kansei-mcp-server

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.

Input Schema

Name	Required	Description
`q`	No	[notes] Symptom or task keywords; omit to see recent notes for this service.
`goal`	No	Workflow goal — triggers recipe mode (e.g., 'onboard employee')
`mode`	No	Explicit mode override
`error`	No	[ask] The error message you received (secrets are masked before anything is stored; send the message, not the whole trace).
`detail`	No	Get full connection guide (auth, endpoints, rate limits)
`period`	No	Time period — triggers history mode
`runtime`	No	[ask] Your runtime family (claude/codex/gpt/gemini/other).
`service`	No	Fuzzy service name — triggers combinations mode
`insights`	No	Get aggregated usage data (success rate, trends, errors)
`services`	No	Your available service IDs — for recipe coverage calculation
`note_scope`	No	[notes] Defaults to field. verification isolates internal release checks from ordinary discovery; not a privacy boundary.
`service_id`	No	Service ID (from search_services)
`compare_with`	No	Competitor service_id for comparison — triggers history mode
`feedback_type`	No	[feedback] Filter by feedback type
`feedback_limit`	No	[feedback] Max results (default 20)
`feedback_status`	No	[feedback] Filter by status. Triggers feedback mode when present.
`voice_agent_type`	No	[voices] Filter by agent type (claude, gpt, gemini)
`voice_question_filter`	No	[voices] Filter by question_id

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedOct 21, 2026

addedInput schema / properties / error

Added value: +{
+  "description": "[ask] The error message you received (secrets are masked before anything is stored; send the message, not the whole trace).",
+  "maxLength": 2000,
+  "type": "string"
+}

changedInput schema / properties / mode / enum

Previous value: -[
-  "tips",
-  "detail",
-  "insights",
-  "recipe",
-  "combinations",
-  "history",
-  "feedback",
-  "voices",
-  "notes"
-]New value: +[
+  "tips",
+  "detail",
+  "insights",
+  "recipe",
+  "combinations",
+  "history",
+  "feedback",
+  "voices",
+  "notes",
+  "ask"
+]

addedInput schema / properties / runtime

Added value: +{
+  "description": "[ask] Your runtime family (claude/codex/gpt/gemini/other).",
+  "maxLength": 40,
+  "type": "string"
+}

Changed3 schema fields changedOct 20, 2026

changedInput schema / properties / mode / enum

Previous value: -[
-  "tips",
-  "detail",
-  "insights",
-  "recipe",
-  "combinations",
-  "history",
-  "feedback",
-  "voices"
-]New value: +[
+  "tips",
+  "detail",
+  "insights",
+  "recipe",
+  "combinations",
+  "history",
+  "feedback",
+  "voices",
+  "notes"
+]

addedInput schema / properties / note_scope

Added value: +{
+  "description": "[notes] Defaults to field. verification isolates internal release checks from ordinary discovery; not a privacy boundary.",
+  "enum": [
+    "field",
+    "verification"
+  ],
+  "type": "string"
+}

addedInput schema / properties / q

Added value: +{
+  "description": "[notes] Symptom or task keywords; omit to see recent notes for this service.",
+  "maxLength": 120,
+  "type": "string"
+}

AddedMay 29, 2026

TDQS

A4.5/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Discloses behavior beyond annotations: each non-notes call records an attempt_id handle and clears handles older than 90 days, and secrets are masked before storage. This actually explains why readOnlyHint=false despite the tool reading data, which is valuable. It stops short of describing rate limits, latency, or failure modes for the mutation side.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loads the purpose, then mode guidance, then the flow context, all in one dense paragraph. Efficient overall, though 'nothing is published' is stated twice and the paragraph is long enough to be harder to scan than a short bulleted mode list would be.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an 18-parameter tool with no output schema, the description covers the primary flows, attempt-handle lifecycle, and secret handling well. Gaps remain: it never describes what the default tips call returns, and four modes (combinations, history, feedback, voices) are only discoverable through schema param descriptions.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description adds the default mode (tips) that the schema does not state and clarifies mode/parameter interplay (which param triggers which mode). It does not, however, explain the modes only reachable via schema (combinations, history, feedback, voices), so it is an incremental rather than complete complement.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Opens with a specific verb+resource (get everything about a service before using it) and immediately situates the tool in the flow 'search_services → lookup → (execute) → report', explicitly naming both siblings. An agent can distinguish lookup from search_services and report without opening any schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives explicit when-to-use routing: default tips mode, notes mode with service_id/q, ask mode with service_id/error, plus detail:true, insights:true, and goal for recipe mode. It also states the exclusions ('without publishing anything', 'nothing is published') and the overall flow position, so mode selection is largely prescribed rather than inferred.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All kansei-mcp-server tools Inspect

Try in Browser

Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Lookup

Input Schema

Schema Changelog

TDQS

Glama MCP Gateway

Resources