Loading ToolBench
A JPMorgan Chase (JPMC) Model Context Protocol (MCP) server for accessing and searching the JPMorgan Chase Payments API documentation
Three tools with clear verb-noun naming (search_, read_, related) and detailed descriptions (150-250 chars each). All tools have input schemas with types and descriptions. However, output schemas are not explicitly documented in the visible code, only inferred from model classes. Parameter descriptions are good but lack explicit format/constraint guidance (e.g., URL validation rules, search phrase length limits). Error handling is minimal; no recovery guidance or actionable error messages visible. Tool composition is sound (each does one thing), but no pagination support for search results despite limit parameter suggesting large result sets.
Fetch and convert a JPMC Payments API documentation page to markdown format. ## Usage This tool retrieves the content of a JPMC documentation page and converts it to markdown format. For long documents, you can make multiple calls with different start_index values to retrieve the entire content in chunks. ## URL Requirements - Must be from the developer.payments.jpmorgan.com domain ## Example URLs - https://developer.payments.jpmorgan.com/docs/commerce/online-payments/capabilities/checkout/how-to/create-checkout-session ## Output Format The output is formatted as markdown text with: - Preserved headings and structure - Code blocks for examples - Lists and tables converted to markdown format
Get related content for a JPMC-PDP Payments API documentation page. ## Usage This tool provides related JPMC-PDP Payments API documentation pages based on a given URL. Use it to discover additional relevant content that might not appear in search results. ## When to Use - After reading a documentation page to find related content - When exploring a new JPMC-PDP service to discover important pages - To find alternative explanations of complex concepts - To discover the most popular pages for a service - To find newly released information by using a service's welcome page URL and checking the **New** recommendations ## Result Interpretation Each recommendation includes: - url: The documentation page URL - title: The page title - context: A brief description (if available)
Search JPMC (JPMorgan Chase) Payments API documentation using the official JPMC API Documentation Search API. ## Usage This tool searches across all JPMC-PDP documentation for pages matching your search phrase. Use it to find relevant documentation when you don't have a specific URL. ## Result Interpretation Each result includes: - rank_order: The relevance ranking (lower is more relevant) - url: The documentation page URL - title: The page title - context: A brief excerpt or summary (if available)
Output schemas not explicitly documented in code. SearchResult, RecommendationResult models exist but their field definitions are not visible in the provided source. LLMs cannot plan downstream tool calls without knowing what fields to expect.
No pagination support for search_documentation despite limit parameter (max 50). If search returns 50 results, agent cannot fetch the next page. Large result sets risk context window exhaustion.
Error handling is implicit. No visible error recovery guidance, categorization (retryable vs fatal), or actionable error messages. If a URL is invalid or search fails, the LLM has no guidance on what to do next.
Inferred effective spec: <=2025-11-25.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | C | 68 | <=2025-11-25 | v2 |
Parameter constraints not fully documented. 'search_phrase' has no length limits or format guidance. 'url' parameter in read_documentation and related states domain allowlist requirement but lacks explicit validation error message guidance.
read_documentation description mentions 'start_index' parameter for chunking long documents, but this parameter is not visible in the input schema shown. Either the parameter is missing or the description is outdated.