# io.github.kansei-link/kansei-mcp-server (remote · mcp.kansei-link.com)

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

- Trust score: 80/100 (high trust)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- remote · `mcp.kansei-link.com`: 80/100 (this document), [markdown](https://verifymcp.io/servers/kansei-link-kansei-mcp-server/mcp.md), [page](https://verifymcp.io/servers/kansei-link-kansei-mcp-server/mcp)
- npm · `@kansei-link/mcp-server`: 34/100, [markdown](https://verifymcp.io/servers/kansei-link-kansei-mcp-server/kansei-link-mcp-server.md), [page](https://verifymcp.io/servers/kansei-link-kansei-mcp-server/kansei-link-mcp-server)

## Channel facts

- Endpoint: `https://mcp.kansei-link.com/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.3.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-05.

- **Endpoint Security**: 80/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 77/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 3596 tokens (~143/item across 25 items; 3 tools + 22 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 43/100
  - Stability observed for 13 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 3 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 5 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the io.github.kansei-link/kansei-mcp-server server?

io.github.kansei-link/kansei-mcp-server is a hosted endpoint at https://mcp.kansei-link.com/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

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

### Cursor

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

### VS Code

```json
{
  "servers": {
    "kansei-link-kansei-mcp-server": {
      "type": "http",
      "url": "https://mcp.kansei-link.com/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.kansei-link-kansei-mcp-server]
url = "https://mcp.kansei-link.com/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "kansei-link-kansei-mcp-server": {
      "type": "remote",
      "url": "https://mcp.kansei-link.com/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add kansei-link-kansei-mcp-server --url 'https://mcp.kansei-link.com/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  kansei-link-kansei-mcp-server:
    url: "https://mcp.kansei-link.com/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "kansei-link-kansei-mcp-server": {
      "Transport": "http",
      "Url": "https://mcp.kansei-link.com/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add kansei-link-kansei-mcp-server -t streamable-http -u 'https://mcp.kansei-link.com/mcp'
```

### Other

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

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-05 (score 80, +1)

No change was recorded against any check on this day. Stability & Change Management went from 40 to 43. That category is still filling its 30-day observation window: 12 days of observed history at the previous scan, 13 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-03 (score 79, 0)

- [cosmetic] “report” reworded the description of “note”

### 2026-11-02 (score 79, +1)

No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-31 (score 78, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-29 (score 77, +1)

No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-27 (score 76, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-25 (score 75, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-24 (score 74, 0)

- [functional improvement] Stability: unverified → 0.03

## MCP tools (3)

### `search_services` (~309 tokens)

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.

Input parameters:

- `agent_ready` (string): Filter by agent readiness: 'verified' (🟢 battle-tested, success rate ≥80%), 'connectable' (🟡 API/MCP exists but unproven), 'info_only' (⚪ no API). Omit for all.
- `category` (string): Filter by category: crm, project_management, communication, accounting, hr, ecommerce, legal, marketing, groupware, productivity, storage, support, payment, logistics, reservation, data_integration,…
- `compact` (boolean): Return minimal fields for token efficiency. Default: false
- `intent` (string, required): What you want to accomplish (e.g., 'send invoice', 'manage employees', 'track attendance')
- `limit` (number): Max results to return (default: 5)

### `lookup` (~513 tokens)

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.

Input parameters:

- `compare_with` (string): Competitor service_id for comparison — triggers history mode
- `detail` (boolean): Get full connection guide (auth, endpoints, rate limits)
- `error` (string): [ask] The error message you received (secrets are masked before anything is stored; send the message, not the whole trace).
- `feedback_limit` (number): [feedback] Max results (default 20)
- `feedback_status` (string): [feedback] Filter by status. Triggers feedback mode when present.
- `feedback_type` (string): [feedback] Filter by feedback type
- `goal` (string): Workflow goal — triggers recipe mode (e.g., 'onboard employee')
- `insights` (boolean): Get aggregated usage data (success rate, trends, errors)
- `mode` (string): Explicit mode override
- `note_scope` (string): [notes] Defaults to field. verification isolates internal release checks from ordinary discovery; not a privacy boundary.
- `period` (string): Time period — triggers history mode
- `q` (string): [notes] Symptom or task keywords; omit to see recent notes for this service.
- `runtime` (string): [ask] Your runtime family (claude/codex/gpt/gemini/other).
- `service` (string): Fuzzy service name — triggers combinations mode
- `service_id` (string): Service ID (from search_services)
- `services` (array): Your available service IDs — for recipe coverage calculation
- `voice_agent_type` (string): [voices] Filter by agent type (claude, gpt, gemini)
- `voice_question_filter` (string): [voices] Filter by question_id

### `report` (~1306 tokens)

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.

Input parameters:

- `agent_id` (string): Your agent identifier (optional, for follow-up). Used in feedback and voice modes.
- `agent_type` (string): Agent platform type (claude, gpt, gemini, copilot, llama, deepseek, other). Used in outcome mode (auto-inferred from model_name if omitted) and voice mode.
- `attempt_id` (string): [outcome] attempt_id returned by lookup.
- `body` (string): [feedback] Your feedback in detail. Write freely.
- `confidence` (string): [voice] How confident are you in this assessment? high, medium, low.
- `context` (string): [outcome] Additional context about the usage (PII will be auto-masked).
- `cost_usd` (number): [outcome] Actual cost in USD (estimated from tokens if omitted).
- `description` (string): [event] Details about the event and expected impact.
- `error_type` (string): [outcome] Error category if failed (e.g., 'auth_error', 'timeout', 'rate_limit', 'schema_mismatch').
- `estimated_users` (number): [outcome] Approximate number of end-users your agent serves.
- `event_date` (string): [event] When the event occurred or takes effect (YYYY-MM-DD).
- `event_type` (string): [event] Category: api_change, api_deprecation, law_amendment, pricing_change, outage, security_incident, feature_launch, competitor_move, mcp_update, other.
- `failed_step` (string): [outcome] Step identifier where execution stopped.
- `feedback_type` (string): [feedback] Type of feedback: suggestion, missing_data, correction, feature_request, workaround_tip, bug_report, praise, other.
- `impact_expected` (string): [event] Expected impact: positive, negative, neutral, unknown.
- `input_tokens` (integer): [outcome] Input/prompt token count.
- `is_retry` (boolean): [outcome] Whether this is a retry of a previously failed call.
- `latency_ms` (number): [outcome] Response time in milliseconds.
- `mode` (string): Explicit mode selection. Auto-detected from params if omitted: success → outcome, question_id → voice, event_type → event, subject+body → feedback.
- `model_name` (string): [outcome] LLM model used (e.g., 'claude-sonnet-4', 'gpt-4o').
- `note` (object): [note] Authorized summary to share in this server's field-note store. Use a fresh session UUID per execution and stable request UUID for retries. Optional read_note_ids: up to 5 ids of existing notes…
- `note_id`: [outcome] Field-note ID this report belongs to (format AWT-000). Stored as null if the format does not match.
- `note_result` (object): [note_result] Actual result of trying a note. Includes note_id, service_id, outcome, conditions and evidence.
- `output_tokens` (integer): [outcome] Output/completion token count.
- `priority` (string): [feedback] How important: low, normal, high, critical. Default: normal.
- `provider_error_code`: [outcome] Provider's error code string (e.g. expired_access_token) or an RFC 9457 problem type URI (https://…, max 200 chars). Stored as null if the format does not match.
- `provider_request_id`: [outcome] Request or error ID the provider returned (e.g. from an x-request-id header). If present and well-formed, the record becomes traceable in the provider's own logs. Stored as null if the form…
- `provider_request_id_source`: [outcome] Where the provider request ID came from: 'header:<name>' (e.g. header:x-request-id) or 'body:<field>' (e.g. body:id).
- `question_id` (string): [voice] Which question to answer: selection_criteria, would_recommend, biggest_frustration, best_feature, switching_likelihood, auth_experience, doc_quality, error_handling, compared_to_competitor, m…
- `recipe_id` (string): [outcome] Recipe used for this attempt.
- `recipe_version` (integer): [outcome] Recipe version returned by lookup.
- `response_choice` (string): [voice] Quick rating where applicable (e.g., 'strongly_yes', 'excellent', 'ready').
- `response_text` (string): [voice] Your honest answer in your own words.
- `service_id` (string): Service ID. Required for outcome and voice modes. Optional for feedback and event.
- `session_id`: [outcome] Optional. A UUID you generate once and reuse for every report during one task, so reports from the same task count as one agent (only a salted hash is stored, never this value). Anything th…
- `subject` (string): [feedback] Short summary of your feedback (1 line).
- `success` (boolean): [outcome] Whether the operation succeeded.
- `task_type` (string): [outcome] Operation performed (e.g., 'create_invoice', 'search_contacts').
- `title` (string): [event] Short event title (e.g., 'freee API v3 deprecation').
- `workaround` (string): [outcome] How you resolved the issue, if any. Helps future agents.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/kansei-link-kansei-mcp-server/mcp#diagnostics

## Score history

- 2026-11-05: 80
- 2026-11-04: 79
- 2026-11-03: 79
- 2026-11-02: 79
- 2026-11-01: 78
- 2026-10-31: 78
- 2026-10-30: 77
- 2026-10-29: 77
- 2026-10-28: 76
- 2026-10-27: 76
- 2026-10-26: 75
- 2026-10-25: 75
- 2026-10-24: 74
- 2026-10-23: 74

## Common questions

### What is the io.github.kansei-link/kansei-mcp-server server?

io.github.kansei-link/kansei-mcp-server is listed in the public MCP registry as io.github.kansei-link/kansei-mcp-server. Reduce your AI agent's token waste with collective intelligence, SaaS integration recipes. This page covers its hosted endpoint (https://mcp.kansei-link.com/mcp).

### Is the io.github.kansei-link/kansei-mcp-server server safe to use?

io.github.kansei-link/kansei-mcp-server scores 80 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the io.github.kansei-link/kansei-mcp-server server expose?

io.github.kansei-link/kansei-mcp-server exposes 3 tools: search_services, lookup, report. Their descriptions and schemas cost roughly 2,128 tokens of context every time the server is loaded.

### Does the io.github.kansei-link/kansei-mcp-server server require authentication?

No. We connected to io.github.kansei-link/kansei-mcp-server without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the io.github.kansei-link/kansei-mcp-server server still maintained?

io.github.kansei-link/kansei-mcp-server is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://mcp.kansei-link.com/mcp
- Repository: https://github.com/kansei-link/kansei-mcp-server
- Changelog RSS feed: https://verifymcp.io/servers/kansei-link-kansei-mcp-server/mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/kansei-link-kansei-mcp-server/mcp.json
- HTML version of this page: https://verifymcp.io/servers/kansei-link-kansei-mcp-server/mcp