Agent skill

Patsnap Ip Searching

by patsnap in patsnap/mcp

Patsnap Patent Research MCP for AI agents. An agent skill from patsnap/mcp.

Apache-2.0Auto-check passedLegal & Compliance

Install Patsnap Ip Searching

skills CLI
$ npx skills add patsnap/mcp --skill patsnap-ip-searching -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install patsnap/mcp patsnap-ip-searching --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/patsnap/mcp.git skills-src && mkdir -p .claude/skills && cp -r skills-src/ip-intelligence/patsnap-ip-searching .claude/skills/patsnap-ip-searching && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
patsnap-ip-searching
GitHub stars
113
Token cost
~1.1k tokens
SKILL.md length
424 words
Files
2
Skills in repo
32
Repo updated
First seen
Licence
Apache-2.0

At a glance

Patsnap Patent Research MCP for AI agents. An agent skill from patsnap/mcp.

  • Defined novelty and infringement-risk research workflows
  • SKILL.md covers Setup, Prerequisites, Instructions for AI Agents and Example Workflows, plus 1 more section
  • Reaches connect.patsnap.com
  • Including asynchronous task retrieval

What it does

Patsnap Ip Searching is an agent skill from patsnap/mcp. Patsnap Patent Research MCP for AI agents. Performs novelty searches, invention freedom-to-operate reviews, and design-patent FTO reviews from technical text, claims, disclosures, or product images. Use for defined novelty and infringement-risk research workflows, including asynchronous task retrieval; do not use it as a substitute for legal advice.

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `README.md`).

It sits in Legal & Compliance, covering Intellectual property and Async programming. It works with Model Context Protocol. The repository describes itself as: MCP server for 200M+ patents, scientific literature, chemistry and pharma records. Search prior art and R&D intelligence powered by PatSnap's proprietary databases via Claude… The licence is Apache-2.0.

When your agent uses it

  • Defined novelty and infringement-risk research workflows
  • Including asynchronous task retrieval
  • Do not use it as a substitute for legal advice

Example prompts

  • “/patsnap-ip-searching”

Requirements

  • A credential in YOUR_API_KEY

What it can do on your machine

Read from SKILL.md and the folder at commit 7a4b429. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are json).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • connect.patsnap.com

    Also links to:

    • open.patsnap.com
    • patsnap.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Patsnap Ip Searching loads about 1.1k tokens when it runs. Until then it costs about 93 tokens; SKILL.md has 424 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~93
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from patsnap/mcp at commit 7a4b429, republished under its Apache-2.0 licence (© patsnap). 424 words, ~1,061 tokens.

Download SKILL.mdSave it as .claude/skills/patsnap-ip-searching/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
patsnap-ip-searching
description
Patsnap Patent Research MCP for AI agents. Performs novelty searches, invention freedom-to-operate reviews, and design-patent FTO reviews from technical text, claims, disclosures, or product images. Use for defined novelty and infringement-risk research workflows, including asynchronous task retrieval; do not use it as a substitute for legal advice.
homepage
https://open.patsnap.com/marketplace/mcp-servers/patsnap-ip-searching
metadata.author
Patsnap
metadata.category
IP Intelligence
metadata.version
0.1.0

Setup

Get your API key at https://open.patsnap.com

Patsnap Patent Research

This skill connects your AI agent to Patsnap's Patent Research MCP server.

Prerequisites

json
{
  "mcpServers": {
    "patsnap_patent_research": {
      "url": "https://connect.patsnap.com/f176d7/mcp?apikey=YOUR_API_KEY",
      "type": "streamableHttp"
    }
  }
}

For the full tool schema, refer to: https://open.patsnap.com/marketplace/mcp-servers/patsnap-ip-searching


Instructions for AI Agents

Choose the correct workflow
  • Use novelty_search for a technical solution, invention disclosure, or claim-text novelty review. Text is the primary input; images are optional supplements. Optional search channels include semantic, Boolean, paper, and web search.
  • Use fto_review for invention-patent infringement-risk research based on a product or technical implementation. The required input object uses text as its primary content and can include translated text and images.
  • Use design_fto for design-patent risk research. Its required input object must contain at least one image; only the first item in input.images is used, and a title is optional.
  • Use a general patent-search MCP instead when the user needs open-ended discovery, query construction, or retrieval without a novelty or FTO analysis workflow.
Configure search and filters carefully

For fto_review, search.mode supports lite for rapid screening and pro for full analysis. Its search settings can also control candidate-patent count and iterative search rounds. Optional filters support country, apd, legal_status, and assignee; application-date ranges use YYYYMMDD, and assignee filters support not_in.

For design_fto, optional filters support country, apd, legal_status, and loc; loc uses Locarno classifications and application-date ranges use YYYYMMDD.

The analysis tools also accept optional execution settings for asynchronous execution or real-time progress, optional output controls such as normalized result-row limits, and an optional caller-supplied task_id.

Show full SKILL.md (179 more words)Show less
Retrieve asynchronous results

When a tool runs asynchronously, preserve its returned task_id and call get_task. The task_id is required. Use view: overview for the status summary; this is the default. Use view: detail when step and result details are needed. Do not start duplicate analyses merely because a task is still running.

Interpret results responsibly

Preserve the user's technical scope, countries, date window, legal-status assumptions, and other filters in the report. Distinguish retrieved patents and service-generated comparisons from your own interpretation. Novelty and FTO outputs support research and triage; they do not establish patent validity, non-infringement, or a legal opinion. Recommend qualified patent counsel for decisions carrying legal or commercial risk.

Example Workflows

  • Search the novelty of an invention disclosure and compare its extracted features with candidate patents.
  • Run a lite FTO screening, then use pro analysis for the highest-risk implementation.
  • Restrict an invention FTO review by country, application date, legal status, and excluded assignees.
  • Review a single product image for design-patent risk in specified Locarno classes.

Resources

© patsnap, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in ip-intelligence/patsnap-ip-searching of patsnap/mcp.

  • SKILL.md
  • README.md

Open the folder on GitHubat commit 7a4b429

Compare with similar skills

Patsnap Ip Searching next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Patsnap Ip Searching compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Patsnap Ip Searching this skillpatsnap/mcp113—~1.1kAutomated safety check: PassApache-2.0
Prior Art Searchillusionaireal/oh-my-patent104—~1.8kAutomated safety check: PassMIT
Mpep SearchRobThePCGuy/Claude-Patent-Creator196—~978Automated safety check: PassMIT
Patent Draft Agentninehills/skills280—~1.2kAutomated safety check: PassNone
Patent ReviewAI4Scientist/nano-scientist1282 repos~1.6kAutomated safety check: NotesNone
Setup AssistantRobThePCGuy/Claude-Patent-Creator196—~1.4kAutomated safety check: NotesMIT

Similar skills

  • Prior Art Search

    illusionaireal/oh-my-patent

    A skill your agent uses when searching patents and technical literature for prior art, novelty, or patentability assessment.

    104 GitHub stars~1.8k tokensUpdated 2 days ago
    Legal & ComplianceAuto-check passed
  • Mpep Search

    RobThePCGuy/Claude-Patent-Creator

    Expert system for searching USPTO MPEP, 35 USC statutes, 37 CFR regulations, and post-Jan 2024 updates.

    196 GitHub stars~978 tokensUpdated 4 days ago
    Legal & ComplianceAuto-check passed
  • Patent Draft Agent

    ninehills/skills

    生成符合中国专利法规范的专利交底书。接收 Markdown 格式的技术描述作为输入,通过多阶段流水线(标题生成、专利检索、发明目的撰写、发明内容撰写、图表生成、报告合并)自动生成完整的专利交底书。

    280 GitHub stars~1.2k tokensUpdated 3 mo ago
    Legal & ComplianceAuto-check passed
  • Patent Review

    AI4Scientist/nano-scientist

    Get an external patent examiner review of a patent application.

    128 GitHub starsUsed in 2 repos~1.6k tokens
    Legal & ComplianceAuto-check: notes
  • Setup Assistant

    RobThePCGuy/Claude-Patent-Creator

    Guides through installation, configuration, and first-time setup of the Claude Patent Creator system.

    196 GitHub stars~1.4k tokensUpdated 4 days ago
    Legal & ComplianceAuto-check: notes
  • Prior Art Scout

    n1m21n/Infinite

    Find publicly documented solutions (peer repos, GitHub, forums) to bugs, platform quirks, dependency gotchas or architectural patterns, respecting the copyleft discussions-only rule.

    271 GitHub stars~1.3k tokensUpdated yesterday
    Legal & ComplianceAuto-check passed

More from patsnap/mcp

All 32 skills in this repo
  • Patsnap TRIZ Concept Solution Engine MCP for AI agents. An agent skill from patsnap/mcp.

    113 GitHub stars~825 tokensUpdated 1 mo ago
    Auto-check passed
  • Patsnap TRIZ Case Library MCP for AI agents. An agent skill from patsnap/mcp.

    113 GitHub stars~885 tokensUpdated 1 mo ago
    Auto-check passed
  • Patsnap Workspace MCP for AI agents. An agent skill from patsnap/mcp.

    113 GitHub stars~777 tokensUpdated 1 mo ago
    Auto-check passed
  • Create or update Patsnap MCP catalog documentation in this repository.

    113 GitHub stars~1.2k tokensUpdated 1 mo ago
    Auto-check passed
  • Patsnap Advanced Patent Search MCP for AI agents. An agent skill from patsnap/mcp.

    113 GitHub stars~650 tokensUpdated 1 mo ago
    Auto-check passed
  • Biological sequence and modality intelligence via Patsnap MCP.

    113 GitHub stars~771 tokensUpdated 1 mo ago
    Auto-check passed

Questions about Patsnap Ip Searching

What does Patsnap Ip Searching do?

Patsnap Patent Research MCP for AI agents. An agent skill from patsnap/mcp. Patsnap Ip Searching is an agent skill from patsnap/mcp. Patsnap Patent Research MCP for AI agents.

When should I use Patsnap Ip Searching?

Patsnap Ip Searching fits situations like: defined novelty and infringement-risk research workflows; including asynchronous task retrieval; do not use it as a substitute for legal advice.

How do I install Patsnap Ip Searching in Claude Code?

Run `npx skills add patsnap/mcp --skill patsnap-ip-searching -a claude-code`. Or copy the skill folder (ip-intelligence/patsnap-ip-searching in patsnap/mcp) into .claude/skills/patsnap-ip-searching in your project. Claude Code loads it when a task matches its description.

How do I install Patsnap Ip Searching in Codex?

Run `npx skills add patsnap/mcp --skill patsnap-ip-searching -a codex`. Or copy the skill folder (ip-intelligence/patsnap-ip-searching in patsnap/mcp) into .agents/skills/patsnap-ip-searching in your project. Codex loads it when a task matches its description.

Can I use Patsnap Ip Searching in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add patsnap/mcp --skill patsnap-ip-searching -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/patsnap-ip-searching, .gemini/skills/patsnap-ip-searching, .github/skills/patsnap-ip-searching and .opencode/skills/patsnap-ip-searching in your project.

What does Patsnap Ip Searching need to run?

SKILL.md names no scripts, command-line tools or credentials: Patsnap Ip Searching is instructions for the agent only. Our summary lists: A credential in YOUR_API_KEY.

Does Patsnap Ip Searching access the network?

SKILL.md names 3 domains. In commands or code: connect.patsnap.com; the agent is likely to contact it when it follows the instructions. As links in the text: open.patsnap.com and patsnap.com. This is read from the text; nothing was executed.

Is Patsnap Ip Searching safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Patsnap Ip Searching use?

Patsnap Ip Searching is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Patsnap Ip Searching use?

About 1.1k tokens (SKILL.md is roughly 4.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Patsnap Ip Searching?

Skills that share tags, products or a category with Patsnap Ip Searching: Prior Art Search (illusionaireal/oh-my-patent, 104 stars), Mpep Search (RobThePCGuy/Claude-Patent-Creator, 196 stars), Patent Draft Agent (ninehills/skills, 280 stars) and Patent Review (AI4Scientist/nano-scientist, 128 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Patsnap Ip Searching?

patsnap (a GitHub organization) maintains it in patsnap/mcp, which has 113 GitHub stars. The repository holds 32 skills in this directory. The repository was last updated on August 20, 2026.

Source: patsnap/mcp on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.