Server definition

Hash: sha256:e03ea868bca905be57b7179b2ee1d6f64c855e7958fcf370a45cacb37256288f
What it is: What a remote MCP server returned when asked what it offers: 3 tools

The blob, as servednamed by its sha256

{
  "instructions": "## KanseiLink — SaaS Integration Intelligence\n\nYou have access to KanseiLink, a continuously-updated database of SaaS integration intelligence — built from connection-method checks, the official MCP registry, curated integration guides, and a growing pool of agent reports.\n\n### WHEN TO USE\nCall `search_services` BEFORE attempting any SaaS API integration.\nYour training data for SaaS APIs is likely 6-12 months old — endpoints change, auth flows break, rate limits shift.\nKanseiLink has current, structured integration data that saves 3-5x tokens vs trial-and-error.\n\n### TRIGGERS — call search_services when:\n- The user mentions ANY SaaS service (freee, SmartHR, kintone, Slack, Notion, Salesforce, Stripe...)\n- The user asks to integrate, connect, or automate a business process involving SaaS\n- You are about to write API integration code\n- The user says 'use kanseilink'\n\n### STANDARD FLOW (3 tools — that's all you need)\n1. `search_services` → find the right service (use `compact: true` to save tokens)\n2. `lookup` → get tips, detail, insights, recipes, history (auto-detects from params)\n3. `report` → after using a service, report success/failure (5 seconds; stored locally, improves this installation's recovery hints and stats)\n\n### ADMIN TOOLS (2 additional — for operators and scout agents)\n- `inspect` → colony health: inspection queue, submit findings, propose/review updates, snapshots, design evaluation\n- `analyze` → analytics: token savings, cost audit, AEO reports and articles\n\n### LOOKUP MODES (all via the `lookup` tool)\n- `lookup({ service_id })` → tips (auth, pitfalls, workarounds) — DEFAULT\n- `lookup({ service_id, detail: true })` → full connection guide\n- `lookup({ service_id, insights: true })` → usage analytics\n- `lookup({ goal: 'workflow description' })` → multi-service recipes\n- `lookup({ service_id, period: '30d' })` → time-series history\n- `lookup({ service: 'name' })` → find service combinations\n- `lookup({ feedback_status: 'open' })` → read community feedback\n- `lookup({ mode: 'voices', service_id })` → read agent opinions\n\n### REPORT MODES (all via the `report` tool)\n- `report({ success: true/false, service_id })` → outcome\n- `report({ subject: '...', body: '...' })` → feedback\n- `report({ event_type: '...', event_date: '...', title: '...' })` → event\n- `report({ question_id: '...', response_text: '...', service_id })` → voice\n\n### MIGRATION from v0.x\nOld tool names are removed. Use: get_service_tips → lookup, get_service_detail → lookup({ detail: true }),\nget_insights → lookup({ insights: true }), get_recipe → lookup({ goal }),\nfind_combinations → lookup({ service }), get_service_history → lookup({ period }),\nreport_outcome → report({ success }), submit_feedback → report({ subject, body }),\nrecord_event → report({ event_type }), agent_voice → report({ question_id }),\nread_feedback → lookup({ feedback_status }), read_agent_voices → lookup({ mode: 'voices' }).\n\n### WHEN NOT TO USE\n- Pure code questions with no SaaS involvement\n- The user is asking about KanseiLink itself (you already know)\n- You already called search_services for the same service in this conversation",
  "tools": [
    {
      "description": "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.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "additionalProperties": false,
        "properties": {
          "compare_with": {
            "description": "Competitor service_id for comparison — triggers history mode",
            "type": "string"
          },
          "detail": {
            "description": "Get full connection guide (auth, endpoints, rate limits)",
            "type": "boolean"
          },
          "feedback_limit": {
            "description": "[feedback] Max results (default 20)",
            "type": "number"
          },
          "feedback_status": {
            "description": "[feedback] Filter by status. Triggers feedback mode when present.",
            "enum": [
              "open",
              "acknowledged",
              "resolved",
              "all"
            ],
            "type": "string"
          },
          "feedback_type": {
            "description": "[feedback] Filter by feedback type",
            "type": "string"
          },
          "goal": {
            "description": "Workflow goal — triggers recipe mode (e.g., 'onboard employee')",
            "type": "string"
          },
          "insights": {
            "description": "Get aggregated usage data (success rate, trends, errors)",
            "type": "boolean"
          },
          "mode": {
            "description": "Explicit mode override",
            "enum": [
              "tips",
              "detail",
              "insights",
              "recipe",
              "combinations",
              "history",
              "feedback",
              "voices"
            ],
            "type": "string"
          },
          "period": {
            "description": "Time period — triggers history mode",
            "enum": [
              "7d",
              "30d",
              "90d",
              "all"
            ],
            "type": "string"
          },
          "service": {
            "description": "Fuzzy service name — triggers combinations mode",
            "type": "string"
          },
          "service_id": {
            "description": "Service ID (from search_services)",
            "type": "string"
          },
          "services": {
            "description": "Your available service IDs — for recipe coverage calculation",
            "items": {
              "type": "string"
            },
            "type": "array"
          },
          "voice_agent_type": {
            "description": "[voices] Filter by agent type (claude, gpt, gemini)",
            "type": "string"
          },
          "voice_question_filter": {
            "description": "[voices] Filter by question_id",
            "type": "string"
          }
        },
        "type": "object"
      },
      "name": "lookup",
      "outputSchema": null
    },
    {
      "description": "Record 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. This is step 4 of the standard flow: search_services → lookup → (execute) → report.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "additionalProperties": false,
        "properties": {
          "agent_id": {
            "description": "Your agent identifier (optional, for follow-up). Used in feedback and voice modes.",
            "type": "string"
          },
          "agent_type": {
            "description": "Agent platform type (claude, gpt, gemini, copilot, llama, deepseek, other). Used in outcome mode (auto-inferred from model_name if omitted) and voice mode.",
            "type": "string"
          },
          "attempt_id": {
            "description": "[outcome] attempt_id returned by lookup.",
            "format": "uuid",
            "type": "string"
          },
          "body": {
            "description": "[feedback] Your feedback in detail. Write freely.",
            "type": "string"
          },
          "confidence": {
            "description": "[voice] How confident are you in this assessment? high, medium, low.",
            "type": "string"
          },
          "context": {
            "description": "[outcome] Additional context about the usage (PII will be auto-masked).",
            "type": "string"
          },
          "cost_usd": {
            "description": "[outcome] Actual cost in USD (estimated from tokens if omitted).",
            "type": "number"
          },
          "description": {
            "description": "[event] Details about the event and expected impact.",
            "type": "string"
          },
          "error_type": {
            "description": "[outcome] Error category if failed (e.g., 'auth_error', 'timeout', 'rate_limit', 'schema_mismatch').",
            "type": "string"
          },
          "estimated_users": {
            "description": "[outcome] Approximate number of end-users your agent serves.",
            "type": "number"
          },
          "event_date": {
            "description": "[event] When the event occurred or takes effect (YYYY-MM-DD).",
            "type": "string"
          },
          "event_type": {
            "description": "[event] Category: api_change, api_deprecation, law_amendment, pricing_change, outage, security_incident, feature_launch, competitor_move, mcp_update, other.",
            "type": "string"
          },
          "failed_step": {
            "description": "[outcome] Step identifier where execution stopped.",
            "maxLength": 200,
            "type": "string"
          },
          "feedback_type": {
            "description": "[feedback] Type of feedback: suggestion, missing_data, correction, feature_request, workaround_tip, bug_report, praise, other.",
            "type": "string"
          },
          "impact_expected": {
            "description": "[event] Expected impact: positive, negative, neutral, unknown.",
            "type": "string"
          },
          "input_tokens": {
            "description": "[outcome] Input/prompt token count.",
            "type": "integer"
          },
          "is_retry": {
            "description": "[outcome] Whether this is a retry of a previously failed call.",
            "type": "boolean"
          },
          "latency_ms": {
            "description": "[outcome] Response time in milliseconds.",
            "type": "number"
          },
          "mode": {
            "description": "Explicit mode selection. Auto-detected from params if omitted: success → outcome, question_id → voice, event_type → event, subject+body → feedback.",
            "enum": [
              "outcome",
              "feedback",
              "event",
              "voice"
            ],
            "type": "string"
          },
          "model_name": {
            "description": "[outcome] LLM model used (e.g., 'claude-sonnet-4', 'gpt-4o').",
            "type": "string"
          },
          "output_tokens": {
            "description": "[outcome] Output/completion token count.",
            "type": "integer"
          },
          "priority": {
            "description": "[feedback] How important: low, normal, high, critical. Default: normal.",
            "type": "string"
          },
          "question_id": {
            "description": "[voice] Which question to answer: selection_criteria, would_recommend, biggest_frustration, best_feature, switching_likelihood, auth_experience, doc_quality, error_handling, compared_to_competitor, mcp_readiness, free_voice.",
            "type": "string"
          },
          "recipe_id": {
            "description": "[outcome] Recipe used for this attempt.",
            "type": "string"
          },
          "recipe_version": {
            "description": "[outcome] Recipe version returned by lookup.",
            "exclusiveMinimum": 0,
            "type": "integer"
          },
          "response_choice": {
            "description": "[voice] Quick rating where applicable (e.g., 'strongly_yes', 'excellent', 'ready').",
            "type": "string"
          },
          "response_text": {
            "description": "[voice] Your honest answer in your own words.",
            "type": "string"
          },
          "service_id": {
            "description": "Service ID. Required for outcome and voice modes. Optional for feedback and event.",
            "type": "string"
          },
          "subject": {
            "description": "[feedback] Short summary of your feedback (1 line).",
            "type": "string"
          },
          "success": {
            "description": "[outcome] Whether the operation succeeded.",
            "type": "boolean"
          },
          "task_type": {
            "description": "[outcome] Operation performed (e.g., 'create_invoice', 'search_contacts').",
            "type": "string"
          },
          "title": {
            "description": "[event] Short event title (e.g., 'freee API v3 deprecation').",
            "type": "string"
          },
          "workaround": {
            "description": "[outcome] How you resolved the issue, if any. Helps future agents.",
            "type": "string"
          }
        },
        "type": "object"
      },
      "name": "report",
      "outputSchema": null
    },
    {
      "description": "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.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "additionalProperties": false,
        "properties": {
          "agent_ready": {
            "description": "Filter by agent readiness: 'verified' (🟢 battle-tested, success rate ≥80%), 'connectable' (🟡 API/MCP exists but unproven), 'info_only' (⚪ no API). Omit for all.",
            "enum": [
              "verified",
              "connectable",
              "info_only"
            ],
            "type": "string"
          },
          "category": {
            "description": "Filter by category: crm, project_management, communication, accounting, hr, ecommerce, legal, marketing, groupware, productivity, storage, support, payment, logistics, reservation, data_integration, bi_analytics, security, developer_tools, ai_ml, database, devops, design",
            "type": "string"
          },
          "compact": {
            "description": "Return minimal fields for token efficiency. Default: false",
            "type": "boolean"
          },
          "intent": {
            "description": "What you want to accomplish (e.g., 'send invoice', 'manage employees', 'track attendance')",
            "type": "string"
          },
          "limit": {
            "default": 5,
            "description": "Max results to return (default: 5)",
            "type": "number"
          }
        },
        "required": [
          "intent"
        ],
        "type": "object"
      },
      "name": "search_services",
      "outputSchema": null
    }
  ]
}

Verify it yourself

curl -s https://api.teppi.xyz/v1/evidence/sha256:e03ea868bca905be57b7179b2ee1d6f64c855e7958fcf370a45cacb37256288f | sha256sum