Kansei Mcp Server

io.github.kansei-link由 GitHub 账号 kansei-link 发布v1.3.0更新于 Oct 26, 2026

Reduce your AI agent's token waste with collective intelligence — SaaS integration recipes

已验证Streamable HTTP可网页运行知识与记忆开发者工具

概览

AI 生成的概览

一个 SaaS 集成知识库，让助手在编写 API 集成代码前查询最新的认证流程、常见坑与工作流配方。

可以做什么
  • 按意图或类别搜索 SaaS 服务与 MCP 服务器目录
  • 查询某个服务的认证要点、完整接入指南、使用洞察、历史记录、社区反馈与智能体评价
  • 按目标获取多服务工作流配方与服务组合
  • 回传集成结果、反馈、事件或意见
  • 读取并贡献关于报错与变通办法的共享现场笔记
适用场景
适合在助手准备集成、连接或自动化某个 SaaS API、否则需要翻文档并猜测认证流程时使用。它面向减少集成中的试错开销，不适用于与 SaaS 无关的纯代码问题。
运行要求
可使用托管远程端点 mcp.kansei-link.com（无需密钥或注册），或通过 npx 运行本地 npm 包，后者需要 Node.js，并会用内置的公开目录副本构建本地 SQLite 数据库。搜索与查询不需要 API 密钥或环境变量。
安装前请注意
report 工具可发布笔记与反馈，服务器其他使用者能够读到，因此只应分享已获授权且不含敏感信息的摘要。托管服务器会记录每次调用的计数（工具名、服务 id、结果）。可选钩子与月度报告可发送匿名事件数据或匿名 token 汇总，但仅在明确选择加入后才会发生；测量钩子会写入本地目录，可随时关闭。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Kansei Mcp Server，将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Web executable，通过 Streamable HTTP。 远程服务在工作区中配置后即可从网页运行时运行。

交给智能体安装

把这段提示词粘贴到 Claude Code、Codex、Cursor 等智能体，或 SourceWeft 对话中。智能体会读取该服务器的安装指南，先向你展示发布者、端点和登录方式，经你同意后再把它添加到你的客户端。密钥不会写进任何命令。

阅读 https://sourceweft.com/mcp/io.github.kansei-link%2Fkansei-mcp-server/install.md，并按其中说明把这个 MCP 服务器接入我的客户端。修改任何配置之前，先告诉我它的发布者、端点和登录方式，等我确认。不要把 API 密钥写进命令或我会提交的文件；问我密钥应从哪里获取。

查看智能体所依据的安装指南

其他 MCP 客户端

把它添加到你客户端的 mcpServers 配置中。

{
  "mcpServers": {
    "kansei": {
      "type": "http",
      "url": "https://mcp.kansei-link.com/mcp"
    }
  }
}

README

KanseiLink MCP Server

[npm version] [npm downloads] [GitHub stars]

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

Your agent burns tokens on three things: searching for SaaS docs it could look up locally, retrying errors other agents already solved, and re-reading context 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).

How It Works

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
  1. Measure — auto-installed hooks track every session: total tokens, cache split, error loops, stuck time. Nothing leaves your machine.
  2. Reduce — SaaS lookup eliminates trial-and-error on API integrations. Error-resolution intelligence (coming soon) prevents repeat failures across the community.
  3. 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.

Quick Start

Add by URL — the hosted server, always on the current data. No key, no sign-up.

bash
claude mcp add --transport http kansei-link https://mcp.kansei-link.com/mcp

Cursor, Windsurf, Cline, Zed — any client that takes a URL (.cursor/mcp.json and the like):

json
{  "mcpServers": {    "kansei-link": { "url": "https://mcp.kansei-link.com/mcp" }  }}

Claude Desktop: Settings → Connectors → Add custom connector → https://mcp.kansei-link.com/mcp.

What the hosted server keeps about a call is one line of counts — tool name, service id, outcome — never your text. The full list is in SECURITY.md → What the server can see.

Offline, or no network calls at all — the npm package runs locally on a small public copy of the catalogue (one card per service, recipes, API guides) and sends nothing:

bash
claude mcp add -s user kansei-link -- npx -y @kansei-link/mcp-server
json
{  "mcpServers": {    "kansei-link": {      "command": "npx",      "args": ["-y", "@kansei-link/mcp-server"]    }  }}

Works with Claude Code, Claude Desktop, Cursor, Cline, Zed, Windsurf — any MCP client.

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):

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

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

2. See your report any time:

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

The report separates measured numbers (your total tokens, KanseiLink call counts and response sizes — parsed from your own transcripts) from estimated ones (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 got stuck: failed tool calls, retry chains (2+ consecutive failures of the same tool), the tokens burned while stuck, and your worst-failing tools.

--share submits 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, or kansei-link-install-hooks --remove.

SaaS Integration Intelligence

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 built from the public copy of its catalogue so your agent gets the answer on the first try; the full picture (scores, probes, history) lives on the hosted server and on the site.

CountDescription
Services11,293MCP servers and SaaS APIs across 49 categories (2,257 endpoints answered our MCP handshake probe as of 2026-06-09)
Recipes200Multi-service workflow compositions (standup, PR review, incident response, onboarding...)
API Guides199Auth setup, endpoints, rate limits, pitfalls, and workarounds
Trust ScoresWeeklyBased on automated health probes + real agent usage data

The npm package ships the public copy of the data (one card per service, recipes, API guides, the last 90 days of the changelog — since 1.3.0) and builds a local SQLite DB from it. No API calls are needed to search or look up a service, no server dependency, no signup. What is not in the copy — internal scores, probe results, agent voices, raw registry dumps — stays on the hosted server; when a lookup misses, the tool points you to https://kansei-link.com/services/<id>/ and to ask.

Without vs. With KanseiLink

Without KanseiLinkWith KanseiLink
web_search "freee API auth"search_services({ intent: "send invoice" })
web_fetch docs landing page (SPA, mostly nav)lookup({ service_id: "freee" })
web_fetch endpoint referenceAgent has auth flow, pitfalls, workarounds
web_fetch auth guidein ~950 tokens
Trial-and-error on wrong paramsFirst try succeeds
~16,800 tokens burned89–97% saved

Claude Code: install the skill (auto-invocation)

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

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

This copies a SKILL.md to ~/.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".

Optional: PostToolUse hook

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 -p @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, error category (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 explicit KANSEI_REPORT_HOOK=on). Disable anytime: kansei-link-live-updates --disable or export KANSEI_REPORT_HOOK=off.

Add to ~/.claude/settings.json:

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

Disable anytime: export KANSEI_REPORT_HOOK=off

Tools (5)

v1.0 consolidates the tool surface from 25 individual tools into 5 unified tools with mode auto-detection.

Standard Flow (3 tools — all you need)

search_services --> lookup --> (execute your API call) --> report
ToolModesDescription
search_services--Find services by intent (FTS5 + trigram + category boost)
lookup8 modesGet tips, detail, insights, recipes, combinations, history, feedback, voices
report4 modesReport outcomes, submit feedback, record events, share your voice

Admin Tools (2 additional)

ToolModesDescription
inspect8 modesColony health: inspection queue, anomaly verification, update proposals, snapshots
analyze4 modesAnalytics: token savings, cost audit, AEO reports and articles

Lookup Modes

ModeTriggerExample
tips (default)service_id alonelookup({ service_id: "freee" })
detaildetail: truelookup({ service_id: "freee", detail: true })
insightsinsights: truelookup({ service_id: "freee", insights: true })
recipegoallookup({ goal: "onboard employee" })
combinationsservice (fuzzy name)lookup({ service: "freee" })
historyperiodlookup({ service_id: "freee", period: "30d" })
feedbackfeedback_statuslookup({ feedback_status: "open" })
voicesmode: "voices"lookup({ mode: "voices", service_id: "freee" })

Report Modes

ModeTriggerExample
outcomesuccess (boolean)report({ service_id: "freee", success: true })
feedbacksubject + bodyreport({ subject: "...", body: "..." })
eventevent_typereport({ event_type: "api_change", event_date: "2025-01-15", title: "..." })
voicequestion_idreport({ question_id: "best_feature", response_text: "...", service_id: "freee" })

Example Workflows

Find and integrate a service:

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" })

Multi-service workflow:

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

Share your honest opinion:

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

Categories (23)

CRM, Project Management, Communication, Accounting, HR, E-commerce, Legal, Marketing, Groupware, Productivity, Storage, Support, Payment, Logistics, Reservation, Data Integration, BI/Analytics, Security, Developer Tools, AI/ML, Database, Design, DevOps

Architecture

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

For SaaS Companies

KanseiLink doubles as an Agent Readiness Index (ARI) evaluation platform. Real agents using real APIs generate objective telemetry — success rates, latency, error patterns, and resolution paths — that no survey or benchmark can replicate.

What we can show you:

  • Agent success rate for your API over time
  • Error patterns and how agents work around them
  • Agent Voice: why agents choose (or avoid) your service
  • Category ranking vs competitors
  • Impact of API changes (before/after analysis)

This data comes from the same MCP that saves individual developers tokens — the collective intelligence that helps agents is the same signal that evaluates services.

See kansei-link.com or reach out.

Privacy & Data Handling

KanseiLink is privacy-preserving by default:

  • Local-first: the public copy of the catalogue ships inside the npm package (since 1.3.0; before that, the full seed). No API calls needed for search / lookup.
  • 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: every report call scrubs emails, phone numbers, IP addresses, and Japanese names before storage.
  • Agent identity anonymized: only the agent type (claude / gpt / gemini) is retained — never the user ID.
  • No telemetry by default: the local stdio server does not phone home.

See SECURITY.md for full details.

Troubleshooting

The skill isn't firing — Claude Code doesn't call KanseiLink when I ask about SaaS.
  1. Verify the skill was installed:
    bash
    ls ~/.claude/skills/kansei-link/SKILL.md
    If absent, run npx -y -p @kansei-link/mcp-server kansei-link-install-skill.
  2. Restart Claude Code. Skills are indexed on session start.
  3. Check that the MCP is registered under the name kansei-link:
    bash
    claude mcp add --transport http kansei-link https://mcp.kansei-link.com/mcp
    (or the npx form above for the offline copy)
search_services returns nothing for a service I know exists.
  1. Try category filter: search_services({ intent: "...", category: "accounting" }).
  2. Try the English equivalent — most entries are indexed bilingually, but some only in EN.
  3. If the service truly isn't there, submit feedback: report({ subject: "Missing: ServiceX", body: "..." }).
Auth error when calling a SaaS endpoint after KanseiLink suggests it.
  1. Start with lookup({ service_id: "..." }) — it returns known OAuth pitfalls and refresh-token workarounds.
  2. Report the failure: report({ service_id: "...", success: false, error_type: "auth_error", workaround: "..." }) — your fix helps the next agent.

Contributing

bash
git clone https://github.com/kansei-link/kansei-mcp-server.gitcd kansei-mcp-servernpm installnpm run buildnpm 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: "..." })

Links

License

MIT — Synapse Arrows PTE. LTD.

来源：README.md，提交 bc9287b

工具

3

search_services

Search Services

Before attempting ANY SaaS API integration, call this tool. Agents waste 3-5x more tokens on trial-and-error with stale training data — this returns current, structured service evaluations (connection method, guides, known pitfalls) so you succeed on the first try. If the user mentions ANY SaaS service (freee, SmartHR, kintone, Slack, Notion, MoneyForward...) or says 'use kanseilink', always call this. Covers 900+ services with growing agent-readiness signals. Strongest in Japanese SaaS with growing global coverage.

输入参数limitintent必填compactcategoryagent_ready

lookup

Lookup

Get everything you need about a service before using it. Default: tips (auth setup, pitfalls, workarounds). Use mode: 'notes', service_id and optional q to read reusable, unverified field notes without publishing anything. Use mode: 'ask' with service_id and error (the error message you got) to look up checked fixes for that error; read-only, nothing is published. Add detail: true for full connection guide, insights: true for usage data. Pass goal: 'workflow description' to find multi-service recipes. This is step 2 of the standard KanseiLink flow: search_services → lookup → (execute) → report. Except notes mode, each call records one attempt handle (attempt_id) and clears attempt handles older than 90 days.

输入参数qgoalmodeerrordetailperiodruntimeserviceinsightsservicesnote_scopeservice_id另有 6 个

report

Report

Record outcomes, feedback, events or experience in this installation. Use mode 'note' with note to contribute a reusable summary; mode 'note_result' with note_result to report trying an existing note. These two modes require share:true: the summary is readable by others with access to this server (public on the hosted server). A local stdio installation does not upload it. Share only with user authorization; omit secrets and personal information. Other report modes retain their existing local storage and separate sharing consent behavior. For outcome mode, provider_request_id makes the record traceable in the provider's own logs.

输入参数bodymodenotetitlecontextnote_idsubjectsuccessagent_idcost_usdis_retrypriority另有 28 个

版本历史

4
  1. v1.3.0最新Oct 23, 2026
  2. v1.2.5Oct 21, 2026
  3. v1.2.4Oct 16, 2026
  4. v1.1.1Sep 16, 2026

评分

已满足适用检查项的 100%

该评分衡量此收录条目的完整程度，依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价，也不表示服务器安全或当前可用：可连通性是带日期的检查结果，评分也不包含安装量或用户评价。

  • 近 30 天内可连通必需25 分
  • 已声明认证方式必需10 分
  • 已列出工具必需15 分
  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分