity · What it can do: HallucC — Hallucination & Safety Guardian · Compare two other plugins

Data comes from public marketplace files in GitHub repositories of their authors. Data comes from the Official MCP Registry (registry.modelcontextprotocol.io), CC0 1.0. Figures come from our own regular passes over the marketplaces, last read on . We publish no contact details for plugin publishers.

Where the data comes from: how the catalog is built