Skip to main content
Glama

Server Details

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

Status
Healthy
Last Tested
Transport
Streamable HTTP
URL
Repository
kansei-link/kansei-mcp-server
GitHub Stars
1
Server Listing
KanseiLink MCP Server

Glama MCP Gateway

Connect through Glama MCP Gateway for full control over tool access and complete visibility into every call.

MCP client
Glama
MCP server

Full call logging

Every tool call is logged with complete inputs and outputs, so you can debug issues and audit what your agents are doing.

Tool access control

Enable or disable individual tools per connector, so you decide what your agents can and cannot do.

Managed credentials

Glama handles OAuth flows, token storage, and automatic rotation, so credentials never expire on your clients.

Usage analytics

See which tools your agents call, how often, and when, so you can understand usage patterns and catch anomalies.

100% free. Your data is private.
Tool DescriptionsA

Average 4.5/5 across 3 of 3 tools scored.

Server CoherenceA
Disambiguation5/5

Each tool has a clearly distinct purpose: search_services finds services, lookup retrieves details, and report submits feedback. No overlap or ambiguity.

Naming Consistency4/5

All tools are verb-based (search_services, lookup, report), but the structure is not fully uniform: search_services uses verb_noun with underscore, while lookup and report are single verbs without underscores.

Tool Count5/5

With only 3 tools, the server is tightly scoped for its purpose of providing service discovery, lookup, and feedback—a balanced and focused set.

Completeness3/5

The tools cover search, detail lookup, and reporting, but the documented flow includes an 'execute' step with no corresponding tool, leaving a notable gap for agents that may need to perform the actual integration.

Available Tools

3 tools
lookupLookupA
Read-only
Inspect

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.

ParametersJSON Schema
NameRequiredDescriptionDefault
goalNoWorkflow goal — triggers recipe mode (e.g., 'onboard employee')
modeNoExplicit mode override
detailNoGet full connection guide (auth, endpoints, rate limits)
periodNoTime period — triggers history mode
serviceNoFuzzy service name — triggers combinations mode
insightsNoGet aggregated usage data (success rate, trends, errors)
servicesNoYour available service IDs — for recipe coverage calculation
service_idNoService ID (from search_services)
compare_withNoCompetitor service_id for comparison — triggers history mode
feedback_typeNo[feedback] Filter by feedback type
feedback_limitNo[feedback] Max results (default 20)
feedback_statusNo[feedback] Filter by status. Triggers feedback mode when present.
voice_agent_typeNo[voices] Filter by agent type (claude, gpt, gemini)
voice_question_filterNo[voices] Filter by question_id
Behavior4/5

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

The annotations already declare readOnlyHint=true, establishing read-only nature. The description reinforces this by focusing on retrieving information. It adds context on default tips and specific parameter behaviors (detail, insights, goal) without contradicting annotations. Minor gap: no mention of rate limits or result format.

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

Conciseness5/5

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

The description is four sentences long, each serving a clear purpose: purpose statement, default behavior, advanced parameter use, and flow positioning. It is front-loaded with the most critical information and contains no superfluous words.

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

Completeness3/5

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

Given 14 parameters and no output schema, the description covers core usage (tips, detail, insights, goal) but omits details on parameters like period, compare_with, service, feedback, and voices. The return format is not described, leaving some gaps. However, the annotations compensate for behavioral safety.

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?

With 100% schema coverage, baseline is 3. The description adds narrative context explaining how parameters like detail, insights, and goal modify behavior (e.g., 'Add detail: true for full connection guide'). This goes beyond schema descriptions by tying parameters to usage scenarios, though not all 14 parameters are explicitly covered.

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?

The description clearly states the tool's purpose as 'Get everything you need about a service before using it', using a specific verb and resource. It distinguishes itself from siblings like search_services (step 1) and execute/report by positioning itself as step 2 in the KanseiLink flow, making the role unambiguous.

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

Usage Guidelines4/5

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

The description provides context on when to use (before using a service) and how it fits in the flow. It explains default behavior and parameter effects (detail, insights, goal). However, it does not explicitly state when not to use it or list alternatives, which slightly reduces clarity.

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

reportReportAInspect

Contribute data back to the KanseiLink community. Report success/failure after using a service (5 seconds, helps everyone), submit feedback, record API change events, or share your qualitative experience. PII is auto-masked. This is step 4 of the standard flow: search_services → lookup → (execute) → report.

ParametersJSON Schema
NameRequiredDescriptionDefault
bodyNo[feedback] Your feedback in detail. Write freely.
modeNoExplicit mode selection. Auto-detected from params if omitted: success → outcome, question_id → voice, event_type → event, subject+body → feedback.
titleNo[event] Short event title (e.g., 'freee API v3 deprecation').
contextNo[outcome] Additional context about the usage (PII will be auto-masked).
subjectNo[feedback] Short summary of your feedback (1 line).
successNo[outcome] Whether the operation succeeded.
agent_idNoYour agent identifier (optional, for follow-up). Used in feedback and voice modes.
cost_usdNo[outcome] Actual cost in USD (estimated from tokens if omitted).
is_retryNo[outcome] Whether this is a retry of a previously failed call.
priorityNo[feedback] How important: low, normal, high, critical. Default: normal.
task_typeNo[outcome] Operation performed (e.g., 'create_invoice', 'search_contacts').
agent_typeNoAgent platform type (claude, gpt, gemini, copilot, llama, deepseek, other). Used in outcome mode (auto-inferred from model_name if omitted) and voice mode.
confidenceNo[voice] How confident are you in this assessment? high, medium, low.
error_typeNo[outcome] Error category if failed (e.g., 'auth_error', 'timeout', 'rate_limit', 'schema_mismatch').
event_dateNo[event] When the event occurred or takes effect (YYYY-MM-DD).
event_typeNo[event] Category: api_change, api_deprecation, law_amendment, pricing_change, outage, security_incident, feature_launch, competitor_move, mcp_update, other.
latency_msNo[outcome] Response time in milliseconds.
model_nameNo[outcome] LLM model used (e.g., 'claude-sonnet-4', 'gpt-4o').
service_idNoService ID. Required for outcome and voice modes. Optional for feedback and event.
workaroundNo[outcome] How you resolved the issue, if any. Helps future agents.
descriptionNo[event] Details about the event and expected impact.
question_idNo[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.
input_tokensNo[outcome] Input/prompt token count.
feedback_typeNo[feedback] Type of feedback: suggestion, missing_data, correction, feature_request, workaround_tip, bug_report, praise, other.
output_tokensNo[outcome] Output/completion token count.
response_textNo[voice] Your honest answer in your own words.
estimated_usersNo[outcome] Approximate number of end-users your agent serves.
impact_expectedNo[event] Expected impact: positive, negative, neutral, unknown.
response_choiceNo[voice] Quick rating where applicable (e.g., 'strongly_yes', 'excellent', 'ready').
Behavior4/5

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

Annotations indicate the tool is neither read-only nor idempotent. The description adds value by specifying that 'PII is auto-masked' and detailing the side effects of submitting data. Since annotations are minimal (only two booleans), the description adequately carries the behavioral transparency burden.

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

Conciseness5/5

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

The description is two sentences plus a phrase, front-loading the main purpose and providing essential context. Every sentence is informative and there is no redundancy.

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

Completeness5/5

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

Despite 29 parameters and no output schema, the description covers the tool's role in the workflow, explains mode selection, mentions PII handling, and references related tools. This is sufficient for an agent to decide when and how to invoke the tool.

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?

The input schema provides 100% coverage with descriptions for all 29 parameters. The description adds context by grouping parameters by mode (e.g., '[outcome]', '[event]') and explaining auto-detection logic, which helps agents understand how to construct requests.

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?

The description clearly states the tool's purpose: 'Contribute data back to the KanseiLink community' and lists specific actions (report success/failure, submit feedback, record events, share experience). It distinguishes from sibling tools like search_services, which focus on retrieving data.

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?

The description explicitly places the tool as 'step 4 of the standard flow: search_services → lookup → (execute) → report', providing clear context for when to use it. It also explains auto-detection of modes and outlines prerequisites for different report types.

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

search_servicesSearch ServicesA
Read-only
Inspect

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.

ParametersJSON Schema
NameRequiredDescriptionDefault
limitNoMax results to return (default: 5)
intentYesWhat you want to accomplish (e.g., 'send invoice', 'manage employees', 'track attendance')
compactNoReturn minimal fields for token efficiency. Default: false
categoryNoFilter 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
agent_readyNoFilter by agent readiness: 'verified' (🟢 battle-tested, success rate ≥80%), 'connectable' (🟡 API/MCP exists but unproven), 'info_only' (⚪ no API). Omit for all.
Behavior5/5

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

Annotations declare readOnlyHint=true; description adds context like token savings, coverage of 900+ services, and agent-readiness signals beyond what annotations provide. No contradiction.

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?

Three sentences packed with value: imperative call to action, reasoning, and scope. Slightly verbose but each sentence earns its place.

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?

Given 5 parameters, 1 enum, no output schema, the description covers usage context, scope, and motivation adequately. Explains return value as 'structured evaluations' enough for agent.

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

Parameters3/5

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

Schema coverage is 100% with good descriptions; description doesn't add much beyond schema, but provides high-level context (e.g., Japanese SaaS strength) that aids parameter selection. Baseline 3 is appropriate.

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?

Clear verb+resource: 'search services' returns structured evaluations. Distinguishes from siblings 'lookup' and 'report' by focusing on SaaS integration guidance.

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?

Explicitly instructs to call before any SaaS API integration, provides examples (freee, Slack, etc.) and warns against trial-and-error. Comprehensive guidance.

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

Discussions

No comments yet. Be the first to start the discussion!

Try in Browser

Your Connectors

Sign in to create a connector for this server.