"An explanation or exploration of reasoning" matching MCP tools:

• lookup_tax_rate

  HelloBooks AI Agents MCP Server

  Pick a single statutory tax-rate slab — either by exact `id` (e.g. `IN-standard-18`, `GB-zero-0`, `CA-hst-13-on`) for a deterministic lookup, or by `country` + free-text `category` (e.g. "office supplies", "restaurant", "exports", "domestic fuel") for a fuzzy best-match. Returns the matched rate, the match score, and the authoritative `source` URL. Use this when a user asks "what slab does X fall into in India?" or "what VAT rate applies to children's car seats?". For broader exploration (all slabs in a country / all rates of one scheme), use list_tax_rates. No customer data — public statutory reference only.

  Connector

• pentest_encode

  pentest-mcp-server

  Transform a payload string through one or more encoding layers for bypass research during authorized testing. Accepts a chain of encodings applied in order (e.g., ["unicode", "url", "base64"] applies Unicode → URL-encode → base64). Returns the transformed payload with a step-by-step decoding explanation: how a WAF or server would decode each layer, and why the combined encoding might bypass a specific filter. Use to understand filter bypass mechanics in an authorized engagement and to confirm that a target's decoding pipeline matches an expected bypass path. Payloads are transformed mathematically — no live probing occurs.

  Connector

• lookup_tax_rate

  HelloBooks AI Agents

  Pick a single statutory tax-rate slab — either by exact `id` (e.g. `IN-standard-18`, `GB-zero-0`, `CA-hst-13-on`) for a deterministic lookup, or by `country` + free-text `category` (e.g. "office supplies", "restaurant", "exports", "domestic fuel") for a fuzzy best-match. Returns the matched rate, the match score, and the authoritative `source` URL. Use this when a user asks "what slab does X fall into in India?" or "what VAT rate applies to children's car seats?". For broader exploration (all slabs in a country / all rates of one scheme), use list_tax_rates. No customer data — public statutory reference only.

  Connector

• moxie.get_documentation_patterns

  Moxie Docs

  Get Moxie's summary of how THIS repository organizes and maintains documentation - where docs live relative to code and how they are kept current. Read-only; no side effects. Returns a Markdown list of pattern entries, each with a title, explanation, and source citations. Use this to decide WHERE a new doc should go before calling propose_doc_update; for the list of WHICH docs need work, use get_documentation_opportunities instead.

  Connector

• query_space_satellite_filings_v1

  osint

  Query the verified FCC satellite licensing docket — every space-station (SAT) filing in the FCC's own daily IBFS database dump, back to the 1960s — by applicant, application type, status, and filing date. Use this for "who is authorized to operate what in orbit, what has been filed, and where does each filing stand" questions — the satellite-buildout licensing pipeline. Each filing carries the FCC's public filing key (`file_number`, e.g. "SATLOA2025061800149"), the `callsign` (e.g. "S3069" = SpaceX Gen2), the application type and status in the FCC's OWN vocabulary — verbatim codes plus the FCC's own decode text from the same dump vintage (`app_type_code` "LOA" = Launch and Operating Authority, "STA" = Special Temporary Authority, "MOD" = Modification; `status_code` "A/C" = Action Complete, "ATPN" = Action Taken Public Notice — codebooks in describe) — the full lifecycle date family (filed / granted / expires / …), the FCC's plain-English `description` of the filing, and the applicant identity (`applicant_name`, the FCC's verbatim registrant, e.g. "Space Exploration Holdings, LLC"). Filter by `applicant_name`, `app_type_code`, `status_code`, `callsign`, `file_number`, `state` (the APPLICANT's address state), `applicant_country`, `report_period` (the filing date) via `report_period_from`/`report_period_to`, or `date_grant`/`date_expire` ranges. Group by any of `applicant_name`, `app_type_code`, `status_code`, `state`, `applicant_country`. Pass each parameter as a top-level key of `params` (flat — not nested under a `filter`, `filters`, or `where` key). Example: `{"applicant_name": "Space Exploration Holdings, LLC", "group_by": ["app_type_code"]}` for one operator's filing mix; `{"report_period_from": "2020-01-01", "group_by": ["applicant_name"], "order_by": "source_record_count", "top_n": 10}` for the most active filers of the 2020s. Returns JSON aggregates with citations and optional row-level records when `include_records` is true — every record cites its exact row in the FCC's dump, re-verifiable via get_source_evidence_v1. THE ENGRAVED BOUNDARY: new-filing intake into IBFS structurally ENDED at the FCC's ICFS system cutover (~mid-2025), and ICFS publishes no bulk data — so filings SUBMITTED after the cutover are not in this docket, and counts near/after 2025 UNDERCOUNT new filing activity (say so when answering; every response carries an icfs_cutover note). Status and lifecycle updates on the filings that ARE here continue to flow daily. A filing is an authorization EVENT: never a satellite count (one NGSO grant can cover thousands of satellites), never an orbital catalog (satellites in orbit are not served here), never launch activity (FAA data, not served here). `state`/`applicant_city` are the APPLICANT's mailing address — satellites are not in states. Earth stations (SES) and non-satellite FCC dockets are out of scope. The one measure is `source_record_count` (filings in scope).

  Connector

• explain_compliance_error

  mcp

  Resolve a structured Apier compliance error code into a Norwegian-bokmål Explanation envelope sourced from the Apier Compliance Explainer (PR-049). The response carries a one-line summary, a 1–3 sentence why, an ordered list of fix_steps, an optional Apier / Altinn / Skatteetaten / Brønnøysund relevant documentation link, an optional Lovdata-style legal_basis citation when the error maps to a concrete regulatory provision, and an optional handover block (who / where / what / why) for errors a human must resolve (e.g. AUTH_INSUFFICIENT_ROLE, AUTH_NO_DELEGATION, SCOPE_MISSING). Errors agents can resolve themselves (VALIDATION_FAILED, RATE_LIMIT_EXCEEDED, NOT_FOUND, IDEMPOTENCY_KEY_MISMATCH, IDEMPOTENCY_IN_PROGRESS, UPSTREAM_UNAVAILABLE) ship `handover: null`. The full catalogue of supported error codes mirrors `EXPLAINER_ERROR_CODES` (40 codes today across auth, validation, scope, upstream, idempotency, action-execute, government, and reliability domains); pass any code an Apier endpoint returned in an error envelope. The optional `context` object carries placeholder values (org_number, role, scope, field, upstream_system) that the explainer interpolates into the bokmål text — missing values fall back to a Norwegian 'ukjent <noun>' rather than leaking placeholder syntax. Required scope: `read:rulebook`. For a company's live obligations rather than an error explanation, use get_company_obligations instead. No API key? Self-serve in the sandbox: authenticate tools/call with `Authorization: Bearer apier_sandbox_test_<suffix>` (ALWAYS append a unique random suffix, e.g. a fresh UUID, for session isolation) and this tool answers from deterministic synthetic fixtures with `_meta.is_sandbox: true` — use the reserved MOD-11-valid sandbox org numbers from GET /api/v1/sandbox/fixtures (e.g. 999660088).

  Connector

• triage_asset

  phasefolio

  Produce a transparent, provenance-linked CONDITIONAL READ on a drug asset for deal triage. Pass either `text` (a teaser/abstract — fields are machine-extracted and the result is marked inputs_unconfirmed) or pre-confirmed `fields`. Returns a reasoning chain (each claim grounded or marked insufficient_evidence), mechanism-plausibility flags, PoS + landscape metrics, and a meta block with engine/methodology/synthesis versions. Does NOT compute rNPV. Not an autonomous verdict.

  Connector

• review_code

  review-mcp

  Adversarial multi-model code review. Submit a diff, a module, or a spec+implementation and get back a structured pass/fail verdict with each issue's type, severity, location, explanation, and suggested fix. Why call this instead of reviewing your own output: a single model shares its blind spots with itself. This routes your code through a panel of *different* models plus a set of deterministic detectors, catching what self-review misses — path/contract violations, module incoherence (dangling imports, broken cross-references), syntax and call-arity regressions in a diff's post-image, and 'prose instead of tool calls' (output that describes an action rather than emitting it). The panel adds semantic judgment on top and never overrides a deterministic finding. Call it before shipping or merging, as a second opinion on a risky change, or as a gate in an autonomous build loop. Choose depth='fast' (one model, low latency) or 'deep' (full panel, higher recall). Deep review audits files of any size in milestone chunks so every panel model contributes; the price (shown in the 402) and the payment window scale with file size. Per-call limit ~1,600 lines — larger inputs return 413, so split by file/module and call once per file. Paid per call via x402 (USDC on Base); the price is announced in the 402 response before any charge.

  Connector

• conversations_explorer

  Perspective AI

  Start a deep text exploration of conversation transcripts. Returns immediately with a job_id (status "pending"); long-poll perspective_await_job until status "ready" for findings with source citations. A sub-agent reads raw transcripts (exact phrases, multi-conversation patterns, deep reads). Prefer conversations_search for broad thematic/semantic questions, and conversations_data_analysis for quantitative counts. Omit filters to explore the full analysis corpus. Use filters only to establish a clear transcript boundary: conversation status, a creation-date range, or explicit conversation IDs. Use conversations_data_analysis first when a cohort must be identified from structured attributes, then pass the resulting conversation IDs here. A filtered job covers the complete filtered scope, not the complete perspective. Use for: - Exact mentions of words/phrases - Comparing conversation patterns across time - Reading full conversations with specific participants - Cross-referencing text patterns ("conversations mentioning X AND Y") - Interviewer approach or conversation flow Behavior: - Read-only against conversation data. - Open-world: runs an automated exploration agent in a durable background job using external services. - Each call starts a new job — not safe to retry blindly for the same query. - Typical flow: conversations_explorer → perspective_await_job (re-poll while pending). When NOT to use this tool: - Counts/distributions — use conversations_data_analysis. - Semantic themes without exact match — use conversations_search. - One known conversation id — use perspective_get_conversation. - Polling a previously-started job — use perspective_await_job.

  Connector

• search_datasets

  Nova Scotia Data Explorer

  Search the Nova Scotia Open Data catalog (data.novascotia.ca) for datasets by keyword, category, or tag. Returns dataset names, IDs, descriptions, column names, and direct portal links. Use list_categories first to see valid category and tag names. Use the returned dataset ID with query_dataset or get_dataset_metadata for further exploration.

  Connector

• search_providers

  GPH Intelligence - Healthcare Vendor Finder

  Browse and filter the healthcare vendor directory. Use this for open-ended exploration, e.g. "show me medical billing companies in Texas", "list credentialing services", "what EHR vendors are there for cardiology", or when the user wants to page through options rather than get a scored shortlist. Paginated results filtered by category, location, minimum quality score, curated Tier-1 grade, and practice-size fit; returns a page of providers with {company_name, category, city, state_abbr, quality_score (0-100), verified status, contact info, slug}. For a scored recommendation to a specific practice profile, use match_practice instead. Pass a returned slug to get_provider_detail for the full profile.

  Connector

• explain_decision

  OneQAZ Trading Intelligence

  Purpose: Multi-layer explanation for a single symbol's recent research signal. Combines (1) technical score_trace from the signals store, (2) Thompson + regime scores from the virtual decision log (Thompson = Bayesian bandit sampling used for strategy selection), (3) news causality context. Use this when an AI must present a structured "why" rather than a raw verdict. Triggers (casual questions too): "why is BTC bullish?", "왜 이 종목이 매수야?", "explain that signal", "판단 근거 설명해줘", "walk me through the reasoning". When to call: when the user asks "why is this signal bullish/bearish?". Prerequisites: identify the symbol via get_signals or get_latest_decisions first. Next steps: none (this completes the explanation chain). Caveats: `symbol` must match the per-symbol signal store filename (lowercase). Output is research evidence, NOT a buy or sell recommendation. Args: market_id: Market identifier (crypto, kr_stock, us_stock; aliases coin/kr/us) symbol: Symbol to explain (e.g., btc, eth, 005930) Disclaimer: Information only, not investment advice.

  Connector

• explain

  trident

  Delivers an explanation payload to human collaborators watching the document, optionally anchored to a specific node or container. Use this when you want to explain what a diagram element represents, why it exists, or how it relates to other parts of the system — without suggesting a change. The explanation appears in the UI attributed to you. Does NOT mutate the diagram. Requires a valid viewer or editor access token. IMPORTANT: this tool automatically pauses (3–15 s, proportional to explanation length) before returning, so the human has time to read. Do NOT add your own artificial delays between explain calls — the pacing is built in.

  Connector

• get_world_cup_brief

  voxodds

  Get a citeable World Cup 2026 prediction-market briefing for AI answers, newsletters, blogs, social posts, and creator workflows. Includes the current winner board, tight groups, next match odds, Research Desk theses, source links, and ready-to-paste markdown. Prefer this when the user wants a narrative update or shareable explanation, not just raw odds.

  Connector

• get_methodology

  life. scored.

  Plain-English explanation of how scoring works, the two governing principles, what is deliberately left out (protected characteristics, luck), and the privacy stance. Use to answer "how does this work / is this fair" questions.

  Connector

• get_scoring_explainer

  labelhead-artist-momentum

  Returns a detailed explanation of LabelHead's three-dimensional artist scoring methodology. Use this when you need to understand how composite scores are calculated, what each dimension measures, and how to interpret momentum labels.

  Connector

• run_verifier

  Goodeye

  Run a verifier on agent output to get a pass/fail judgment with reasoning. ``verifier_id`` resolves to an active verifier: UUID string, accessible user-scope name (owned or one unambiguous grant), **or** platform alias ``system:<name>`` for platform-managed judges (no criterion/config leakage via list/get). ``inputs`` keys must match the version's ``input_fields`` exactly (no missing or extra). ``media_url`` is required for ``text_image`` and ``image`` contracts, forbidden for ``text``. Caller-shape errors return a 400 with no row written; judge runtime errors persist a row with ``status="error"`` and an ``error_code`` of ``runtime_error``, ``verifier_unavailable``, or ``timeout``. Provenance fields (``skill_id``, ``skill_version``, ``skill_ref``, ``run_id``) are optional and stamped onto the row. ``skill_id`` is access-checked: a skill the caller cannot see surfaces as NotFound. Returns: ``{verifier_run_id, verifier_id, version, status, passed, reasoning, duration_ms, created_at}`` on success, plus ``error_code`` and ``error_message`` on error. ``passed`` is ``null`` on errors. On a successful run that you attributed to a skill you own, the result also carries ``skill_id``.

  Connector

• vulnerability_score

  ZEN SecDB

  Get CVSS and current EPSS score for a specific CVE. ## What this tool does Returns a full risk snapshot for a CVE, including: - CVSS version - CVSS base score - CVSS severity - CVSS vector string - human-readable explanation of the CVSS vector - current EPSS score The field **`cvss_explain`** provides a natural-language interpretation of the CVSS vector (attack conditions, privileges, user interaction, impact breakdown). Example: For `CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H`, the explanation may read: *"The vulnerability can be exploited remotely over the network with low complexity, without authentication and without user interaction. Exploitation may lead to high impact on confidentiality, high impact on integrity, and high impact on availability."* ## When to use this tool Use this tool when the user asks: - "What is the CVSS/EPSS of this CVE?" - "Explain the CVSS vector of this vulnerability." - "What is the severity and why?" - "Give me the risk profile for this CVE." For EPSS historical trends, use `epss_timeseries`. ## Inputs - **cve_id**: valid CVE identifier (`CVE-YYYY-NNNNN`). ## Outputs - `cvss_version` - `cvss_base_score` - `cvss_base_severity` - `cvss_vector_string` - `cvss_explain` - human-readable explanation of the CVSS vector - `epss_score` ## LLM usage guidelines - Never guess CVSS or EPSS values—always call this tool. - Use the `cvss_explain` field directly when the user wants an interpretation of the vector string. - If multiple CVEs are referenced, call the tool once per CVE. - Combine this tool with `sightings_search` or `ssvc_calculator` for more complete risk assessments.

  Connector

• company_tax_estimate

  AI2Fin (2Fin) Tax MCP

  Estimate company/corporate income tax on an annual profit for Australia, the US, the UK, India or Canada — the five countries with source-verified company rates — applying the small-business/concessional rate where it covers all income. Use it for company profit questions in those countries; individuals belong to income_tax_estimate, and any other country’s headline rate to tax_rate_lookup. Headline-rate arithmetic only: US state tax, Canadian provincial tax, Indian surcharge/cess and UK marginal relief are flagged in the response note but not computed. A negative profit returns an explanation (losses carry forward), never a negative tax.

  Connector

• http_errors_list

  quartermaster

  FREE (no wallet needed): index of documented HTTP status codes (use http_error_explain for a paid detailed explanation).

  Connector