patsnap-workspace

patsnap-workspace is a skill for Claude Code, Codex from patsnap/mcp. It costs 55 tokens per session (737 once invoked), scanned A, original, Apache-2.0.

A reader for patent collections stored in Patsnap Workspaces, including their folders, fields, and annotations. It reads existing collections rather than searching all patents.

In plain words
What is it for?
Reading patents from a selected workspace folder, inspecting custom fields or AI labels, and retrieving comments attached to those records.
Why use it?
It avoids manually navigating workspace folders and checking separate fields or comments. It also reduces errors by using the workspace and folder identifiers returned by Patsnap.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Reading patents from a selected workspace folder, inspecting custom fields or AI labels, and retrieving comments attached to those records.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/patsnap/mcp/patsnap-workspace
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 patsnap/mcp --skill patsnap-workspace
Clone the repo
git clone --depth 1 https://github.com/patsnap/mcp

Made for: Claude Code, Codex.

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 patsnap-workspace

README.md
[![agentmods](https://agentmods.dev/badge/skills/patsnap/mcp/patsnap-workspace/github.svg)](https://agentmods.dev/skills/patsnap/mcp/patsnap-workspace)
Your own site
<a href="https://agentmods.dev/skills/patsnap/mcp/patsnap-workspace"><img src="https://agentmods.dev/badge/skills/patsnap/mcp/patsnap-workspace/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 patsnap-workspace

Your own site · 80×15
<a href="https://agentmods.dev/skills/patsnap/mcp/patsnap-workspace"><img src="https://agentmods.dev/badge/skills/patsnap/mcp/patsnap-workspace.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 737 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00055 $0.00737
Opus 5 $0.00028 $0.00368
Sonnet 5 $0.00011 $0.00147
Haiku 4.5 $0.00006 $0.00074

Measured 10d ago against content hash faa4ba9613b5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

patsnap-workspace 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 10d 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.

ip-intelligence/patsnap-workspace/SKILL.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Setup

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

Workspace Patent Collection Reader

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

Prerequisites

{
  "mcpServers": {
    "patsnap_workspace": {
      "url": "https://connect.zhihuiya.com/48a232/logic-mcp?apikey=YOUR_API_KEY",
      "type": "streamableHttp"
    }
  }
}

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


Instructions for AI Agents

Follow the identifier chain

  1. Call list_workspace_spaces, optionally filtering type by all, self, shared, or public, or using search_name.
  2. Use the returned space_id with list_workspace_folders; optionally search folder names.
  3. Call list_workspace_fields(space_id) when fields, AI labels, custom fields, or annotations are involved.
  4. Call get_workspace_patents(space_id, folder_id, ...) for folder patents.
  5. Call get_workspace_annotations(space_id, folder_id, ...) for AI-label/custom-field values and optional comments.

Never guess space_id, folder_id, or field_ids. When multiple names match, present candidates before reading a large collection.

Respect tool limits

get_workspace_patents supports keyword, limit, and zero-based offset. It does not support filters, sorting, ranges, custom-field filters, or AI-label filters. If you post-filter a manageable returned set, label that as local processing rather than a server-side query.

get_workspace_annotations accepts optional patent_ids or publication numbers, with a maximum of 200, optional field_ids, include_comments, and pagination controls. Empty annotations mean no stored value, not a negative classification.

Report scope

Preserve workspace and folder names with their IDs, state whether results are complete or sampled, cite publication numbers or returned IDs, and distinguish comments from structured field values. The MCP is read-oriented; do not imply it edits workspace content.

Read the full file on GitHub · 72 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 10d ago First seen · 72 lines · 55 tokens per session scan A faa4ba9613b5

Subscribe to this mod's changes

patsnap-workspace is a skill published in the GitHub repository patsnap/mcp (111 stars, last pushed 21d ago), licensed Apache-2.0. It adds 55 tokens to every session and 737 once invoked, about $0.0003 per session on Opus 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 2026-08-30.

Related

Other skills, from other repositories

molecular-dynamics

Run and analyze molecular dynamics simulations with OpenMM and MDAnalysis. Set up protein and protein-ligand systems with PDBFixer, choose force fields and water models (AMBER14, CHARMM36m, ff19SB, GAFF2, TIP3P), solvate and add ions, run energy minimization, NVT/NPT equilibration and production MD on GPU, then…

K-Dense-AI/drug-discovery-agent-skills · 180 tokens

molfeat

Molecular featurization hub with one consistent interface over 100+ featurizers. Fingerprints (ECFP/Morgan, MACCS, atom pair, topological torsion, Avalon, RDKit, ERG), RDKit and Mordred descriptor sets, pharmacophore and 3D shape descriptors, scaffold keys, and pretrained embeddings (ChemBERTa, ChemGPT, MolT5, GIN…

K-Dense-AI/drug-discovery-agent-skills · 165 tokens

glycoengineering

Analyze and engineer protein glycosylation. Scan sequences for canonical N-glycosylation sequons (N-X-S/T with X not proline, including overlapping sites), predict O-GalNAc hotspots, read glycan notation, and reach the curated external tooling (NetNGlyc, NetOGlyc, GlycoShield, GlycoWorkbench, GlyTouCan, GlyConnect).…

K-Dense-AI/drug-discovery-agent-skills · 183 tokens

rowan

Rowan is a cloud-native molecular modeling and medicinal-chemistry workflow platform with a Python API. Use for pKa and macropKa prediction, conformer and tautomer ensembles, docking and analogue docking, protein-ligand cofolding, MSA generation, molecular dynamics, permeability, descriptor workflows, and related…

K-Dense-AI/drug-discovery-agent-skills · 100 tokens

chembl

Query the ChEMBL database web services for measured bioactivity data, compound records and calculated properties, targets, assays, mechanisms of action, drug indications and warnings. Use this skill to build curated SAR or QSAR datasets for a target, look compounds up by SMILES, InChIKey, name, or ChEMBL id, run…

K-Dense-AI/drug-discovery-agent-skills · 134 tokens

open-targets

Query the Open Targets Platform GraphQL API for target-disease associations, genetic and clinical evidence, tractability and safety liabilities, target prioritisation metrics, known drugs and mechanisms of action, and disease ontology. Use this skill for target identification and validation, target-disease evidence…

K-Dense-AI/drug-discovery-agent-skills · 124 tokens