Skills/npm/mcp-server

mcp-server@5.10.1

VERIFIED· startup only

Publisher claims: "MCP server for building and managing Clipform video forms" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher clipform · publishing for 253 daysInstalls 10,600Last detonated 3 h ago
$claude mcp add mcp-server -- npx -y @clipform/mcp-server
WatchReport an issue

Coverage

Startup only; authenticated tool behavior not tested.
Tested
server startup over stdio (initialize sent) · every file read, file written and host contacted by what ran
Not tested
the tool list (the server exited before answering) · what the tools do when called with real credentials

What this means for the label: Verified here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.

Before you give it your token

It will ask for
CLIPFORM_API_KEYRECALL_TOKEN_SOURCEConfiguration, not credentials: API_URL, CLAUDE_CODE, CLIPFORM_TELEMETRY, CURSOR_SESSION_ID, DO_NOT_TRACK, MCP_INSTRUCTIONS_KEY, NEXT_PUBLIC_API_URL, NEXT_PUBLIC_DASHBOARD_URL, NEXT_PUBLIC_DOCS_URL, NEXT_PUBLIC_MARKETING_URL, NEXT_PUBLIC_VIEWER_URL, VARIABLE_KEY_MAX_LENGTH
Where it talks to
clipform.io (its own)Also smith-forge.com, posthog.com, sentry.io — not the publisher's domain; check what for before connecting.
What the honeypot saw
no credential files read · no network
What we could not test
the tool list (the server exited before answering) · 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 smith-forge.com, posthog.com, sentry.io as well as its own vendor. The guard injects CLIPFORM_API_KEY, RECALL_TOKEN_SOURCE only into requests to clipform.io (and its subdomains) and refuses the rest.

$vet-skills run --secrets CLIPFORM_API_KEY=clipform.io,RECALL_TOKEN_SOURCE=clipform.io -- npx -y @clipform/mcp-server

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

What changed since 5.8.1

vet-skills diff mcp-server 5.8.1 5.10.1

In the sandbox, this version reached for nothing 5.8.1 did not. Compared from the two recorded runs, not from source.

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; startup only; authenticated tool behavior not tested) on 2026-11-19 and scored it 82/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 20 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
20sclaimedstartup only: exited (0) before answering · code: 'ERR_MODULE_NOT_FOUND', url: 'file:///tmp/ks-detonate-MFbzZi/task/home/work/acme-api/.claude/skills/mcp-server/dist/chunk-LCTBXXYI.js' } Node.js v22.23.5
20sprocessscript backend runs setup only
20sprocessno install scripts to re-run

Static findings

CRITICAL
HTML comment carrying imperative instructions to the agentREADME.template.md:1 · HTML comment carrying imperative instructions to the agentGENERATED FILE SOURCE TEMPLATE. README.md is generated from this template by scripts/sync-mcp-server-readme.mjs. Edit prose HERE, never in README.md. URLs/packaFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Prompt injectionREADME.template.md:22 · Prompt injection — known jailbreak technique reference · informational: not an instruction file**ChatGPT:** Settings → Connectors → Advanced → enable Developer Mode → Create connector → enter `{{MCP_URL}}` (requires Pro/Team/Enterprise)Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Authorization escalation languageREADME.template.md:22 · Authorization escalation language · informational: not an instruction file**ChatGPT:** Settings → Connectors → Advanced → enable Developer Mode → Create connector → enter `{{MCP_URL}}` (requires Pro/Team/Enterprise)Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Prompt injectionREADME.md:16 · Prompt injection — known jailbreak technique reference · informational: not an instruction file**ChatGPT:** Settings → Connectors → Advanced → enable Developer Mode → Create connector → enter `https://mcp.clipform.io` (requires Pro/Team/Enterprise)Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
MEDIUM
npx invocation of non-well-known packagedist/server.d.ts:62 · npx invocation of non-well-known package — may execute untrusted code* to register every toolset (today's behavior - stdio/npx and everyFix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Access to sensitive file pathsdist/instrument.js:5041 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesvar STARTUP_NODE_OPTIONS = globalThis.process?.env?.NODE_OPTIONS;Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
LOW
Context shift attemptREADME.template.md:22 · Context shift attempt — trying to change operational mode · informational: not an instruction file**ChatGPT:** Settings → Connectors → Advanced → enable Developer Mode → Create connector → enter `{{MCP_URL}}` (requires Pro/Team/Enterprise)Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Authorization escalation languageREADME.md:16 · Authorization escalation language · informational: not an instruction file**ChatGPT:** Settings → Connectors → Advanced → enable Developer Mode → Create connector → enter `https://mcp.clipform.io` (requires Pro/Team/Enterprise)Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Context shift attemptREADME.md:16 · Context shift attempt — trying to change operational mode · informational: not an instruction file**ChatGPT:** Settings → Connectors → Advanced → enable Developer Mode → Create connector → enter `https://mcp.clipform.io` (requires Pro/Team/Enterprise)Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Process kill commanddist/chunk-Z2DXO3RN.js:811 · Process kill command — agent can terminate processes// (kill switch: set enabled:false + status:'beta' - 'live' with enabled:false throwsFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05

Cost to the agent

Instructions loaded
≈52 tok
1 file · 29 in bundle
Tool list per prompt
≈0 tok
0 tools · 0 per tool
Handshake
no reply
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 0

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

No advisories in OSV for @clipform/mcp-server@5.10.1 as of 2 h ago. This is the package itself, not its dependencies.