io.github.kansei-link/kansei-mcp-server

Official

by kansei-link · HTML

Local-first MCP navigator for AI agents. 11,000+ services, 200 recipes, 89-97% token savings.

Local-first navigator indexing 11,000+ services and 200 recipes for token-efficient AI agent access.

Topics

aeoai-agentmcpmcp-servermodel-context-protocoljapanese-saasagent-toolsjapanjapanese-businessclaude-codecursordeveloper-toolslocal-firstsaassqlitetoken-optimization

README.md9 KBView on GitHub

KanseiLink MCP Server

Local-first MCP navigator for AI agents. Find, evaluate, and compose MCP tools -- 80% fewer tokens vs trial-and-error.

Your agent wastes thousands of tokens every time it hits a new MCP service: searching docs, guessing auth flows, recovering from errors. KanseiLink eliminates that loop with a local SQLite DB of pre-evaluated services, trust scores, and step-by-step recipes.

Token savings: 89-97% measured across 7 services (avg ~16,800 tokens without → ~950 with KanseiLink).

Quick Start

bash

npx @kansei-link/mcp-server

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

Add to your config (claude_desktop_config.json, .cursor/mcp.json, etc.):

json

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

Or with Claude Code CLI:

bash

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

What's Inside

	Count	Description
Services	11,000+	MCP servers and SaaS APIs across 23 categories (2,257 MCP-verified via handshake)
Recipes	200	Multi-service workflow compositions (standup, PR review, incident response, onboarding...)
API Guides	199	Auth setup, endpoints, rate limits, pitfalls, and workarounds
Trust Scores	Weekly	Based on automated health probes + real agent usage data

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

Why Not Just Read the Docs?

Without KanseiLink	With 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 reference	Agent has auth flow, pitfalls, workarounds
`web_fetch` auth guide	in ~950 tokens
Trial-and-error on wrong params	First try succeeds
~16,800 tokens burned	89-97% 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 @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).

Add to ~/.claude/settings.json:

json

{
  "hooks": {
    "PostToolUse": [{
      "matcher": "mcp__.*",
      "hooks": [{ "type": "command", "command": "npx -y @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)

code

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

Tool	Modes	Description
`search_services`	--	Find services by intent (FTS5 + trigram + category boost)
`lookup`	8 modes	Get tips, detail, insights, recipes, combinations, history, feedback, voices
`report`	4 modes	Report outcomes, submit feedback, record events, share your voice

Admin Tools (2 additional)

Tool	Modes	Description
`inspect`	8 modes	Colony health: inspection queue, anomaly verification, update proposals, snapshots
`analyze`	4 modes	Analytics: token savings, cost audit, AEO reports and articles

Lookup Modes

Mode	Trigger	Example
tips (default)	`service_id` alone	`lookup({ service_id: "freee" })`
detail	`detail: true`	`lookup({ service_id: "freee", detail: true })`
insights	`insights: true`	`lookup({ service_id: "freee", insights: true })`
recipe	`goal`	`lookup({ goal: "onboard employee" })`
combinations	`service` (fuzzy name)	`lookup({ service: "freee" })`
history	`period`	`lookup({ service_id: "freee", period: "30d" })`
feedback	`feedback_status`	`lookup({ feedback_status: "open" })`
voices	`mode: "voices"`	`lookup({ mode: "voices", service_id: "freee" })`

Report Modes

Mode	Trigger	Example
outcome	`success` (boolean)	`report({ service_id: "freee", success: true })`
feedback	`subject` + `body`	`report({ subject: "...", body: "..." })`
event	`event_type`	`report({ event_type: "api_change", event_date: "2025-01-15", title: "..." })`
voice	`question_id`	`report({ question_id: "best_feature", response_text: "...", service_id: "freee" })`

Example Workflows

Find and integrate a service:

code

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:

code

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

Share your honest opinion:

code

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

code

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 can generate intelligence reports showing how AI agents experience your API:

Success rate, latency, error patterns over time
Agent Voice: selection criteria, frustrations, recommendations
Category ranking vs competitors
Impact of API changes (before/after analysis)

Interested? See kansei-link.com or reach out.

Privacy & Data Handling

KanseiLink is privacy-preserving by default:

Local-first: the full service DB ships inside the npm package. No API calls needed.
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

<details> <summary>The skill isn't firing -- Claude Code doesn't call KanseiLink when I ask about SaaS.</summary>

Verify the skill was installed:
bash
```
ls ~/.claude/skills/kansei-link/SKILL.md
```
If absent, run npx -y @kansei-link/mcp-server kansei-link-install-skill.
Restart Claude Code. Skills are indexed on session start.

Check that the MCP is registered under the name kansei-link:

bash

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

</details> <details> <summary><code>search_services</code> returns nothing for a service I know exists.</summary>

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: "..." }).

</details> <details> <summary>Auth error when calling a SaaS endpoint after KanseiLink suggests it.</summary>

Start with lookup({ 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.

</details>

Contributing

bash

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:

code

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

License

MIT -- Synapse Arrows PTE. LTD.

Install

claude_desktop_config.json

{
  "mcpServers": {
    "kansei-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "@kansei-link/mcp-server@1.1.0"
      ]
    }
  }
}

Topics

KanseiLink MCP Server

Quick Start

What's Inside

Why Not Just Read the Docs?

Claude Code: install the skill (auto-invocation)

Optional: PostToolUse hook

Tools (5)

Standard Flow (3 tools -- all you need)

Admin Tools (2 additional)

Lookup Modes

Report Modes

Example Workflows

Categories (23)

Architecture

For SaaS Companies

Privacy & Data Handling

Troubleshooting

Contributing

Links

License

Install