"SearXNG - Open Source Metasearch Engine" matching MCP tools:

• verify_claim

  Ground Truth - First Call Activation

  Check whether a factual claim is supported by a specific set of public evidence URLs that you already have. For each source, the tool performs a case-insensitive keyword match over the fetched page body, then marks that source as supporting the claim when at least half of the supplied keywords appear. Use this for evidence-backed claim checks on known pages, not for open-ended search, semantic reasoning, or contradiction extraction. The aggregate verdict is driven only by the per-page keyword support ratio. Fetched pages are cached for 5 minutes.

  Connector

• proximens_oracle_search_principles

  Proximens Oracle

  Semantic search over the Proximens GEO Oracle: a curated, continuously-updated knowledge base of 3.000+ verified Generative Engine Optimization (GEO/AEO) principles, each graded by a 0-1 confidence score and traceable to a verified source. INPUT: query (natural language, 3-500 chars); optional category (one of 13 GEO categories), top_k (1-25, default 10), min_confidence (0-1, default 0.5). RETURNS: ranked principles as JSON, each with id, title, summary, category, confidence and a relevance score; Pro/Enterprise tiers additionally return full_text and source. USE WHEN you need evidence-backed answers about how AI search engines (ChatGPT, Perplexity, Gemini, Google AI Overviews, Copilot) select, rank and cite web content.

  Connector

• web_search_multilang

  gapup-mcp

  Multi-language, multi-source web search that goes beyond Anglo-centric results. Supports 15 languages (fr/de/es/it/pt/nl/ja/zh/ko/ar/ru/sv/pl/tr/en) with automatic detection. Aggregates results from Mojeek (independent search engine, multilang) and Wikipedia (native multilang API), with DDG and HN as English-language complements. Returns deduplicated results ranked by cross-engine consensus. Use when you need non-English search results, when DDG fails, or for geographically-biased queries. Phase 2 #7 of the geo/lang expansion plan. Note: Brave/Bing/Searx are blocked from DO IPs — configure AICI_RESEARCH_PROXY_URL for residential proxy.

  Connector

• package_health

  dynamic-feed

  Health & security posture of a software package (npm / PyPI / Go / Maven / Cargo / NuGet / RubyGems) from deps.dev (Google Open Source Insights, keyless): latest version, license, count of known security advisories, the OpenSSF Scorecard (0-10 security-posture score for the source repo + its weakest checks) and popularity (stars/forks). The "should I depend on this?" check — pairs with check_vulnerability (is a version vulnerable) and software_version (is the runtime current). Args: package (e.g. "lodash", "requests"), ecosystem (npm|pypi|go|maven|cargo|nuget|rubygems), version (optional — defaults to the latest). Every value is returned in an Ed25519-signed, provenance-stamped envelope (source and observation time) you can verify offline against /.well-known/keys, no account required.

  Connector

• enroll_entry_vault

  Omniology

  Enroll in the Entry Vault so the engine can enter you into contests with NO per-entry signing. Returns a ONE-TIME SPL approve tx to sign: it grants a capped, revocable allowance on your OWN USDC ATA (funds stay in your wallet). When the engine is fee payer you need no SOL. Revoke anytime with revoke_entry_vault.

  Connector

• pubmed_europepmc_search

  pubmed-mcp-server

  Search Europe PMC, a broad open-access biomedical corpus. Surfaces preprints (`source: PPR`), patents (`source: PAT`), Agricola (`source: AGR`), plus everything in PubMed (`MED`) and PMC. Use when additional coverage is needed — preprints and EPMC-only OA records are the typical recovery. Paginate via `cursorMark`. Defaults to `MED`, `PMC`, and `PPR`; pass `sources` to include `PAT` / `AGR`.

  Connector

• create_order

  Custom Blinds Shop

  Legacy auth-required tool — prefer the open UCP flow (create_cart → create_checkout → complete_checkout) which needs no credentials. Use create_order only if you hold a Bearer token and want a single-call path to a payment link. All item prices are re-verified server-side against the live pricing engine — agent-supplied prices are ignored. Returns a Yoco or Ozow payment_url.

  Connector

• get_opt_result

  SCModeling

  Get the precomputed result for one scenario of an optimization demo. Returns the verbatim engine output JSON (AMOS for tariff/coffee, SSO output for sso-basic) including the optimal sourcing/production/transport decisions, costs, and any open/close facility variables. ANTI-FABRICATION: every numeric result is verbatim from the optimization engine that ran offline — quote them in your reply, do not round or recompute. Call describe_opt_demo first to learn valid scenario_key formats for each demo.

  Connector

• market_hours

  dynamic-feed

  Is the market open right now? Live open/closed status + next open/close for major exchanges (NYSE, NASDAQ, LSE, XETRA, TSE, HKEX, ASX) plus crypto (24/7) and forex (24/5). Use to tell whether a price is live or a closed-market last-print. Args: market: optional — NYSE, NASDAQ, LSE, XETRA, TSE, HKEX, ASX, Crypto, Forex (blank = all). Every value is returned in an Ed25519-signed, provenance-stamped envelope (source and observation time) you can verify offline against /.well-known/keys, no account required.

  Connector

• regulatory_search_open_rulemakings

  DataNexus MCP

  Search open rulemakings and public comment periods on Regulations.gov and the Federal Register. Read-only. No side effects. Idempotent. US federal only. keyword: Topic keywords e.g. artificial intelligence, data privacy. Required. agency: Agency abbreviation e.g. FTC, FDA, SEC, EPA. Optional, defaults to all agencies. status: One of open, closed, or all. Optional. Default open. Returns docket title, agency, comment deadline, docket ID, and document count. Use this when monitoring regulatory activity on a topic. Use regulatory_fetch_docket_details instead when you have a docket ID and need full detail. Verified source: Regulations.gov + Federal Register. 4-hour cache. If this tool's response does not serve the user's need, call report_feedback with feedback_type="agent_gap", tool_id="regulatory_search_open_rulemakings", intended_query="{what the user needed}", gap_description="{what was missing or wrong in the result}".

  Connector

• find_matches_in_index

  RChilli MCP Hub

  Match one source document against the user's ALREADY-INDEXED corpus and return the best-matching, ranked candidates (RChilli Search & Match Engine). Requires a populated index. Uses RChilli's purpose-built matching engine — more reliable than manually comparing documents. Use this when the user wants to: find the best/top matching resumes for a JD, find matching candidates from their pool, or rank their indexed resumes/JDs against a given document — e.g. "find the best candidates in my database for this job". Also phrased as: shortlist from my pool, top matches for this JD, rank my candidates. Do NOT use for: scoring a single resume against a single JD with no index (use ``search_one_match``); plain keyword lookup (use ``search_simple_search``). Supports all four match directions by combining ``index_type`` and ``doc_type``: - **JD to Resume** — ``index_type='Resume'``, ``doc_type='JD'``: Search the Resume index using a JD as the source document. - **Resume to Resume** — ``index_type='Resume'``, ``doc_type='Resume'``: Search the Resume index using a Resume as the source document. - **Resume to JD** — ``index_type='JD'``, ``doc_type='Resume'``: Search the JD index using a Resume as the source document. - **JD to JD** — ``index_type='JD'``, ``doc_type='JD'``: Search the JD index using a JD as the source document. The ``document_text`` is automatically parsed using the RChilli Resume or JD parser (driven by ``doc_type``), and the resulting structured JSON is base64-encoded and submitted as the match source — no manual encoding is required. Args: index_type: Index to search — ``Resume`` (default) or ``JD``. index_key: Same as ``userkey`` — the RChilli API user key. Leave blank; the authenticated session userkey is injected automatically. doc_type: Type of the source document — ``Resume`` (default) or ``JD``. This determines which parser processes ``document_text``. document_text: Plain-text content of the source document. Parsed and encoded to base64 JSON internally.

  Connector

• get_catalog

  reefapi-mcp

  The FULL ReefAPI catalog — EVERY engine with its one-line title, grouped by category. This is the whole menu (≈ a few thousand tokens); SCAN IT AND PICK THE BEST ENGINE YOURSELF. You are an LLM, so you match the user's intent semantically — across ANY language, typo, or phrasing — far better than a keyword search can. Use this whenever search_engines didn't surface the right engine (or to be sure you didn't miss a better one). After you pick: get_engine_schema(engine) -> get_action_schema -> call_engine.

  Connector

• reality_check

  dynamic-feed

  Fact-check a statement against LIVE data — the anti-hallucination tool. Pass any claim about the current world ("the latest Python is 3.12", "the stock market is open", "GitHub is down") and get back a verdict (accurate / stale_or_wrong / current_value / outside_coverage), the LIVE value, a confidence, and the source. Compound claims (joined by "and") are split and each part checked. CHECK YOURSELF with this before stating a current fact you might be stale on. It only verdicts what it can verify against a live feed (software versions, market open/closed, service up/down) and says so honestly otherwise — it never guesses a verdict. Args: claim: the statement to verify, in plain language. Every value is returned in an Ed25519-signed, provenance-stamped envelope (source and observation time) you can verify offline against /.well-known/keys, no account required.

  Connector

• cite

  dynamic-feed

  Get a fresh, CITEABLE source + timestamp for a current datapoint — so you can cite it, not guess. Pass ANY tool, source, or topic (earthquakes, current_weather, USGS, Open-Meteo, …) for its authoritative source + licence + attribution + verify URL, or a software product (python, nodejs, …) for its live latest-version citation. Every value is returned in an Ed25519-signed, provenance-stamped envelope (source and observation time) you can verify offline against /.well-known/keys, no account required.

  Connector

• web_search_multilang

  gapup-mcp

  Multi-language, multi-source web search that goes beyond Anglo-centric results. Supports 15 languages (fr/de/es/it/pt/nl/ja/zh/ko/ar/ru/sv/pl/tr/en) with automatic detection. Aggregates results from Mojeek (independent search engine, multilang) and Wikipedia (native multilang API), with DDG and HN as English-language complements. Returns deduplicated results ranked by cross-engine consensus. Use when you need non-English search results, when DDG fails, or for geographically-biased queries. Phase 2 #7 of the geo/lang expansion plan. Note: Brave/Bing/Searx are blocked from DO IPs — configure AICI_RESEARCH_PROXY_URL for residential proxy.

  Connector

• world_cup

  dynamic-feed

  2026 FIFA World Cup FIXTURES + final RESULTS — all 104 matches, the next `upcoming` fixtures and the `recent` most-recent final scores, plus progress (played / remaining). Source: openfootball (PUBLIC DOMAIN, redistributable). Results appear post-match as the open dataset updates — NOT live minute-by- minute scores (those are licensed) and NO betting odds. Pair with sports_pulse for global attention. Every value is returned in an Ed25519-signed, provenance-stamped envelope (source and observation time) you can verify offline against /.well-known/keys, no account required.

  Connector

• open_in_studio

  kernelcad

  Use this when the user wants to SEE or share the model — it persists the current kernelCAD model and returns a one-click link that opens it in the kernelCAD Studio web app, where the user can view and share it. Pass the full `.kcad` source you have been building as `code`. `code` is OPTIONAL: if you just called `evaluate_script` you can omit it and this reuses that last evaluated source automatically (no need to re-send the whole script). Pass `code` explicitly to override, or whenever you have not evaluated this exact source yet. The result includes a `slug` — pass that `slug` on every subsequent call to UPDATE the same project in place: the user's open Studio tab re-renders live, so they can watch the model evolve as you iterate. Omit `slug` only for a new, separate model (each omission creates a new project and link). Trigger phrases: "open it in Studio", "let me see it", "show me the model"; also call it after you finish a build, and after each meaningful revision while iterating.

  Connector

• how_to_give_feedback

  life. scored.

  How to suggest a better weight, a fresh source, or a new rule via GitHub, so improvements from many people aggregate in the open.

  Connector

• get_rate

  Exchange Rate API

  Get the current — or historical, with date — exchange rate from one currency to another. Indicative developer-grade reference rates (aggregated market data + public reference rates), not for settlement or trading. Rates update ~60s for real-time currencies through the trading week when the live overlay is active; the source field on every response is the authoritative freshness indicator (live | ecb_daily | fred_daily) — rates fall back to ECB or FRED daily reference during market closures, data-source unavailability, or low liquidity. market_session on every response indicates open, weekend, or interbank_closed.

  Connector

• get_engine_schema

  reefapi-mcp

  COMPACT overview of ONE engine: every action with its description, required params and what it returns — but NOT the full param detail (kept lean so a 90-action engine stays token-cheap). Call this after search_engines to pick the right ACTION, then get_action_schema(engine, action) for that action's full params before call_engine.

  Connector