mcp-server@5.12.0
VERIFIED· startup onlyPublisher claims: "MCP server for building and managing Clipform video forms" Observed in sandbox: no network, touches nothing outside the project, writes no memory.
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 we saw when it ran
- 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.
Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.
What changed since 5.10.1
vet-skills diff mcp-server 5.10.1 5.12.0In the sandbox, this version reached for nothing 5.10.1 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 2026-11-21 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 deviationsStatic findings
**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.**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.**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.// (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.**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.var 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.**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.**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.GENERATED 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.* to register every toolset (today's behavior - stdio/npx and everyFix: Pin versions and sources; vendor anything fetched at install time.Cost to the agent
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.