KanseiLink

Reduce your AI agent's token waste with collective intelligence.

Your agent burns tokens on three things:searchingfor SaaS docs it could look up locally,retryingerrors other agents already solved, andre-readingcontext it already processed. KanseiLink tackles the first two — and measures all three so you know exactly where your tokens go.

Measured savings: 89–97% on SaaS integration research(avg ~16,800 tokens without → ~950 with KanseiLink, across 7 services).

Install MCP → agent wastes fewer tokens (lookup + collective intelligence) ↓ usage data stays local (opt-in: anonymous scalars only) ↓ collective intelligence grows → everyone's agent gets smarter

- Measure— auto-installed hooks track every session: total tokens, cache split, error loops, stuck time. Nothing leaves your machine.
- Reduce— SaaS lookup eliminates trial-and-error on API integrations. Error-resolution intelligence (coming soon) prevents repeat failures across the community.
- Compare— opt-in monthly "Wrapped" report shows where your tokens went and how you rank among measured users.

If KanseiLink saves your agent tokens,give it a star ⭐— 700+ developers install it from npm every month, and stars are how the next one finds it.

{ "mcpServers": { "kansei-link": { "command": "npx", "args": ["-y", "@kansei-link/mcp-server"] } } }

claude mcp add -s user kansei-link -- npx -y @kansei-link/mcp-server

Wrapped: Your Monthly Agent Fuel-Efficiency Report

KanseiLink measures — locally, on your machine — how many tokens your agent sessions consume and how much of that KanseiLink saved you, then renders a monthly "Wrapped" share card.

1. Install the measurement hooks(one command, idempotent, backs up your settings first):

npx -y @kansei-link/mcp-server kansei-link-install-hooks

This adds aStop/SessionEndhook that parses each session transcript and writes token totals + KanseiLink call stats to~/.kansei-link/usage/.Nothing is uploaded.

npx -y @kansei-link/mcp-server kansei-link-wrapped # current month (JA) npx -y @kansei-link/mcp-server kansei-link-wrapped --lang en # English npx -y @kansei-link/mcp-server kansei-link-wrapped --share # opt-in: get your rank

The report separatesmeasurednumbers (your total tokens, KanseiLink call counts and response sizes — parsed from your own transcripts) fromestimatedones (the avoided web-research cost, based on the 2026-04-16 freee/kintone/smarthr benchmark) — labels shown on every surface.

It also shows where your agent gotstuck: failed tool calls, retry chains (2+ consecutive failures of the same tool), the tokens burned while stuck, and your worst-failing tools.

--sharesubmits only scalar monthly aggregates (anonymous id + token counts, never content) and returns how you rank among measured users ("top X% saver"). Below 20 measured users for the month, you get the cohort size instead of a rank.

Disable measurement anytime:export KANSEI_USAGE_HOOK=off, orkansei-link-install-hooks --remove.

The core reason agents waste tokens on SaaS APIs: they search docs, guess auth flows, and recover from errors — every single time. KanseiLink ships a local SQLite DB so your agent gets the answer on the first try.

All data ships inside the npm package as a local SQLite DB.Zero API calls needed.No server dependency, no signup.

Claude Code: install the skill (auto-invocation)

Installing the MCP alone doesn't teach Claude Codewhento call KanseiLink. The bundled skill fixes that:

npx -y @kansei-link/mcp-server kansei-link-install-skill

This copies aSKILL.mdto~/.claude/skills/kansei-link/. Claude Code auto-discovers it and fires the skill on phrases like "connect to Stripe", "Slack MCPある？", "send invoice via freee" — no need to say "use KanseiLink".

Auto-capture success/failure after every MCP call (agents tend to forget reporting).

Consent (v1.2, BREAKING).Installing the hook alone no longer transmits anything. All central transmission is governed by one consent gate (~/.kansei-link/consent.json), with this priority:DO_NOT_TRACK=1/ explicit OFF → explicit ON (KANSEI_REPORT_HOOK=on) → Live Updates consent (npx -y @kansei-link/mcp-server kansei-link-live-updates --enable) →default OFF (Local Mode, zero transmission). Existing hook users are OFF until they re-consent. Manage:kansei-link-live-updates --status|--enable|--disable,kansei-link-privacy --status|--reset-id.

What this hook sends when enabled (and what it never sends).A small pseudonymous event to KanseiLink's hosted endpoint after each MCP tool call. The payload is a fixed 7-field set, frozen by a snapshot test (scripts/smoke-hook-payload.mjs):

- sent: service slug (or MCP server name), success/failure, tool name, errorcategory(e.g.auth_error), a fixed context string
- never sent: prompts, tool inputs/outputs, page/customer/record names, API keys, file paths, free text of any kind. No account or machine identifier is attached.

Installing the hook does NOT opt you in — transmission requires the consent gate above (Live Updates consent, or an explicitKANSEI_REPORT_HOOK=on). Disable anytime:kansei-link-live-updates --disableorexport KANSEI_REPORT_HOOK=off.

{ "hooks": { "PostToolUse": [{ "matcher": "mcp__.", "hooks": [{ "type": "command", "command": "npx -y @kansei-link/mcp-server kansei-link-report-hook" }] }] } }

search_services --> lookup --> (execute your API call) --> report

search_services({ intent: "send invoice to clients", compact: true }) --> lookup({ service_id: "freee" }) // tips: auth, pitfalls, workarounds --> lookup({ service_id: "freee", detail: true }) // full connection guide --> (execute your API call) --> report({ service_id: "freee", success: true, task_type: "create_invoice" })

lookup({ goal: "create invoice and notify via slack", services: ["freee", "slack"] }) --> Step-by-step recipe with coverage scoring

report({ service_id: "stripe", question_id: "biggest_frustration", response_text: "Webhook signature verification docs are unclear for non-Node runtimes" })

Agent <-> KanseiLink MCP Server <-> SQLite (local, zero-config) | +-- search_services -> FTS5 + trigram (CJK) + LIKE + category detection +-- lookup -> tips / detail / insights / recipe / combinations / | history / feedback / voices (auto-detected) +-- report -> outcome / feedback / event / voice (auto-detected) +-- inspect -> queue / submit / propose / review / snapshot / evaluate +-- analyze -> token_savings / cost / aeo_report / aeo_article

- Local-first: the full service DB ships inside the npm package. No API calls needed.
- Measurement stays local: the usage hook writes to~/.kansei-link/usage/on your machine. Nothing is uploaded unless you opt in with--share, which sends only scalar aggregates (token counts), never content.
- PII auto-masking: everyreportcall scrubs emails, phone numbers, IP addresses, and Japanese names before storage.
- Agent identity anonymized: only the agenttype*(claude / gpt / gemini) is retained — never the user ID.
- No telemetry by default: the local stdio server doesnotphone home.
- Verify the skill was installed:

ls ~/.claude/skills/kansei-link/SKILL.md

claude mcp add -s user kansei-link -- npx -y @kansei-link/mcp-server

- Try category filter:search_services({ intent: "...", category: "accounting" }).
- Try the English equivalent — most entries are indexed bilingually, but some only in EN.
- If the service truly isn't there, submit feedback:report({ subject: "Missing: ServiceX", body: "..." }).
- Start withlookup({ service_id: "..." })— it returns known OAuth pitfalls and refresh-token workarounds.
- Report the failure:report({ service_id: "...", success: false, error_type: "auth_error", workaround: "..." })— your fix helps the next agent.

git clone https://github.com/kansei-link/kansei-mcp-server.git cd kansei-mcp-server npm install npm run build npm start # start stdio server

PRs welcome. If you find a service that's missing or has wrong info, the fastest path is:

report({ subject: "Fix: ServiceX auth is OAuth2 not API key", body: "..." })

- npm
- Website
- MCP Registry:io.github.kansei-link/kansei-mcp-server
- Glama

Build and deploy full-stack Next.js apps with 98 tools for React, AWS, and MongoDB