Skills/npm/plexo-mcp

plexo-mcp@1.1.5

VERIFIED

Publisher claims: "Model Context Protocol (MCP) Server for Plexo - Landing page generation, email templates, publishing, and analytics." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher charisol · publishing for 122 daysInstalls 557Last detonated 14 min ago
$claude mcp add plexo-mcp -- npx -y @charisol/plexo-mcp
WatchReport an issue

Coverage

Server started and answered tools/list.
Tested
MCP initialize and tools/list · every tool description, for hidden instructions · every file read, file written and host contacted by what ran
Not tested
what the tools do when called with real credentials

Before you give it your token

It will ask for
PLEXO_API_KEYConfiguration, not credentials: PLEXO_BASE_URL
Where it talks to
charisol.io (its own)Also example.org — not the publisher's domain; check what for before connecting.
What we saw when it ran
no credential files read · no network
What we could not test
what the tools do when called with real credentials

Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names example.org as well as its own vendor. The guard injects PLEXO_API_KEY only into requests to charisol.io (and its subdomains) and refuses the rest.

$vet-skills run --secrets PLEXO_API_KEY=charisol.io -- npx -y @charisol/plexo-mcp

Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.

What changed since 1.1.2

vet-skills diff plexo-mcp 1.1.2 1.1.5

This version reaches for something 1.1.2 did not: 27 new tools (add_custom_section, adopt_monthly_donors, apply_site_health_fix, approve_funnel_enrollment_page, …). Compared from the two recorded runs, not from source.

New tools
add_custom_section, adopt_monthly_donors, apply_site_health_fix, approve_funnel_enrollment_page, cancel_monthly_donation, check_site_health, connect_wordpress_migrator_plugin, create_donation_campaign, create_section_type, get_domain_switch_plan, get_funnel_addon_slots, get_section_entry +15
Tools removed
create_commerce_product, create_email_template, create_funnel_page, create_landing_page, create_landing_page_subpage, create_raw_landing_page, delete_commerce_product, delete_published_domain, delete_template, design_blog_layout, duplicate_landing_page_page, get_analytics +15

The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios) on 2026-11-22 and scored it 89/100 (Verified). It did what it claims and nothing else we could detect: no undeclared network egress, no credential reads, no persistent instruction writes. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 26 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
6.1sprocessdependency install exit 0
26sclaimed172 tools: publish_existing_landing_page, get_landing_page_pages, delete_landing_page_page, list_landing_pages, list_email_templates, get_blog_layout, reset_blog_layout, get_blog_settings, update_blog_settings, list_blog_posts, get_blog_post, create_blog_post, update_blog_post, delete_blog_post, list_blog_categories, create_blog_category, delete_blog_category, list_blog_tags, create_blog_tag, delete_blog_tag, list_blog_authors, create_blog_author, delete_blog_author, list_blog_comments, moderate_blog_comment
26stoolsa9e10a297d7e7e3c
26stools5763bd96398fb734
26stools284c41649eb79c5e
26stools0c4e936fd17930d0
26stoolsd60df683ab9a1bd1
26stools0bd2d69087410741
26stoolsf4cf4dbba0b4829f
26stools12b5e646d2a04363
26stools805421522d8d30a1
26stools35c559eef82fa87a
26stoolsf10fc1be996e42c3
26stools9ad3c2f4aa8cc227
26stools4b3fd04e3abc3ce7
26stools787fe7802e64de2a
26stoolsbdd2cff8e09ed642
26stoolsd38a8d80d78671b0
26stools712eb6f1b8457903
26stools4d69ab889b800c51
26stools23a2c0ac245bbcc8
26stoolsba03e53386f4008a
26stools77d1579c1d1b45da
26stoolsb44e0f39d50d0afa
26stools0e23488be74300d0
26stools7237b5eae5051292
26stoolsd1c4e48ff4ee41bf
26stools2392e1fe2e845c6e
26stools8efd34c1a3fdbed9
26stools0ace8102c983515e
26stools6ab07ccc46baf712
26stools2eb260d48ef29690
26stoolsbd2429adc44ec734
26stools4406292373e0efa0
26stoolsf64a65c2a0404b4a
26stools4ec59c5aea54739a
26stoolscf751c339ed27e7b
26stools3b4934a5b0a2956c
26stools9cd9315a2efab15b
26stools7a9d621c98abbde3
26stools9f6c2d920a5fa625
26stoolscc98514ccb7ac742
26stools81977afc8af03306
26stools82d32b3437d42795
26stools913b6f255a403f1e
26stools72c73f59870f9c82
26stools9315cc53672348d0
26stools83ebe1e10feede22
26stoolsada44907e4aa6f5f
26stoolsc9533c5cb10143ca
26stools1f09879cf07a75bb
26stools4ba46116beeabdf6
26stools361652978b8839c8
26stoolsdf86864fa040910c
26stoolsd1730648486cded6
26stools0abeb594f312f6d4
26stoolsd5d86da51b1d6230
26stools9be0476f4ca0bb3d
26stools50925ed8b3b844f3
26stools7313d90cc3199f25
26stools5947ead39188561c
26stoolsa7e9b8f6d0dcc028
26stools29e6966137fc6df0
26stools79d6c6a86ba571e7
26stoolsdb8325c4c8ca4aa2
26stoolsc11dca01edab3035
26stools0d34ad5ab908b3d3
26stoolsc17eb1a37888d128
26stools5fd9ce266045a7ca
26stools4e291669f89ed7c9
26stools0e8259f101983b85
26stoolsf06ad610e6f10379
26stoolsd0956315c24dbc9f
26stools68bffc7190792418
26stools9947b326fce54e91
26stoolsc55d961ef18a35a9
26stools7efe412f7a020824
26stools26a8b7d7be53c064
26stools68237a3d609ec1d1
26stools25b18bfcfe1c4812
26stoolsf96d231a9bd0f5b9
26stools038092d77674753e
26sprocessscript backend runs setup only
26sprocessno install scripts to re-run

Static findings

MEDIUM
File type combined with upload actiondist/appToolDefs.js:92 · File type combined with upload action — agent may exfiltrate local data files…re from the project root, e.g. src/pages/Dashboard.tsx, db/migrations/0002_tasks.sql, functions/send-invoice.ts. Changes aren't visible until app_build.", "inputSchema": { …Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actiondist/hostedToolDefs.js:1735 · File type combined with upload action — agent may exfiltrate local data files…re from the project root, e.g. src/pages/Dashboard.tsx, db/migrations/0002_tasks.sql, functions/send-invoice.ts. Changes aren't visible until app_build. BRAND: a site may have a br…Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
LOW
Unpinned dependency.github/workflows/publish-npm.yml:29 · Unpinned dependencyrun: npm install -g npm@latestFix: Pin the exact version (`[email protected]`, `==1.2.3`) so every install gets the bytes that were reviewed.
AST06
MEDIUM
File type combined with upload actionsrc/appToolDefs.ts:89 · File type combined with upload action — agent may exfiltrate local data files…re from the project root, e.g. src/pages/Dashboard.tsx, db/migrations/0002_tasks.sql, functions/send-invoice.ts. Changes aren't visible until app_build.", "inputSchema": { …Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionsrc/webToolManifest.json:4174 · File type combined with upload action — agent may exfiltrate local data files…re from the project root, e.g. src/pages/Dashboard.tsx, db/migrations/0002_tasks.sql, functions/send-invoice.ts. Changes aren't visible until app_build. BRAND: a site may have a br…Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionsrc/hostedToolDefs.ts:1732 · File type combined with upload action — agent may exfiltrate local data files…re from the project root, e.g. src/pages/Dashboard.tsx, db/migrations/0002_tasks.sql, functions/send-invoice.ts. Changes aren't visible until app_build. BRAND: a site may have a br…Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07

Cost to the agent

Instructions loaded
≈66 tok
1 file · 48 in bundle
Tool list per prompt
≈50,073 tok
172 tools · 291 per tool
Handshake
4015 ms
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 588

Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.

Known vulnerabilities

Not checked against OSV yet; the weekly check has not reached this version.