Search / io.github.kansei-link/kansei-mcp-server
kansei-mcp-server
R0· no sign-inReduce your AI agent's token waste with collective intelligence — SaaS integration recipes
v1.2.4 · active · repository · descriptor JSON · versions
Search / io.github.kansei-link/kansei-mcp-server
R0· no sign-inReduce your AI agent's token waste with collective intelligence — SaaS integration recipes
v1.2.4 · active · repository · descriptor JSON · versions
{
"mcpServers": {
"kansei-mcp-server": {
"type": "http",
"url": "https://kansei-link-mcp-production.up.railway.app/mcp"
}
}
}claude mcp add --transport http kansei-mcp-server https://kansei-link-mcp-production.up.railway.app/mcp[mcp_servers.kansei-mcp-server]
url = "https://kansei-link-mcp-production.up.railway.app/mcp"
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"kansei-mcp-server": {
"type": "remote",
"url": "https://kansei-link-mcp-production.up.railway.app/mcp",
"enabled": true
}
}
}{
"mcpServers": {
"kansei-mcp-server": {
"type": "http",
"url": "https://kansei-link-mcp-production.up.railway.app/mcp"
}
},
"deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=kansei-mcp-server&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8va2Fuc2VpLWxpbmstbWNwLXByb2R1Y3Rpb24udXAucmFpbHdheS5hcHAvbWNwIn0%3D"
}{
"servers": {
"kansei-mcp-server": {
"type": "http",
"url": "https://kansei-link-mcp-production.up.railway.app/mcp"
}
}
}{
"mcpServers": {
"kansei-mcp-server": {
"httpUrl": "https://kansei-link-mcp-production.up.railway.app/mcp"
}
}
}extensions:
"kansei-mcp-server":
enabled: true
name: "kansei-mcp-server"
type: streamable_http
uri: "https://kansei-link-mcp-production.up.railway.app/mcp"
timeout: 300
protocol.modernnewest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28protocol.statelessonly applies to 2026-07-28 serversprotocol.transportstreamable HTTPprotocol.list_ttlonly applies to 2026-07-28 serversauth.prm, auth.as_metadata, auth.cimdno remote uses OAuthauth.secret_in_urlno templated URLtools.descriptionsevery tool has a descriptiontools.description_lengthdescriptions are concisetools.schemasevery tool has an object input schematools.annotations3 of 3 tools declare readOnlyHint or destructiveHinttools.directory_hints2 of 3 tools declare all four hints; missing: search_services (idempotentHint)tools.token_costabout 3,019 tokens to load every tooltools.api_dumptools are not a one-to-one API dumpstability.changes5 tool changes in 30 daysstability.rug_pull1 tools kept their name but changed most of their description in 30 days; review before trusting themdeps.known_vulns1 advisory of lower severity or without a published fix: GHSA-p7fg-763f-g4gf in @anthropic-ai/[email protected] (direct, fixed in 0.91.1)deps.mcp_sdk_version@modelcontextprotocol/sdk 1.32.1, no known advisorydeps.resolvable@kansei-link/[email protected] resolved: 142 packagesreportchangeddescription, input schemameaning changedRecord what happened after using a service: success/failure outcome, feedback, API change events, or qualitative experience. Data is saved to this installation's LOCAL database only (improves local recovery hints and stats) — nothing is sent to KanseiLink unless you separately opt in to sharing. PII is auto-masked before storage. If the provider returned a request ID, including it as provider_request_id makes the record traceable in the provider's own logs. This is step 4 of the standard flow: search_services → lookup → (execute) → 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.
lookupchangeddescription, input schemaGet everything you need about a service before using it. Default: tips (auth setup, pitfalls, workarounds). 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. Each call records one attempt handle (attempt_id) and clears attempt handles older than 90 days.
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. 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.
reportchangedannotationslookupchangeddescription, annotationsGet everything you need about a service before using it. Default: tips (auth setup, pitfalls, workarounds). 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.
Get everything you need about a service before using it. Default: tips (auth setup, pitfalls, workarounds). 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. Each call records one attempt handle (attempt_id) and clears attempt handles older than 90 days.
search_serviceschangedannotationsFull history: list_changes · trend: quality JSON.
Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. How it is computed.
+repository +namespace-matches-repo +reachable +uptime-100% +updated-5d-ago
Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed. How it is computed.
@kansei-link/[email protected] npm141 dependencies, resolved · MCP SDK @modelcontextprotocol/sdk 1.32.1 · advisories checked 2026-10-20
| advisory | severity | package | fixed in |
|---|---|---|---|
| GHSA-p7fg-763f-g4gfClaude SDK for TypeScript has Insecure Default File Permissions in Local Filesystem Memory Tool | moderate | @anthropic-ai/[email protected]direct | fixed in 0.91.1 |
Dependency graphs from deps.dev; advisories from OSV.dev, including the GitHub Advisory Database and the PyPI Advisory Database; all CC BY 4.0. The graph is what a clean install of this version resolves today; nothing was installed or run. How it is checked.
| remote | auth | reachable | uptime 30d | p50 | protocol | last ok |
|---|---|---|---|---|---|---|
https://kansei-link-mcp-production.up.railway.app/mcp streamable-http | none | yes | 100% | 4328 ms | 2025-11-25 | 2026-10-20 |
| package | registry | version | runtime | secrets |
|---|---|---|---|---|
@kansei-link/mcp-server | npm | 1.2.4 | – |
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. 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. |
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. |
search_servicesread-only | 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. |
Schemas: list_tools.
{
"name": "io.github.kansei-link/kansei-mcp-server",
"$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
"remotes": [
{
"url": "https://kansei-link-mcp-production.up.railway.app/mcp",
"type": "streamable-http"
}
],
"version": "1.2.4",
"packages": [
{
"version": "1.2.4",
"transport": {
"type": "stdio"
},
"identifier": "@kansei-link/mcp-server",
"registryType": "npm"
}
],
"repository": {
"url": "https://github.com/kansei-link/kansei-mcp-server",
"source": "github"
},
"description": "Reduce your AI agent's token waste with collective intelligence — SaaS integration recipes"
}