Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@finpay-mcp-server Which payment hub has the lowest success rate right now?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
An MCP (Model Context Protocol) server that exposes a fictional payment domain as tools, resources, and prompt templates. Connect Claude Desktop (or any MCP client) and reason over the FinPay platform — transactions, payment hubs, microservices, and system health.
Built with TypeScript + Node.js using the official @modelcontextprotocol/sdk.
Full MCP server implementation: 8 tools, 2 resources, 2 prompts
Production-quality TypeScript with strict type checking throughout
Tool schema design using zod — every parameter is typed and described
MCP governance: tool naming conventions, schema versioning, access control patterns
stdio transport for Claude Desktop; optional HTTP transport for remote clients
Related MCP server: GoldenGate MCP Server
Prerequisites: Node.js 22+, npm
git clone https://github.com/your-handle/finpay-mcp-server
cd finpay-mcp-server
npm install
npm run buildConnect to Claude Desktop:
Add to ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"finpay": {
"command": "node",
"args": ["/Users/ThanhNguyen/AI_WS/finpay-mcp-server/dist/index.js"]
}
}
}Restart Claude Desktop. The FinPay tools will appear in the tool panel.
Run in development mode (hot reload):
npm run devRun with HTTP transport (Streamable HTTP, stateless):
node dist/index.js --transport http --port 3100To require an API key on the HTTP transport:
MCP_API_KEY=your-secret node dist/index.js --transport http --port 3100Clients must then send Authorization: Bearer your-secret with every request.
All tools operate on in-memory fixture data — no API keys or external services required (except search_docs).
Tool | Description |
| Look up a transaction by ID ( |
| List recent transactions. Filterable by |
Tool | Description |
| Get a hub's details: status, currencies, latency, 24h success rate |
| List all hubs (GlobalPay, SwiftRoute, MobileFirst, RegionalX) |
Tool | Description |
| Describe a microservice: purpose, dependencies, dependents, health |
| List all microservices in the FinPay platform |
Tool | Description |
| Unified health snapshot: overall status, per-service health, per-hub metrics, active alerts |
| Full-text search via docu-rag API (requires |
Resources expose read-only data that the LLM can load directly into context.
URI | Content |
| JSON catalog of all services with full metadata |
| Markdown system architecture overview |
Prompt templates inject structured system context to guide LLM behaviour.
architecture-reviewLoads the full service catalog, hub list, and dependency graph. Asks the model to conduct a structured architecture review.
Optional argument: focus — area to concentrate on (e.g., resilience, scalability, security)
incident-triageLoads current system health, recent FAILED/DEGRADED transactions, and hub health metrics. Guides the model through a structured incident triage.
Optional argument: transactionId — specific transaction to investigate
Variable | Default | Description |
| — | Base URL of the docu-rag API. Enables |
|
|
|
|
| Path to the log file. Directory is created automatically on startup. |
| — | HTTP transport only. If set, all requests must include |
No API keys required for the core 7 tools. The server runs fully without any .env file.
Copy .env.example if you want to enable the optional search_docs tool:
cp .env.example .env
# Set DOCU_RAG_URL=http://localhost:8001Once connected to Claude Desktop, try:
Show me all FAILED transactions in the last hour.Which payment hub has the lowest success rate right now?Explain the dependency chain for hub-adapter-service and tell me what breaks if compliance-service goes down.Run an architecture review focused on resilience.Triage the incident for transaction TXN-100000011.Names are snake_case, verb-first for actions: get_, list_, search_, explain_
Tool names are a public API — never renamed once published
Breaking changes (removed/renamed params) require a new tool name (e.g., get_transaction_v2) and a deprecation notice before the old one is removed
This server follows semantic versioning (package.json):
Change type | Version bump |
New optional parameter or new response field | Patch (0.0.X) |
New tool, new resource, new prompt | Minor (0.X.0) |
Removed tool, removed required param, renamed tool | Major (X.0.0) only after deprecation period |
stdio transport inherits OS user permissions. It is suitable for local, trusted use only (Claude Desktop on your own machine).
HTTP transport is intended for hosted deployments. In production, all tool calls should require Authorization: Bearer <token>. The current HTTP transport implementation accepts a --api-key flag to enable simple token validation. Scope-based access control (restricting which tools a given API key can call) is documented in docs/decisions/ADR-001-transport-strategy.md and recommended for any multi-tenant deployment.
All tools in this server are read-only over mock data. In a production server with write access to real systems, each mutating tool would require an explicit capability scope.
npm run typecheck # type-check without building
npm test # run tests (vitest)
npm run lint # eslint
npm run build # compile to dist/CI runs on every push: type-check → lint → test.
src/
├── index.ts # Entry point — CLI arg parsing, transport selection
├── server.ts # McpServer setup, registers all tools/resources/prompts
├── logger.ts # File + stderr logger (writes to logs/app.log)
├── logging-transport.ts # Transport wrapper — access log per request/response cycle
├── tools/
│ ├── transactions.ts # get_transaction, list_transactions
│ ├── hubs.ts # get_payment_hub, list_payment_hubs
│ ├── services.ts # explain_service, list_services
│ ├── health.ts # get_system_health
│ └── docs.ts # search_docs (docu-rag proxy, requires DOCU_RAG_URL)
├── resources/
│ ├── services-catalog.ts # finpay://services/catalog
│ └── architecture-overview.ts # finpay://architecture/overview
├── prompts/
│ ├── architecture-review.ts
│ └── incident-triage.ts
└── data/
├── transactions.json # 20 fixture transactions
├── hubs.json # 4 fixture hubs
└── services.json # 7 fixture services
logs/ # Runtime log output (gitignored)
└── app.log
docs/decisions/ # Architecture Decision Records
tests/
└── tools/ # Unit tests for all tool modulesMIT
Get a detailed explanation of a FinPay microservice: its purpose, owning team, implementation language, upstream dependencies, downstream dependents, current health status, and port. Also returns a human-readable dependency graph description. Returns a NOT_FOUND error if the service name does not exist.
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | Service name (e.g. api-gateway, transaction-service, hub-adapter-service, compliance-service, fx-service, notification-service, audit-service) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the burden of behavioral disclosure. It clearly lists the return contents and explicitly notes that a NOT_FOUND error is returned for nonexistent service names. It does not discuss side effects or permissions, but the 'Get' verb implies a read-only operation, making this acceptable.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two concise sentences, front-loaded with the primary purpose and followed by key details and error behavior. No redundant or filler content is present.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a single-parameter tool with no output schema, the description comprehensively lists all returned data elements and the error condition. It explains the human-readable dependency graph aspect, covering the tool's scope adequately without needing to over-explain.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema already provides 100% coverage of the single 'name' parameter, including examples. The description adds the error condition tied to the parameter ('if the service name does not exist') but does not add further semantic detail beyond what the schema offers, so the baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Get a detailed explanation of a FinPay microservice' and enumerates the specific details returned (purpose, owning team, language, dependencies, health, port). This distinguishes it from sibling tools like list_services or get_system_health, which serve different purposes.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies this tool is for retrieving detailed information about a specific service, but it does not explicitly state when to use it versus other tools like list_services or get_system_health, nor does it mention any prerequisites such as confirming the service exists first.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get a payment hub's current details and health metrics. Returns hub status, supported currencies, supported countries, transfer amount limits, average latency, and 24h success rate. Returns a NOT_FOUND error if the hub ID does not exist.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | Hub ID (e.g. hub-001, hub-002, hub-003, hub-004) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It discloses what the tool returns (health metrics, supported currencies/countries, limits) and explicitly mentions the NOT_FOUND error for invalid IDs, which is useful behavioral context. It does not mention auth or rate limits, but for a simple read-only getter, this is adequate.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two concise sentences. The first sentence front-loads the purpose and return data; the second covers error behavior. Every word earns its place with no fluff or repetition.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple getter with one parameter and no output schema, the description sufficiently covers input, output, and error cases. It lists all key return fields and the error condition, making it self-contained and complete for its complexity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with a clear description and examples for the 'id' parameter. The tool description adds no extra semantic value beyond what the schema already provides; mentioning 'hub ID' in the error case is redundant. Baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb ('Get'), identifies the resource ('a payment hub'), and clearly states the scope ('current details and health metrics'). It lists the exact data returned (status, currencies, countries, limits, latency, success rate), distinguishing it from sibling tools that list hubs or transactions.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description clearly implies when to use this tool (when you need a single hub's details/health), and the error behavior indicates it's for an existing hub. However, it does not explicitly name alternatives like list_payment_hubs or state exclusions, so it falls slightly short of full guideline clarity.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get a unified health snapshot of the entire FinPay platform. Returns overall system status (HEALTHY, DEGRADED, or DOWN), per-service health, per-hub health with success rates, and any active alerts. Use this tool first when triaging incidents.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the disclosure burden. It clearly communicates a read-only operation by using 'Get' and 'Returns,' and it details the output (status, per-service, per-hub success, alerts). It does not explicitly state there are no side effects, but the nature of a health snapshot makes this evident.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences, front-loaded with the main function, and each sentence adds value: first states what it does, second explains output and usage. No wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (no params, no output schema), the description is highly complete. It covers the return structure (system status, per-service, per-hub, alerts) and provides usage context. No important aspect is missing.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has zero parameters, and the description correctly omits any parameter information. The schema is trivially 100% covered, and with no params, the description adds no parameter semantics. Baseline is 4.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses the specific verb 'Get' and clearly identifies the resource ('unified health snapshot of the entire FinPay platform'). It also enumerates the return contents, distinguishing it from sibling tools that focus on individual services or transactions.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It explicitly states 'Use this tool first when triaging incidents,' providing clear context for when to invoke it. However, it does not name alternatives or specify when not to use it, so it falls short of a 5.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Look up a single FinPay transaction by its ID. Returns the full transaction object including status, amount, currencies, exchange rate, sender/recipient names, and hub assignment. Returns a NOT_FOUND error if the ID does not exist.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | Transaction ID (format: TXN-XXXXXXXXX) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It discloses the return payload (full transaction object with specific fields) and the error behavior (NOT_FOUND if ID doesn't exist). While it doesn't explicitly state it's read-only, 'look up' implies no side effects. This is adequate for a simple get-like tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences with no fluff. The first sentence states the action and key detail (single, by ID). The second sentence adds valuable return-content and error information. Every word earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a one-parameter lookup tool with no output schema and no annotations, the description is complete: it explains the action, the required input, the return contents, and the error condition. There is no missing critical information for an agent to decide to invoke it correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema already provides 100% coverage: the only parameter 'id' has a description with format (TXN-XXXXXXXXX) and is required. The description adds no extra meaning about the parameter beyond 'by its ID', which is redundant. Baseline 3 applies because schema coverage is high and the description doesn't need to compensate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description starts with a clear verb and resource: 'Look up a single FinPay transaction by its ID.' The word 'single' and 'by its ID' distinguishes it from the sibling tool list_transactions, which presumably returns multiple transactions. It also specifies the return content (status, amount, currencies, etc.), making the purpose unambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description clearly implies the tool is for fetching a specific transaction when you already have its ID. It does not explicitly name alternatives like list_transactions for cases without an ID, but the phrasing 'by its ID' provides context and implies a precondition. No exclusions are stated, but it's enough for clear context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List all payment hubs in the FinPay platform with their current status and health metrics. Returns all 4 hubs: GlobalPay (global), SwiftRoute (SWIFT high-value), MobileFirst (mobile money), and RegionalX (Southeast Asia).
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the transparency burden. It discloses the output scope (all 4 named hubs) and that it includes status and health metrics, implying a read-only operation. It does not detail error behavior or exact metric fields, but for a parameterless list tool this is adequate.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two concise sentences that front-load the purpose and then provide useful specifics (the four hubs). No redundant language or unnecessary filler.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple no-parameter list tool with no output schema, the description is sufficiently complete. It states what is returned and even names all results. Slightly more detail on the exact health metrics would improve it, but the current description is enough for selection and invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has zero parameters and the schema is empty, so the baseline is 4. The description adds no parameter details, but none are needed; it instead explains the fixed set of hubs, which is more relevant.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool 'List all payment hubs' with 'current status and health metrics', and even enumerates the exact four hubs. This unambiguously defines the resource and verb, and distinguishes from sibling get_payment_hub which targets a single hub.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description makes it clear this is for an overview of all payment hubs, implying it should be used when a complete listing is needed. It doesn't explicitly mention alternatives like get_payment_hub, but the 'all 4 hubs' phrasing provides sufficient context for when to choose this tool.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List all 7 microservices in the FinPay platform with their metadata and current health status. Services include: api-gateway, transaction-service, hub-adapter-service, compliance-service, fx-service, notification-service, and audit-service.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the burden of disclosing behavior. It implies a read-only operation via the verb 'List' and mentions live health status, but it does not explicitly state absence of side effects, permission requirements, or error behavior. While adequate for a simple list tool, it falls short of full transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences, front-loaded with the core purpose and then listing the specific services. Every word earns its place, with no redundancy or fluff.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple zero-parameter tool with no output schema, the description is complete. It specifies the exact scope (all 7 microservices), the content (metadata and current health status), and even enumerates all service names, giving the agent full context to understand the tool's output.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has zero parameters, so the baseline is 4. The description does not need to explain parameters; it focuses on what the tool returns. It adds no parameter-related semantics because there are none to describe.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool lists all 7 microservices in the FinPay platform with metadata and current health status. It uses a specific verb ('List') and resource ('microservices'), and enumerates the exact services included, distinguishing it from siblings like list_payment_hubs.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description makes it obvious when to use this tool: to list all microservices. It provides clear context but does not explicitly mention alternatives or exclusionary conditions, such as using get_system_health for health-only queries. The naming and scope imply usage, but no direct comparison to siblings is given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List recent FinPay transactions with optional filters. Returns up to 50 transactions ordered by createdAt descending. Supports filtering by status and/or hubId. Returns an empty array if no transactions match the filters.
| Name | Required | Description | Default |
|---|---|---|---|
| hubId | No | Filter by payment hub ID (e.g. hub-001, hub-002, hub-003, hub-004). | |
| limit | No | Maximum number of records to return. Between 1 and 50. | |
| status | No | Filter by transaction status. One of: PENDING, COMPLIANCE_SCREENING, FX_LOCKED, SENT_TO_HUB, COMPLETED, FAILED, REFUNDED. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the burden. It discloses ordering (createdAt descending), result cap (up to 50), and empty-array behavior when no filters match. It does not precisely define 'recent' (time window) or mention pagination/rate limits, but these are minor for a read-only list tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Four short sentences, front-loaded with the purpose ('List recent FinPay transactions'), followed by concrete behavioral details. Every sentence contributes distinct information with no redundancy or fluff.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool is simple (3 optional params, no output schema). The description covers the main operational aspects: return type, filters, limit, ordering, and empty result. It doesn't describe the transaction object shape, but that is likely covered by get_transaction and is not essential for a list tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema already describes all three parameters with examples, enum values, and default limits (100% coverage). The description adds the 'and/or' combinability of status and hubId, and ties the limit parameter to the 50-item cap, providing semantic value beyond the schema's individual property descriptions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb ('List') and identifies the resource ('FinPay transactions'), along with scope ('recent', up to 50, filters). It clearly distinguishes from siblings like get_transaction (singular) and list_payment_hubs (different resource), making the tool's purpose unambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description conveys it is the tool for querying a set of transactions with optional status/hubId filters, and clarifies the 50-limit constraint. It does not explicitly name alternatives or state when not to use it, but the plural 'List' and filter options imply the intended use vs. singular get_transaction. Clear context but no explicit exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Full-text search over FinPay architecture documentation via the docu-rag API. Returns a synthesised answer plus the top matching document chunks. Requires the DOCU_RAG_URL environment variable to be set; returns a disabled error if it is not configured.
| Name | Required | Description | Default |
|---|---|---|---|
| topK | No | Number of document chunks to return. Between 1 and 10. | |
| query | Yes | Natural language question about the FinPay architecture, e.g. 'How does FX rate locking work?' or 'What happens when compliance rejects a transaction?' |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the disclosure burden. It discloses the dependency on DOCU_RAG_URL and the disabled error behavior, as well as the response shape (synthesised answer plus chunks). This goes beyond the schema, though it could specify rate limits or auth, but for a search tool this is sufficient.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences, front-loaded with the core purpose, then quickly covers return value and configuration. No wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (2 params, no output schema), the description covers purpose, return value, environment dependency, and error condition. It doesn't mention pagination but topK bounds are in the schema. Overall complete for a search tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so the schema already documents both query and topK clearly. The description adds no extra parameter meaning beyond what the schema provides; it only references 'top matching chunks' which aligns with topK. Baseline 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Full-text search over FinPay architecture documentation' with a specific verb and resource, and outlines the return type (synthesised answer plus top chunks). This distinguishes it from sibling tools that target specific resources like transactions or services.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for querying architecture documentation but does not explicitly compare to alternatives. It mentions the DOCU_RAG_URL prerequisite, which is useful operational context, but lacks guidance on when to prefer this tool over sibling resource-specific tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v1.0.0explain_serviceget_payment_hubget_system_healthget_transactionlist_payment_hubslist_serviceslist_transactionssearch_docsScored across 8 tools
Each tool has a clear, distinct purpose: list_* returns collections, get_* returns individual entities by ID, explain_service provides detailed service metadata, and search_docs handles documentation queries. No two tools overlap in function or target resource.
All tool names follow a consistent verb_noun pattern in snake_case. List tools use 'list_', retrieval tools use 'get_', plus 'explain_' and 'search_' which are also descriptive verbs. Naming is uniform and predictable.
Eight tools is well within the ideal range for a payment platform query/monitoring server. Each tool covers a needed operation without redundancy or bloat.
The server provides complete read-only coverage for its domain: listing and getting hubs, services, and transactions, plus overall system health and documentation search. No obvious gaps for the intended use case; write operations are likely out of scope.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
MCP server unifying ERPs, CRMs, APIs and knowledge base for Claude, ChatGPT and Gemini.
MCP server for Modern Treasury — payment orders, transactions, counterparties and ledgers.
MCP server for building and testing AI agents with multi-model experimentation and insights.
Hosted MCP server for live public-data APIs and Skills for AI agents.