Frank AI Researcher icon

Frank AI Researcher

nar-vardanyan/frank · v1.1.0 · Tools & Integrations

by nar-vardanyanScan grade: Good

MCP server: AI-moderated voice interviews with your own customers, so an assistant can create studies, run them, and read the transcripts

Protect this install with HOL Guard

Guard checks the skills and MCP servers a plugin adds on your machine and asks you before a risky action runs. The scores above are free, and no plan changes them.

Is Frank AI Researcher a fit?

From the plugin's manifest and HOL's scan. Anything the plugin does not declare is shown as not declared.

Works with

  • Cursor
  • MCP
  • 1 skill
  • 1 MCP server

Before you install

Sign-in
Not declared
Declared access
Not declared
License
MIT

Check before relying on it

  • Some security checks did not finish: Cisco skill scan and Cisco MCP scan. See the evidence
  • The publisher has not verified ownership on HOL.

What is Frank AI Researcher?

Frank AI Researcher is a published tools & integrations plugin for AI coding agents that works with Cursor and MCP, developed by nar-vardanyan and distributed through the HOL AI plugin registry. MCP server: AI-moderated voice interviews with your own customers, so an assistant can create studies, run them, and read the transcripts.

Canonical slug
nar-vardanyan/frank
Version
v1.1.0 · updated Nov 20, 2026

Registry snapshot

Owner verification
Not verified
Scanner
HOL plugin scanner
Security result
Needs review
Digest verified
Yes
1 bundled skillRead, copy or download each SKILL.mdOpen skills

Trust and security

Trust & reputation

85

HOL Trust Score

Per-metric points (0–100 each) combined via a weighted average into the overall score.

Installability
100/100
Maintenance
65/100
MCP server setup
100/100
Plugin Security
89/100
Provenance
70/100
Publisher Quality
75/100

Provenance

Plugin root
.
Source repo
https://github.com/nar-vardanyan/frank-mcp
Source commit
448786fd2f20…
Publisher verified
No
Owner verified
Not owner verified
Agent Plugins 1.0
Not detected

Scanner CI check is still running

No action is required. This listing will update after the catalog rechecks scanner CI.

README badge check is still running

No action is required. This listing will update after the catalog rechecks the source README.

Needs review
Security result
89
Security score
0
High findings
Provider
codex-plugin-scanner
Grade
B · Good
Version
3.24.2
cisco-skill-scanner: failedcisco-mcp-scanner: unavailable

Manifest Validation

25/31

9 checks

Security

24/24

9 checks

Operational Security

N/A

5 checks · not applicable

Best Practices

9/12

5 checks

Marketplace

N/A

3 checks · not applicable

Skill Security

5/5

4 checks

Code Quality

10/10

2 checks

Published advisories

None matched in GitHub security advisories, checked . This covers published advisories only, not problems nobody has reported.

GitHub security advisories are those the source repository has published.

Findings

infomanifest-validationPLUGIN_JSON_INTERFACE_SHORTDESCRIPTION

The interface object is missing a valid "shortDescription" value.

Add a valid "shortDescription" field to the interface metadata.

infomanifest-validationPLUGIN_JSON_INTERFACE_LONGDESCRIPTION

The interface object is missing a valid "longDescription" value.

Add a valid "longDescription" field to the interface metadata.

infomanifest-validationPLUGIN_JSON_INTERFACE_CATEGORY

The interface object is missing a valid "category" value.

Add a valid "category" field to the interface metadata.

infomanifest-validationPLUGIN_JSON_INTERFACE_CAPABILITIES

The interface object is missing a valid "capabilities" value.

Add a valid "capabilities" field to the interface metadata.

infomanifest-validationPLUGIN_JSON_INTERFACE_ASSET_WEBSITEURL

The interface field "websiteURL" must use HTTPS or point to a safe in-repo asset.

Update "websiteURL" to use HTTPS or an existing relative asset path.

infomanifest-validationPLUGIN_JSON_INTERFACE_ASSET_PRIVACYPOLICYURL

The interface field "privacyPolicyURL" must use HTTPS or point to a safe in-repo asset.

Update "privacyPolicyURL" to use HTTPS or an existing relative asset path.

infomanifest-validationPLUGIN_JSON_INTERFACE_ASSET_TERMSOFSERVICEURL

The interface field "termsOfServiceURL" must use HTTPS or point to a safe in-repo asset.

Update "termsOfServiceURL" to use HTTPS or an existing relative asset path.

infomanifest-validationPLUGIN_JSON_INTERFACE_ASSET_COMPOSERICON

The interface field "composerIcon" must use HTTPS or point to a safe in-repo asset.

Update "composerIcon" to use HTTPS or an existing relative asset path.

infomanifest-validationPLUGIN_JSON_INTERFACE_ASSET_LOGO

The interface field "logo" must use HTTPS or point to a safe in-repo asset.

Update "logo" to use HTTPS or an existing relative asset path.

infomanifest-validationPLUGIN_JSON_INTERFACE_ASSET_SCREENSHOTS

The interface field "screenshots" must use HTTPS or point to a safe in-repo asset.

Update "screenshots" to use HTTPS or an existing relative asset path.

infobest-practicesCODEXIGNORE_MISSING

A .codexignore file helps prevent accidental inclusion of local artifacts and secrets.

Add a .codexignore file with generated assets, local state, and secret paths.

Install guidance

Install in Cursor

Install the bundled skills into Cursor with the open Skills CLI.

Skills CLI docs

Optional: install HOL Guard for Cursor first, so it can check this plugin's tools on your machine before Cursor uses them.

  1. 1

    Install with the Skills CLI

    The open Skills CLI detects installed agents and installs this plugin's skills for Cursor.

    shell
  2. 2

    Restart and verify

    Start a new Cursor session and confirm the skill is listed before relying on it. The Skills CLI lists what it installed.

    shell

To remove it later, run npx [email protected] remove nar-vardanyan/frank-mcp.

Did setup work in Cursor?

No setup reports for Cursor yet. Self-reported by signed-in visitors. Copying a command is not counted, and most installs are never reported.

Attested installs: Fewer than 10 attested installs of this plugin in week 2026-W46, so no number is shown. Counted from opt-in HOL Guard install reports, once per machine and runtime, and never mixed with the answers above. How install reports work.

Loading reviews

Plugin manifest

{
  "name": "frank",
  "version": "1.1.0",
  "description": "Connect Cursor to Frank AI Researcher’s remote MCP server to run customer research: list and read studies, interviews, and transcripts; create products and draft studies; and, with approval, publish a study or configure the interview widget.",
  "author": {
    "name": "Prelaunch Group, Inc.",
    "email": "[email protected]"
  },
  "homepage": "https://www.hifrank.ai",
  "repository": "https://github.com/nar-vardanyan/frank-mcp",
  "license": "MIT",
  "keywords": [
    "mcp",
    "user-research",
    "interviews",
    "customer-research",
    "product-research",
    "ai-interviews"
  ],
  "logo": "assets/logo.png",
  "interface": {
    "displayName": "frank",
    "developerName": "nar-vardanyan"
  },
  "skills": "./",
  "mcpServers": "./.registry/mcp.json",
  "holManifestOrigin": "repository",
  "registryIndexVersion": 9
}

Marketplace source

Repo URL
https://github.com/nar-vardanyan/frank-mcp
Marketplace path
Unknown
Source path
.
Install policy
Unspecified

Skills

1 SKILL.md file ship with this plugin. Preview, copy, or download each one, then install them with the Skills CLI.

Share
skills-cli

File inventory

.codex-plugin/plugin.json

plugin-manifest

778 bytes

b0cadfa563e00c3c…

.cursor-plugin/plugin.json

file

688 bytes

13d41e5a92c1bac1…

.mcp.json

file

89 bytes

693d2c6c8fe9ebad…

.registry/mcp.json

mcp-config

61 bytes

63a548e094775742…

LICENSE

file

1,440 bytes

ad8a254c53ab39cf…

README.md

file

12,791 bytes

2ab4814b99f2527d…

SECURITY.md

file

1,931 bytes

14167fc29ae8adee…

skills/customer-interviews/prompts/01-churned-users.md

skill

794 bytes

4fd340e78a595a72…

skills/customer-interviews/prompts/02-onboarding-friction.md

skill

771 bytes

cd06988419ddde3d…

skills/customer-interviews/prompts/03-pricing-perception.md

skill

830 bytes

2f9be6f4582a48e0…

skills/customer-interviews/prompts/04-feature-discovery.md

skill

795 bytes

5a8586bad871148f…

skills/customer-interviews/prompts/05-win-loss.md

skill

720 bytes

6d628ed2268cda8e…

skills/customer-interviews/prompts/06-pmf-survey-follow-ups.md

skill

891 bytes

71f756d5503c7183…

skills/customer-interviews/prompts/07-multilingual.md

skill

954 bytes

fd58ed5b3f0049b4…

skills/customer-interviews/prompts/08-trial-non-conversion.md

skill

725 bytes

a848f2cc1aafea8c…

skills/customer-interviews/prompts/09-renewal.md

skill

724 bytes

af3585f7d7accf8a…

skills/customer-interviews/prompts/10-downgrade.md

skill

707 bytes

27590f5f904be651…

skills/customer-interviews/prompts/11-early-usefulness.md

skill

742 bytes

291bd9a3c672ad88…

skills/customer-interviews/prompts/12-feature-dropoff.md

skill

751 bytes

8123f17a59e232ac…

skills/customer-interviews/SKILL.md

skill

13,934 bytes

376fb05a90bda440…

Frank AI Researcher — Frequently asked questions

What is Frank AI Researcher?
Frank AI Researcher is an AI plugin in the HOL registry. MCP server: AI-moderated voice interviews with your own customers, so an assistant can create studies, run them, and read the transcripts.
How do I install Frank AI Researcher?
Install Frank AI Researcher in your harness: Cursor — npx [email protected] add nar-vardanyan/frank-mcp; MCP — git clone https://github.com/nar-vardanyan/frank-mcp; Any agent — npx [email protected] add nar-vardanyan/frank-mcp. Full step-by-step guidance is on the HOL plugin page.
How do I install Frank AI Researcher in Cursor?
To install Frank AI Researcher in Cursor, start with npx [email protected] add nar-vardanyan/frank-mcp. The complete step-by-step install guide for Cursor is on the HOL plugin page.
How do I install Frank AI Researcher in MCP?
To install Frank AI Researcher in MCP, start with git clone https://github.com/nar-vardanyan/frank-mcp. The complete step-by-step install guide for MCP is on the HOL plugin page.
How is the Trust Score for Frank AI Researcher computed?
Frank AI Researcher has a HOL Trust Score of 85 out of 100. The score is a weighted sum of six components from a static scan of the source, capped for high-severity findings and adjusted by two disclosed policies. Memberships and payments are not inputs, and a scan is not a safety guarantee. Full breakdown: https://hol.org/registry/plugins/nar-vardanyan%2Ffrank/trust
Who publishes Frank AI Researcher?
Frank AI Researcher is published by nar-vardanyan and listed on HOL.

Directory acceptance

Listed in 0 of 5 directory lists

Read from the list each directory publishes on GitHub. Being listed means the directory accepted the plugin; it is not a HOL security rating.

Lists last read . HOL re-reads them every day.

Submitting it? Check it against each directory's rules

Install signal

HOL cannot see every install. These are separate signals from different sources, so they are not added together. Counts under each floor show as <N.

Install commands issued here
<5
HOL Guard install commands issued from this listing, last 28 days.
Opt-in install reports
<10
Machines that reported installing it through HOL Guard in week 2026-W46. Reporting is opt-in, so most installs are not counted.
HOL Guard workspaces
<5
Workspaces that approved it or include it in an approved-plugin feed, as of today.

Reviews and similar plugins