← 返回 Skills 市场
maverick

Pandadoc mcp

作者 Maverick · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ⚠ suspicious
26
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install maverick-pandadoc-mcp
功能描述
Use PandaDoc integration context for documents, templates, recipients, proposals, and document status. Use after Maverick connects PandaDoc and provisions ru...
使用说明 (SKILL.md)

PandaDoc

Quick start

This skill has the shared mcporter wrapper scripts, but no skill-local mcporter.json is registered for PandaDoc yet. Do not call bash {baseDir}/scripts/invoke.sh until a provider MCP manifest is added. In current runtime, inspect the available PandaDoc tools first, then use the smallest read path that can identify the document, template, recipient, proposal, or status target.

When a PandaDoc MCP manifest is added, follow the same wrapper rule as Linear: invoke through bash {baseDir}/scripts/invoke.sh, never call mcporter directly, and discover tool schemas before choosing tool names.

Safety

Write operations that create, send, update, complete, delete, or modify documents, templates, recipients, proposals, or document status can affect customer-visible signing workflows. Confirm clear user intent before invoking write tools, and read current document/template state before making changes.

Authentication

Tokens are provisioned and rotated automatically. If available runtime tools return HTTP 401 that doesn't recover within a few seconds, the OAuth grant has been revoked — re-authorize the integration to refresh credentials.

Data flow

No provider-owned PandaDoc MCP endpoint is registered in this repository yet. Runtime tool calls, if present in the active OpenClaw environment, use Maverick-provisioned OAuth credentials and expose PandaDoc document, template, recipient, proposal, and status data to the active tool provider. Use this skill for PandaDoc-related work only; do not pass unrelated sensitive content through these tools.

Dependencies

  • mcporter (github.com/steipete/mcporter) — MCP CLI used by the shared wrapper once a PandaDoc MCP manifest exists. Auto-installed via npm install -g --ignore-scripts mcporter if missing on PATH (see install spec in frontmatter). The install spec uses unpinned mcporter (npm latest); operators with strict supply-chain controls should override the install to pin a specific version (e.g. mcporter@\x3Cversion>).
  • jq (stedolan.github.io/jq) — JSON processor used by the vault initializer. System dependency; install via your OS package manager (apt install jq, brew install jq, etc.).
  • flock (part of util-linux) — file locking used to serialize concurrent vault writes. Available by default on Linux; on macOS install via brew install flock.
  • shasum (Perl, ships with Digest::SHA) — computes the SHA-256 hashes used to derive the mcporter vault key and the provisioned-token marker. Preinstalled on macOS and on Debian/Ubuntu (incl. the deployed cloudflare/sandbox Ubuntu 22.04 image); on minimal Linux images install perl-Digest-SHA. The script invokes shasum -a 256 rather than GNU sha256sum so it runs on stock macOS without coreutils.
安全使用建议
Install only if you trust the Maverick/OpenClaw runtime provider for PandaDoc, can verify the actual MCP tools/endpoints in your environment, and are comfortable granting OAuth access that may read or change PandaDoc documents, templates, proposals, recipients, and status.
功能分析
Type: OpenClaw Skill Name: maverick-pandadoc-mcp Version: 1.0.0 The skill is a standard integration wrapper for PandaDoc using the mcporter tool. It manages OAuth token lifecycle by seeding a local credential vault (~/.mcporter/credentials.json) from environment variables provided by the OpenClaw runtime. The implementation in scripts/init-mcporter.sh and scripts/invoke.sh uses safe shell scripting practices, including atomic file operations, file locking for concurrency, and passing secrets to jq via environment variables to prevent exposure in process listings. No malicious behavior or data exfiltration was identified.
能力标签
requires-oauth-tokenrequires-sensitive-credentials
能力评估
Purpose & Capability
The PandaDoc purpose is coherent, but the artifacts say no provider-owned PandaDoc MCP manifest or endpoint is registered while still relying on active runtime tools, so the exact tool provider and endpoint are not reviewable here.
Instruction Scope
The skill appropriately warns that document/template/proposal write operations can affect customer-visible workflows and should require clear user intent.
Install Mechanism
The install path uses the expected mcporter wrapper tooling, but mcporter is installed from npm latest rather than a pinned version.
Credentials
PandaDoc OAuth access is purpose-aligned, but it is high-impact business-account access and the runtime data boundary is not fully captured by the repository artifacts.
Persistence & Privilege
The helper script persists OAuth access and refresh tokens into the shared local mcporter credential vault; this is disclosed in code and purpose-aligned, but users should treat it as sensitive.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install maverick-pandadoc-mcp
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /maverick-pandadoc-mcp 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.0
- Initial release of the maverick-pandadoc-mcp skill. - Provides a context for working with PandaDoc documents, templates, recipients, proposals, and status using Maverick-provisioned OAuth credentials. - No provider-owned PandaDoc MCP manifest is registered yet; runtime tools must be inspected and used with care. - Includes guidance on authentication, safety, data flow, and required dependencies (mcporter, jq, flock, shasum).
元数据
Slug maverick-pandadoc-mcp
版本 1.0.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 1
常见问题

Pandadoc mcp 是什么?

Use PandaDoc integration context for documents, templates, recipients, proposals, and document status. Use after Maverick connects PandaDoc and provisions ru... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 26 次。

如何安装 Pandadoc mcp?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install maverick-pandadoc-mcp」即可一键安装,无需额外配置。

Pandadoc mcp 是免费的吗?

是的,Pandadoc mcp 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Pandadoc mcp 支持哪些平台?

Pandadoc mcp 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 Pandadoc mcp?

由 Maverick(@maverick)开发并维护,当前版本 v1.0.0。

💬 留言讨论