"SearXNG, a privacy-respecting metasearch engine" matching MCP tools:

• kirk_list_models

  Kirk — Unsupervised Structural Change Detection

  Enumerate the model_ids the sealed engine exposes, with the engine sha stamped in-response. Purpose: Discover the model catalog and record the sealed engine sha alongside your inference results. Use when: You are wiring a client for the first time and need model_id values for kirk_score_book / kirk_score_book_batch calls, or you want a machine-readable catalog with attestation. Do not use when: You need per-model hyperparameter detail — those are intentionally not exposed on the customer surface. Capability class(es): C5 (engine sha attested on every response). Path fit: Validation via MCP (this tool). Production integrations run in-process under sealed-engine attestation — same binary sha as this endpoint. Contact Kavara for deployment options. Cost: 0 IU. Free tool.

  Connector

• engine_info

  Backtest360

  Engine version, API contract number, and health. Free (not quota-counted). Call once at the start of a session to confirm the engine is reachable and which contract it serves.

  Connector

• list_compiled_corridors

  lr-labs

  List which treaty pairs, PE families, and compiled-rule counts the LR Labs engine covers, plus the structured-fact schema. Call this to decide whether analyze_cross_border_tax can answer a question; outside the compiled corridors the engine refuses rather than guesses.

  Connector

• post_to_youtube

  Hermoso

  Publish a finished video to the brand’s connected YouTube channel. Pass a Hermoso render URL (or an upload_file url for a local/external file). DEFAULTS TO UNLISTED (link-only — not on the channel, not searchable, but shareable by link AND usable as a YouTube/Google ad). Pass privacy:"public" to put it ON the channel (a public publish — confirm with the user first) or privacy:"private" for eyes-only. Do NOT use "private" for anything meant to run as an ad — private videos CANNOT be used as ads; unlisted is the ad-ready setting. SCHEDULE it with publishAt, FILE it under the right categoryId (the default 22 "People & Blogs" is wrong for most ads), SUBSCRIBER NOTIFICATIONS FOLLOW PRIVACY — a public publish announces the video to the channel’s subscribers (YouTube’s own default), while unlisted/private uploads stay quiet; pass notifySubscribers explicitly to override either way. Needs a connected YouTube channel (Settings ▸ Connectors ▸ YouTube).

  Connector

• generate_voice

  Hermoso

  RAW text-to-speech from the voice-model catalog: speak a script in a chosen voice and return the served MP3 URL. For a standalone voiceover / narration clip — NOT for adding audio to a video (render_ad and generate_video voice their own spots; change_voice re-voices a finished clip). engine picks the voice model (default 'seed-audio'; also 'eleven-v3', 'minimax-speech', 'kokoro'); voice is a preset name from that engine (see hermoso_capabilities → voice engines) — a name that engine does not have is REFUSED for free with its real list, and a few engines generate their own voice and take no preset at all (the reply says which voice actually spoke). Paid (a couple of credits by length; ≤900 characters).

  Connector

• get_product_recommendation

  Custom Blinds Shop

  Translate a customer's primary concern into a product recommendation. primary_concern must be one of: blockout, heat, glare, moisture, privacy, security, automation. Optionally narrow by room (bedroom, lounge, etc.), location, budget, and aesthetic. Returns a recommended product_id with rationale — pass it to get_price or configure_product next. Security concern routes to brochure MCP (Garden Route customers only).

  Connector

• kirk_verify_engine

  Kirk — Unsupervised Structural Change Detection

  Verify sealed engine identity — returns the sha256 of the running scoring binary. Also serves as a liveness probe against the sealed backend. Purpose: Attest which Kirk build is currently serving scoring calls. Response carries the sealed engine sha (kirk_version) that will stamp any subsequent kirk_score_* result. Secondary role: a cheap liveness probe for callers wiring up MCP for the first time. Use when: You want to record engine sha in your own provenance log before capturing scoring output, or you want a cheap liveness check ahead of a larger validation batch. Do not use when: You want a scoring result — this returns identity/liveness only, no entropies. Capability class(es): C5 (cryptographic attestation of engine identity). Path fit: Validation via MCP (this tool). Production integrations run in-process under sealed-engine attestation — same binary sha as this endpoint. Contact Kavara for deployment options. Cost: 0 IU. Free tool. For agent-driven callers, the _cost envelope still reports iu_this_call=0 and the running session totals. Returns: Dict with `status`, `engine`, `env`, and `kirk_version` (the sealed .so sha). A non-2xx response raises; caller sees a clean MCP tool error.

  Connector

• domain_settings

  BorealHost

  Update domain settings (auto-renew, WHOIS privacy, registrar lock). Only provided (non-None) fields are updated. Requires: API key with write scope. Args: domain_name: Full domain name (e.g. "example.com") auto_renew: Enable/disable automatic renewal whois_privacy: Enable/disable WHOIS privacy protection locked: Enable/disable registrar lock (prevents unauthorized transfers) Returns: {"success": true, "domain": "example.com", "auto_renew": true, "whois_privacy": true, "locked": true} Errors: NOT_FOUND: Domain not found or not owned by account

  Connector

• tiktok_creator_info

  Hermoso

  Read the connected TikTok creator’s REAL posting options BEFORE posting: which privacy levels THEY are allowed to use, whether comments / duet / stitch are available on their account, their maximum video length, and their nickname. TikTok REQUIRES that the user is shown these actual options and picks a privacy level — never assume or default one. Call this first, show the options, get the user’s pick, then call post_to_tiktok with destination:"post". The SAME privacy options govern PHOTO posts (slideshows), not just video — TikTok takes the same four levels on both. Needs TikTok connected (Settings ▸ Connectors ▸ TikTok).

  Connector

• format_batch

  Caliper

  Analyze multiple geometry files in a single batch request. Submit up to 10 files, receive a single quote, pay once, and get structured metadata for all files. Supports mixed formats. Read-only analysis — does not modify, convert, or repair files. Payment is required via x402 (USDC on Base) or card via MPP (Stripe). If no payment is provided, the response includes the total price and per-file breakdown. Retry with the payment argument containing "transaction", "network", and "priceToken". Partial success: if some files fail processing, you still receive results for the files that succeeded. Privacy policy: https://caliper.fit/privacy

  Connector

• get_engine_schema

  ReefAPI

  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

• call_engine

  ReefAPI

  Call a ReefAPI engine action — POST /<engine>/v1/<action> with `params`. Returns the uniform { ok, data, meta, error } envelope. Get param names from get_engine_schema first. Needs YOUR ReefAPI key (the local server reads REEFAPI_KEY; the hosted server reads the `Authorization: Bearer ak_live_...` header you configure on the connection). Get a key at https://reefapi.com. Failed calls cost no credits.

  Connector

• get_catalog

  ReefAPI

  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

• 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_security_info

  Fluentive MCP

  Returns Fluentive's security, privacy, and compliance information. Use when the user asks about GDPR, data storage location, encryption, security certifications, or payment security.

  Connector

• axint.repair

  Axint

  Plan a project-aware Apple repair for existing apps. Indexes the local project, classifies build/UI/runtime evidence, runs Cloud Check when source is provided, ranks likely SwiftUI/App files, returns a host-aware patch/proof plan, and writes .axint/repair plus a privacy-safe .axint/feedback packet. Use: use for existing app bugs with logs, UI symptoms, or runtime evidence; not for greenfield generation. Inputs: describe the observed bug and attach logs or evidence; modifiedFiles and project index narrow the plan. Effects: writes .axint/repair and privacy-safe .axint/feedback artifacts; reads local project files.

  Connector

• approve_message

  LinkedIn MCP Server (Salesbot)

  Approve a draft and hand it to the campaign executor for sending (respecting daily limits and allowed hours). Optionally pass edited_messages to overwrite specific drafts before approval. By default each draft is verified by a second-pass quality check (Czech vocative, hallucinations, prompt adherence) — set skip_gpt_check=true to bypass. If the quality check rejects the message, the draft is automatically sent back for a rewrite based on the feedback.

  Connector

• redact

  concordance

  Strip PII (emails, SSNs, credit cards, IPs, URLs) from text to stable placeholders before you pass it onward; the mapping is returned so YOU reveal replies locally. For true privacy run this on a LOCAL/sovereign engine (the text never leaves your machine) or use the client libraries — the strip belongs at your edge. Deterministic; pair with verify for a receipt.

  Connector

• get_grade_distribution

  NTNU Courses (unofficial)

  Historical grade distribution for an NTNU course (per year and semester, with counts and percentages; grades A-F, or pass/fail codes). Accepts bare codes like 'TDT4100'. Omit years to get all recorded years. Small counts may be privacy-masked. Data comes from Norway's official DBH statistics.

  Connector

• legal_get

  ComOS Federation Gateway

  Fetch a ComOS legal instrument as raw markdown: the Terms of Service, Privacy Policy, Data Processing Agreement (DPA), or a one-page Data Retention Summary. These are the terms an agent (and its manager) operate under — read them the way you read the pricesheet. Public and read-only; discloses, does not gate. Argument `document` is one of: terms | privacy | dpa | retention. CO 311. Returns: The requested legal instrument as raw markdown. Example: call legal_get with arguments {"document":"<document>"}.

  Connector