Borrowing it
Nothing to install: this file belongs to kansei-link/kansei-mcp-server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/kansei-link/kansei-mcp-server/main/CLAUDE.mdgit clone --depth 1 https://github.com/kansei-link/kansei-mcp-serverWrote 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.
[](https://agentmods.dev/instructions/kansei-link/kansei-mcp-server/claude-md)<a href="https://agentmods.dev/instructions/kansei-link/kansei-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/kansei-link/kansei-mcp-server/claude-md/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.
<a href="https://agentmods.dev/instructions/kansei-link/kansei-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/kansei-link/kansei-mcp-server/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00495 | $0.00495 |
| Opus 5.5 | $0.00198 | $0.00198 |
| Sonnet 5.5 | $0.00099 | $0.00099 |
| Haiku 4.5 | $0.00049 | $0.00049 |
Grade A, and why
kansei-mcp-server CLAUDE.md 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 15d 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.
What it actually says
KanseiLink MCP Server
Reduce your AI agent's token waste with collective intelligence — SaaS integration recipes, error resolution, and monthly efficiency reports.
Available Tools
- search_services — Find SaaS/MCP services by intent (e.g., "send invoice", "manage employees")
- lookup — Get tips, detail, insights, recipes, combinations, history, feedback, voices (auto-detected from params)
- report — Report outcomes, submit feedback, record events, share your voice
- inspect — Colony health: inspection queue, anomaly verification, update proposals, snapshots
- analyze — Analytics: token savings, cost audit, AEO reports and articles
Recommended Workflow
search_services → find the right service
lookup → get tips / full connection guide / recipe
(use the service)
report → share what happened (helps future agents)
Wrapped (Token Measurement)
Install hooks to measure token consumption per session:
npx -y -p @kansei-link/mcp-server kansei-link-install-hooks
View monthly report:
npx -y -p @kansei-link/mcp-server kansei-link-wrapped
Data Policy
- The npm package carries the public copy of the catalogue (1.3.0+): service cards, recipes, API guides. Internal scores, probes, voices and raw registry data are not shipped; a lookup miss points to https://kansei-link.com/services// and to
ask. - All context in report is PII-masked before storage
- Agent identity is anonymized (hashed)
- Usage measurement stays local unless user opts in with --share
- See SECURITY.md for full policy
Connection
By URL (hosted, current data, no key):
claude mcp add --transport http kansei-link https://mcp.kansei-link.com/mcp
{
"kansei-link": { "url": "https://mcp.kansei-link.com/mcp" }
}
Offline (npm, local copy of the public data, sends nothing):
{
"kansei-link": {
"command": "npx",
"args": ["-y", "@kansei-link/mcp-server"]
}
}
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.
- 15d ago Changed · +14 lines · +85 tokens per session ab09df53c8e2
- 16d ago Changed · +1 lines · +61 tokens per session 20f7e3c4440f
- 1mo ago Changed · +4 tokens per session f40592194510
- 2mo ago First seen · 51 lines · 345 tokens per session scan A 05ce3ce4c301
kansei-mcp-server CLAUDE.md is an instructions file published in the GitHub repository kansei-link/kansei-mcp-server (1 stars, last pushed 4d ago), licensed MIT. It adds 495 tokens to every session, about $0.0020 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 2026-08-31.
kansei-mcp-server CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| kansei-mcp-server CLAUDE.mdkansei-link/kansei-mcp-server | Instructions file | 1 | 4d ago | MIT | A | 495 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| vscode model-prompts.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 2,022 | GitHub Copilot |