jotform-sign

jotform-sign is a skill for Claude Code from jotform/mcp-server. It costs 58 tokens per session (729 once invoked), scanned A, original, MIT.

A document-signing tool for preparing contracts, agreements, non-disclosure agreements, and consent documents, then sending them for signatures and checking their status.

In plain words
What is it for?
Use it to create or edit a signing document, set its signers, send an invitation, or see who has signed.
Why use it?
It removes the need to prepare and track signing documents manually across separate tools.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the jotform-sign plugin — 1 skill shipped together

Good fit Use it to create or edit a signing document, set its signers, send an invitation, or see who has signed.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jotform/mcp-server/jotform-sign
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add jotform/mcp-server --skill jotform-sign
Clone the repo
git clone --depth 1 https://github.com/jotform/mcp-server

Made for: Claude Code.

Or install jotform-sign, the plugin that ships this one along with the rest of its 1 skill.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for jotform-sign

README.md
[![agentmods](https://agentmods.dev/badge/skills/jotform/mcp-server/jotform-sign/github.svg)](https://agentmods.dev/skills/jotform/mcp-server/jotform-sign)
Your own site
<a href="https://agentmods.dev/skills/jotform/mcp-server/jotform-sign"><img src="https://agentmods.dev/badge/skills/jotform/mcp-server/jotform-sign/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for jotform-sign

Your own site · 80×15
<a href="https://agentmods.dev/skills/jotform/mcp-server/jotform-sign"><img src="https://agentmods.dev/badge/skills/jotform/mcp-server/jotform-sign.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 729 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00058 $0.00729
Opus 5.5 $0.00023 $0.00292
Sonnet 5.5 $0.00012 $0.00146
Haiku 4.5 $0.00006 $0.00073

Measured 2d ago against content hash ad3c6083ba75, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

jotform-sign scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

integrations/claude/jotform-sign/skills/jotform-sign/SKILL.md · 31 lines

How it starts

The opening of the file, as written. The whole thing — 31 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Jotform Sign

Use tools from the jotform-sign connector. When another connector exposes the same short tool name, choose the tool that belongs to jotform-sign. A Jotform form ID is not a Sign document ID.

Prepare and edit

  1. Treat the connected server's current tool definitions as the contract. If the connector is unavailable, name the connection the user needs. Never ask for a password or token in chat.
  2. Find an existing signing asset with this connector's search, or use a Sign identifier the user supplied. Resolve an ambiguous match before editing or sending.
  3. Use create_sign_document with the user's prompt for a new document. Include document_title or a file only where the live schema accepts them. An uploaded reference is not a promise to keep the original file as the final document. Do not invent legal terms, personal data, download URLs, or signer addresses.
  4. Use display_sign_document, edit_sign_document, or update_sign_document_content for the change the user asked for. Leave unrelated content in place. For a team workspace, resolve the team with this connector's get_teams. For create_sign_document, personal workspace uses workspace_type: "personal" and team_id: "".
  5. A processing result is not a finished document. Check readiness only through the retrieval path this server documents. Do not call creation or editing again as a status check, and do not use the Forms or Apps fetch. If no status path is available, report the document as pending and keep its returned identifier.

Configure and send

  • Use get_signers and update_signer for the document's actual roles. Do not assume a new draft already has the intended recipients.
  • Creating a draft does not authorize email. Call send_for_signature only when the user asked to send and the recipients and document are known. Ask only when something required is missing or ambiguous.
  • Honor a requested signing order or reminder when the schema supports it. Do not add sends or reminders the user did not ask for.
  • A send creates a separate sent copy. Keep a returned sent-copy ID apart from the draft ID, and report a send only when the tool result confirms it. On an ambiguous response, check status instead of sending again.
  • get_signing_status reads current status. It does not subscribe to updates. A sent-copy ID checks that copy. A draft ID may aggregate copies, so do not claim one copy is complete from an aggregate result.

Read the full file on GitHub · 31 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 31 lines · 58 tokens per session scan A ad3c6083ba75

Subscribe to this mod's changes

jotform-sign is a skill published in the GitHub repository jotform/mcp-server (29 stars, last pushed 3d ago), licensed MIT. It adds 58 tokens to every session and 729 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-23.

Related

Other skills, from other repositories

shopify-app-store-review

Run a pre-submission compliance check against your Shopify app's codebase. Reviews App Store requirements and surfaces likely issues before you submit for official review.

Shopify/Shopify-AI-Toolkit · 36 tokens

pandadoc-approval-send

Create a document from a template and route it through its internal approval chain — read the approval steps, send through the chain where the API allows it, and hand off to PandaDoc where it does not. Use when a document needs internal sign-off before it reaches the counterparty.

PandaDoc/mcp-server-guide · 63 tokens

pandadoc-onboarding-agreement

Generate an onboarding or employment document from a template with the new joiner's details prefilled, make sure every field is assigned to them, then send for signature. Use when someone is onboarding a hire and needs paperwork issued.

PandaDoc/mcp-server-guide · 52 tokens

pandadoc-nda-fast-send

Send a standard NDA to a counterparty in one motion — find the right NDA template, prefill the counterparty, make sure every signature is assigned, confirm, then send. Use when someone wants an NDA, mutual NDA or confidentiality agreement issued.

PandaDoc/mcp-server-guide · 58 tokens

pandadoc-renewal-radar

Digest of signed contracts approaching renewal or expiry, with counterparty, value and days remaining. Reads the extracted renewal fields (renewal action deadline, term lengths, renewal type, opt-out period) rather than guessing a term from the document body, and distinguishes a contract's own end date from the…

PandaDoc/mcp-server-guide · 90 tokens

pandadoc-contract-register

Build a register of signed contracts with their key terms — counterparty, dates, value and negotiated provisions — from PandaDoc's extracted metadata, labelled with how confident each value is. Use when someone wants a contract register, key terms pulled out, or all agreements for a customer.

PandaDoc/mcp-server-guide · 62 tokens