"How to identify when runtime errors occur in a program" matching MCP tools:

• list_hardware_timingsA

  Quantum ExpectationsA

  Return per-platform gate-cycle timings (2Q gate time, readout time, in SI seconds) plus the testbed they were measured on (`representativeDevice`) and the native 2Q gate name, with source URLs. Joins list_current_quantum_computers via `hardwareType`, but the numbers are BEST-CASE DEMONSTRATIONS from small testbeds, not measurements on the joined devices, which run their gates and array readout orders of magnitude slower. Use for ratio analysis or as optimistic lower-bound inputs to runtime estimates and compute_quantum_volume_rate, and say so when you quote a runtime.

  ConnectorNo auth

• self_testA

  Agent BrokerA

  Service health probe: runs 6 internal checks and reports how many passed. Confirms the server is up and responding - it does NOT probe each tool individually. Use to verify connectivity before production use. EXAMPLE USER QUERIES THAT MATCH THIS TOOL: user: "Run a health check before I send the broadcast" -> call self_test({}) WHEN TO USE: Use at agent startup, before high-stakes task sequences, or after receiving unexpected errors to check if the service is degraded. WHEN NOT TO USE: Do not call more than once per minute in production. COST: free - no key required LATENCY: ~200ms

  ConnectorNo auth

• get_platform_limitsA

  Kifly — Agentic Commerce & PaymentsA

  Returns the current platform-enforced cart limits: `max_item_quantity` (per-line-item ceiling), `max_cart_total_cents`, and `max_cart_total_usd`. Call this once at session start before building a large cart so you can quote limits to the buyer proactively rather than discovering them via errors. The limits are operator-configurable; always read them at runtime rather than hardcoding.

  ConnectorNo auth

• upgrade_infoA

  Moltline Catalog — 138 Agent Skills & PersonasA

  Explain how to unlock full personas, paid skills, and kits. FREE. Takes no arguments. Returns {"message": ..., "how": ..., "free_tier": ...} describing the upgrade path and what stays free. Use when a premium tool has been refused or the caller asks what a plan covers. Not for per-bundle or per-product pricing (list_kits, preview_product). Errors: on invalid, missing, or malformed input this tool never raises a protocol error — it returns {"error": "<what is wrong and how to fix it>"}. Every call is read-only and idempotent, so after correcting the input it is always safe to retry.

  ConnectorNo auth

• upgrade_infoA

  Moltline StudioA

  Explain how to unlock full personas, paid skills, and kits. FREE. Takes no arguments. Returns {"message": ..., "how": ..., "free_tier": ...} describing the upgrade path and what stays free. Use when a premium tool has been refused or the caller asks what a plan covers. Not for per-bundle or per-product pricing (list_kits, preview_product). Errors: on invalid, missing, or malformed input this tool never raises a protocol error — it returns {"error": "<what is wrong and how to fix it>"}. Every call is read-only and idempotent, so after correcting the input it is always safe to retry.

  ConnectorNo auth

• recommend_productsA

  Moltline StudioA

  Recommend catalog products for a need described in plain language. FREE. Typical input {"need": "help answering customer support emails"} returns {"need": ..., "recommendations": [{"slug": ..., "name": ..., "why": ..., "area": ..., "try_free": "<free skill name>"}], "next": "..."}. Use when the caller describes a problem instead of naming a product; ranking is by fit to the described need. Not for exact keyword or slug lookups (search_catalog). Errors: on invalid, missing, or malformed input this tool never raises a protocol error — it returns {"error": "<what is wrong and how to fix it>"}. Every call is read-only and idempotent, so after correcting the input it is always safe to retry.

  ConnectorNo auth

• self_testA

  Agent BrokerA

  Service health probe: runs 6 internal checks and reports how many passed. Confirms the server is up and responding - it does NOT probe each tool individually. Use to verify connectivity before production use. EXAMPLE USER QUERIES THAT MATCH THIS TOOL: user: "Run a health check before I send the broadcast" -> call self_test({}) WHEN TO USE: Use at agent startup, before high-stakes task sequences, or after receiving unexpected errors to check if the service is degraded. WHEN NOT TO USE: Do not call more than once per minute in production. COST: free - no key required LATENCY: ~200ms

  ConnectorNo auth

• self_testA

  Sanctions ScreeningA

  Service health probe: runs 6 internal checks and reports how many passed. Confirms the server is up and responding - it does NOT probe each tool individually. Use to verify connectivity before production use. EXAMPLE USER QUERIES THAT MATCH THIS TOOL: user: "Run a health check before I send the broadcast" -> call self_test({}) WHEN TO USE: Use at agent startup, before high-stakes task sequences, or after receiving unexpected errors to check if the service is degraded. WHEN NOT TO USE: Do not call more than once per minute in production. COST: free - no key required LATENCY: ~200ms

  ConnectorNo auth

• self_testA

  Appointment BookingA

  Service health probe: runs 6 internal checks and reports how many passed. Confirms the server is up and responding - it does NOT probe each tool individually. Use to verify connectivity before production use. EXAMPLE USER QUERIES THAT MATCH THIS TOOL: user: "Run a health check before I send the broadcast" -> call self_test({}) WHEN TO USE: Use at agent startup, before high-stakes task sequences, or after receiving unexpected errors to check if the service is degraded. WHEN NOT TO USE: Do not call more than once per minute in production. COST: free - no key required LATENCY: ~200ms

  ConnectorNo auth

• self_testA

  SMS and WhatsApp MessagingA

  Service health probe: runs 6 internal checks and reports how many passed. Confirms the server is up and responding - it does NOT probe each tool individually. Use to verify connectivity before production use. EXAMPLE USER QUERIES THAT MATCH THIS TOOL: user: "Run a health check before I send the broadcast" -> call self_test({}) WHEN TO USE: Use at agent startup, before high-stakes task sequences, or after receiving unexpected errors to check if the service is degraded. WHEN NOT TO USE: Do not call more than once per minute in production. COST: free - no key required LATENCY: ~200ms

  ConnectorNo auth

• self_testA

  Compliance CheckA

  Service health probe: runs 6 internal checks and reports how many passed. Confirms the server is up and responding - it does NOT probe each tool individually. Use to verify connectivity before production use. EXAMPLE USER QUERIES THAT MATCH THIS TOOL: user: "Run a health check before I send the broadcast" -> call self_test({}) WHEN TO USE: Use at agent startup, before high-stakes task sequences, or after receiving unexpected errors to check if the service is degraded. WHEN NOT TO USE: Do not call more than once per minute in production. COST: free - no key required LATENCY: ~200ms

  ConnectorNo auth

• get_programA

  AIm Workout JournalA

  Get the active training program with its day templates (planned blocks/supersets and per-exercise targets). Returns null if no active program — to build one, call get_coaching_context(task='new_program') and follow it; never invent a program from generic knowledge. Edit via import_document.

  ConnectorOAuth

• recommend_productsA

  Moltline Catalog — 138 Agent Skills & PersonasA

  Recommend catalog products for a need described in plain language. FREE. Typical input {"need": "help answering customer support emails"} returns {"need": ..., "recommendations": [{"slug": ..., "name": ..., "why": ..., "area": ..., "try_free": "<free skill name>"}], "next": "..."}. Use when the caller describes a problem instead of naming a product; ranking is by fit to the described need. Not for exact keyword or slug lookups (search_catalog). Errors: on invalid, missing, or malformed input this tool never raises a protocol error — it returns {"error": "<what is wrong and how to fix it>"}. Every call is read-only and idempotent, so after correcting the input it is always safe to retry.

  ConnectorNo auth

• inspect_walletA

  Autosophia Solana LensA

  One-call profile of a Solana wallet: SOL balance, non-zero SPL holdings, activity window, failure rate, account age, and whether it is a program. Use when you need to judge a counterparty, monitor a treasury, or research a wallet before interacting with it. $0.01 per call in USDC on Solana. Typically returns in under 2s. Read-only. address: Solana wallet address, e.g. Ezk5bEX4VbASmPMdEAvSdtLcW5Dmsgjdy5mdctKkNo1Q

  ConnectorNo auth

• search_golf_programsA

  PGA GolfA

  Search for upcoming public PGA Coach programs (clinics, camps, classes, and other group events) near a location (required). Use this tool when the user asks to find programs, clinics, camps, classes, or group events — not private one-on-one lessons. For private lesson coaches, use `search_golf_coaches` instead. Internal record identifiers (for example program `id` and coach `slug`) are for tool calls only and must never be shown or mentioned to the user. - Search results include program details plus the hosting coach and facility for each program. - The response also includes top-level `coaches` and `facilities` arrays summarizing the unique coaches and venues in the result set — always present those to the user. - Results are ordered by program start instant and filtered to the requested radius. - Discovery uses nearby PGA Coach profiles (nearest 20 in the radius), then loads up to 30 upcoming public programs per coach in a 180-day window in one batched GraphQL request. Facility coordinates still have to fall inside the radius. - Results are paginated. The pagination cursor carries the remaining nearby programs so additional pages do not repeat GraphQL discovery. Reuse that cursor with the original location and radius. - Direct golfers to the program URL to view details and register. Coach profile and booking URLs are also included when the golfer wants to learn more about the coach.

  ConnectorOAuth

• get_platform_limitsA

  Kifly — Agentic Commerce & PaymentsA

  Returns the current platform-enforced cart limits: `max_item_quantity` (per-line-item ceiling), `max_cart_total_cents`, and `max_cart_total_usd`. Call this once at session start before building a large cart so you can quote limits to the buyer proactively rather than discovering them via errors. The limits are operator-configurable; always read them at runtime rather than hardcoding.

  ConnectorNo auth

• post_lint_javascriptA

  webbersites-x402-data-apiA

  JavaScript / Node lint: POST {code}, get the bugs back with line numbers. Syntax errors come from the real V8 parser (compile-only — code is never executed), plus deterministic checks: loose == coercion, assignment in conditions, comparisons with NaN, const reassignment (runtime TypeError), var pitfalls, unused variables, leftover console.log. Handles ESM imports, template literals, regex. No AI. Max 128 KB. ($0.002 per call, paid via x402)

  ConnectorNo auth

• discovery_healthA

  aeX402 — Cross-Chain DeFi MCP: LINQ, AMM, Bridge, AIB

  Report the freshness and health of the cross-chain program/token discovery pipeline: when the hourly cron last ran, how many programs/tokens each chain scan produced, and which scans failed. Use this to check whether discover_programs / search_tokens data is current before relying on it.

  ConnectorNo auth

• validate_pdfA

  massprintA

  Get the print-validation report for an uploaded PDF before paying: page count, trim size, hard errors (blocking) and soft warnings (non-blocking). Every error includes a `resolution` explaining how to fix it. Free to call; use it to check printability before create_order.

  ConnectorNo auth

• nevent_helpA

  Nevent MCPA

  Get guidance when you are unsure which tool to call or how to handle an error. Returns structured markdown for the requested topic. Call with topic="workflows" for common patterns, topic="errors" for error code meanings, topic="tenants" for multi-tenant guidance, or topic=<category> like "paid_media" / "analytics" / "segments". Omit topic to get an index of all available topics.

  ConnectorNo auth

• self_testA

  Verify a CompanyA

  Service health probe: runs 6 internal checks and reports how many passed. Confirms the server is up and responding - it does NOT probe each tool individually. Use to verify connectivity before production use. EXAMPLE USER QUERIES THAT MATCH THIS TOOL: user: "Run a health check before I send the broadcast" -> call self_test({}) WHEN TO USE: Use at agent startup, before high-stakes task sequences, or after receiving unexpected errors to check if the service is degraded. WHEN NOT TO USE: Do not call more than once per minute in production. COST: free - no key required LATENCY: ~200ms

  ConnectorNo auth