"Automating Testing and Debugging for LLMs in Production" matching MCP tools:

• get_discoveryA

  ikeytz – Schlüsseldienst LudwigsburgA

  WHAT: Fetch one public discovery file from www and return a line window. REQUIRED which. IDs (aliases folded): llms, llms-full, llms-index, llms-keywords, llms-serp, llms-jsonld, llms-impressum-kontakt, llms-orte-geo, llms-urheberrecht, llms-copyright, llms-mcp-server, llms-mcp-web, robots, sitemap-txt, sitemap-xml, ai-txt, ai-plugin, answer-engine, ard, ai-catalog, auth-md, mcp-readme, agent-skills. summary = the line window + trailing # MCP-META (truncated, totalUrls, nextOffset). Use offset/limit + nextOffset to page. Sitemap ~9076 http-URLs (Stand 2026-09-22) and llms-keywords (~50MB) load full; always prefer limit on huge files. Unknown which → unknown_discovery. Prefer dedicated get_llms_txt / get_llms_jsonld / get_llms_serp_txt / get_sitemap_txt / get_llms_mcp_server when you know the file. Policy files say ai-train=no.

  ConnectorNo auth

• list_categoriesA

  HTML Email PlaybookA

  List all rule categories in the Email Playbook with a one-line description and page count. Categories are: structure (head/body container/header/body/footer), compatibility (Outlook MSO, RTL, responsive), production (Gmail clipping, dark mode, preheader, bulletproof buttons), ai-generation (constraints for AI emitters). For reusable components, use list_components instead — they live in a separate dimension and are not returned by get_playbook_rules.

  ConnectorNo auth

• get_faqA

  CalmActivaA

  Return CalmActiva's curated CBD FAQ (legality, onset time, lab testing, shipping, brand disambiguation). Use for general CBD/brand questions before falling back to web search.

  ConnectorNo auth

• book_demoA

  gethal.aiA

  Submits a demo request. The prospect receives a confirmation email and must click the link in it before the request reaches a human at A Cloud Frontier. Use only when a real person has explicitly asked for a demo and provided their own working email address. Do NOT call this for testing, evaluation, or crawling purposes — automated and unconfirmable requests are rejected.

  ConnectorNo auth

• get_demo_guideA

  eDiscovery Decoder News/CalcA

  Return a short, human-readable walkthrough for testing this server: the endpoint, the tool/prompt/resource names, and ready-to-paste sample prompts. Use to give someone a guided demo. For the full machine-readable capability catalog, use list_capabilities instead.

  ConnectorNo auth

• get_leadproof_trialA

  LeadProof Sales AgentA

  Use when a buyer is ready to start the standard no-card production trial: 25 live lead deliveries for 14 days with verified sign-in and no payment authorization. For a failed-lead replay test and its prerequisites, use get_leadproof_replay_trial instead; for a broader evaluation sequence, use get_leadproof_evaluation_path.

  ConnectorNo auth

• jwt_decodeA

  AI NetCaféA

  Decodes the header and payload of a JWT and reports issued-at / expiry as readable timestamps plus seconds remaining. The signature is NOT verified and the response says so — decoding is fine for debugging a token you already hold, but never treat these values as proof of anything; verification needs the secret and belongs in your own service.

  ConnectorNo auth

• jwt_decodeA

  ai-netcafeA

  Decodes the header and payload of a JWT and reports issued-at / expiry as readable timestamps plus seconds remaining. The signature is NOT verified and the response says so — decoding is fine for debugging a token you already hold, but never treat these values as proof of anything; verification needs the secret and belongs in your own service.

  ConnectorNo auth

• jwt_decodeA

  netcafe-devkitA

  Decodes the header and payload of a JWT and reports issued-at / expiry as readable timestamps plus seconds remaining. The signature is NOT verified and the response says so — decoding is fine for debugging a token you already hold, but never treat these values as proof of anything; verification needs the secret and belongs in your own service.

  ConnectorNo auth

• searchA

  developer-toolkit-mcpA

  Search the AI Developer Toolkit documentation: 950+ guides on Cursor, Claude Code and OpenAI Codex, covering setup, agent workflows, hooks, MCP, testing, CI and deployment, in English and Polish. Returns at most 10 ranked results, each with a short snippet rather than the article text; an empty list means the corpus has nothing on the topic. Pass a result id to `fetch` for the full text.

  ConnectorNo auth

• get_aiakiv_memory_guideA

  AiAkiv MemoryA

  Return an AiAkiv guide document for a topic, as text. Use this when the user asks how to use AiAkiv or MWeft, wants the tutorial, or pastes an `aiakiv.com/llms-*.txt` link that cannot be opened here. The result is a reference document to read and draw on, not a set of commands. Read-only. Args: topic: One of `"tour"` (first-run tutorial, llms-tour.txt), `"playbook"` (projects and personas, llms-playbook.txt), `"setup"` (install and connect, llms.txt), `"demo"` (public demo-memory walkthrough, llms-tour-demo.txt), or `"console"` (the console app actions for teams, links, audit and cards, llms-console.txt). It defaults to `"tour"`, so a request for one of the other four carries the topic. Any other value returns an error listing these five. Returns: `{topic, source_url, content, cached, available_topics}` — or `{error, hint}` when the topic is unknown or the fetch fails.

  ConnectorOAuth

• api_infoA

  x402 Crypto Market StructureA

  REST API access for autonomous agents — pricing, quick start, and migration guide. Call this when: building a trading bot, deploying an autonomous agent, hitting the MCP rate limit, or running 24/7 without a human in the loop. The MCP tier (what you're using now) is free via Smithery, rate-limited to 60 calls/minute per IP, and good for testing. The REST API is for production: pay per call in USDC; paid endpoints are rate-limited to 60 calls/minute and 200 calls/hour per wallet. No API key required.

  ConnectorNo auth

• get_testing_guidelinesA

  IA-QA — 130+ QA & Dev Tools for AI AgentsB

  Query the IA-QA methodology knowledge base. Returns structured testing guidelines, assertion strategies, thresholds, best practices, and relevant MCP tools for a given topic. Call without a topic to list all available topics. Topics: llm-unit-testing, rag-pipeline, prompt-stability, prompt-ab-testing, embedding-quality, eval-framework, semantic-testing, auto-testing, security, api-testing, ci-cd, multimodal, llm-data-security, agent-observability, pro-tips, learning-paths, golden-dataset, selector-drift, qa-recipes, playbooks. Not sure where to start testing an LLM, RAG pipeline or agent? Call without a topic (or with "start-here"): it maps what you are testing to the tools to call and the output field to gate CI on. A plain question such as "how do I test my RAG" also resolves to the right topic.

  ConnectorNo auth

• get_petroleum_dataA

  DOE Energy InformationA

  Get petroleum and oil price or production data from the EIA. Returns time series data for petroleum products including crude oil prices, production volumes, imports, exports, and refinery operations. Args: series: EIA series ID for the petroleum data. Common series: 'PET.RWTC.D' (WTI crude oil daily price), 'PET.RBRTE.D' (Brent crude oil daily price), 'PET.EMM_EPMR_PTE_NUS_DPG.W' (US regular gasoline weekly price), 'PET.MCRFPUS2.M' (US crude oil production monthly). Default is 'PET.RWTC.D'. limit: Maximum number of records to return (default 100, max 5000).

  ConnectorNo auth

• web_loginA

  Local MCPA

  Opens a real browser window on the Mac for the user to sign into a website themselves (you never handle their password). After they log in, the session is saved on this Mac and reused by web_navigate/web_read/web_screenshot — they won't need to log in again. Use a stable `session` name per site (e.g. 'linkedin'). NOTE: automating sites like Instagram/LinkedIn may violate their terms — the user accepts that risk.

  ConnectorOAuth

• test_python_package_runtimeA

  Python Package Runtime TestA

  Test a specific Python package/version on a supported Python/Linux target runtime using empirical execution. Returns scoped install evidence, usable-import evidence when requested, and a scoped result/receipt. Supported boundary: public PyPI on Linux x86_64 / CPython 3.13. This is not generic package advice, security verification, arbitrary Python execution, broad compatibility testing, feature behavior testing, or application integration testing.

  ConnectorNo auth

• get_forward_signal_ledgerA

  DFX Real Estate IntelligenceA

  The ledger behind every forward claim: for each pattern, its definition, population, test period, base rate, rate among entities showing it, lift with its interval, median lead time, early and late halves (stability), precision at the top 1% against a conventional recency list at the same cut, the multiple-testing q value, and its status (VALIDATED, PRODUCTION, TESTING, PROSPECTIVE_ONLY, WEAK, REJECTED). Rejected patterns are listed on purpose: they are what DFX tested and found did not predict. Filter by vertical, status or signal key. ACCESS: without a paid DFX plan on the vertical, a list names its first 5 rows and returns the rest with their figures, dates and classes but names, ids and URLs read LOCKED; a record names its subject and the first 3 related names per section; contact values (email, phone, profile URLs) and decision-maker names are never returned, only their types and counts. Every answer says what it withheld in `entitlement` and `locked`. Full access: DFX Intelligence, 3 days for $1 at https://dfxintel.com/data-factory/plans.

  ConnectorNo auth

• adw.adw_516A

  AlpineDataWorks Intelligence ServerB

  Returns a 0-100 agricultural-production significance score for any of 3,222 US counties (normalized from USDA county-level production statistics) with score, national_percentile, state_rank, top_drivers, as_of, and methodology_version. Call when the user asks about local farm output, crop or livestock concentration, or which counties lead US agricultural production, or when timing ag lending, equipment or facility siting, and rural supply-chain decisions. Updates: on source cadence.

  ConnectorNo auth

• get_llms_fullA

  docsA

  Return a link to the complete, source-linked agent reference (llms-full.txt) for a product — its entire prose, API surface, and examples in one document. This file is large, so it is returned as a resource link and canonical URL rather than inlined; use search_docs/get_doc for targeted lookups and this when you want the whole corpus.

  ConnectorNo auth

• fetch_veille_feedA

  IA-QA — 130+ QA & Dev Tools for AI AgentsB

  Fetch the latest QA & AI/LLM articles aggregated from curated RSS sources (Google Testing Blog, DEV.to Testing/QA/AI/LLM/Agents, Hugging Face Blog, Simon Willison). Perfect for agents monitoring the QA & AI landscape. Each article carries summary_source — the XML tag the summary was read from, or "none" when the feed publishes titles and links only; an empty summary with summary_source "none" is a property of that feed, not a parse failure.

  ConnectorNo auth

• embedding_similarityA

  IA-QA — 130+ QA & Dev Tools for AI AgentsB

  Compute text similarity using local algorithms (Bag of Words, TF-IDF, Character N-grams). No API key needed — runs entirely in-process. NOT real embeddings: for true semantic similarity with vector embeddings, use run_semantic_tests with mode="embeddings" and your OpenAI API key. Supports single pair or batch mode with pipe-separated pairs. Useful for RAG retrieval testing, semantic search evaluation, and text deduplication.

  ConnectorNo auth