"Using llama.cpp and Searxng with local models" matching MCP tools:

• get_available_models

  Gonka Second Opinion (multi-model)

  List all AI models available on Gonka Network with live pricing. Models work as drop-in replacements for OpenAI and Anthropic — same SDK, same API calls. Use this when user asks which model to use or wants alternatives to GPT-4o / Claude. Returns: model IDs (use directly in openai.chat.completions.create), status, USD per 1M tokens. After this: call calculate_savings() to see annual savings with these models.

  Connector

• list_models

  BridgeNode MCP

  List available models and their prices — free, no payment, no authentication required. Read-only: no state changes; data is served from the server's local config, so repeated calls return identical results (idempotent). Accepts no parameters: the input schema is an empty object, and any arguments passed are ignored. Calling it without arguments returns the complete catalog with per-token prices; there is no filtering, pagination, or configuration. Use this tool to inspect models and prices before calling the paid chat_completions tool. Same data as GET /v1/models (§5.2). Do not use it to generate text (use chat_completions) or to estimate a specific request's cost (use get_price_estimate).

  Connector

• axint.registry.search

  Axint

  Search the Axint Registry for already-published packages that match a natural-language query. Use this BEFORE calling axint.feature or axint.compile so the agent can install an existing package instead of regenerating Swift the community has already shipped. Use: use before generating code to find reusable packages; not for validating local Swift. Inputs: query drives ranking; kind and platform narrow results without changing the registry source. Effects: read-only local registry search using AXINT_REGISTRY_PATH or sibling checkout; no network by default.

  Connector

• create_snapshot

  BorealHost

  Create a local container snapshot (async). Runs in background — returns immediately with status "creating". Poll list_snapshots() to check when status becomes "completed" or "failed". Available for VPS, dedicated, and cloud plans (any plan with max_snapshots > 0). Local snapshots are stored on the host disk and count against disk quota. Requires: API key with write scope. Args: slug: Site identifier description: Optional description (max 200 chars) Returns: {"id": "uuid", "name": "snap-...", "status": "creating", "storage_type": "local", "message": "Snapshot started. Poll list_snapshots() to check status."} Errors: VALIDATION_ERROR: Max snapshots reached or insufficient disk quota

  Connector

• compare-llm-models

  OptimToken

  Browse and filter the whole LLM catalogue and get back a ranked table: price, quality (ELO), efficiency and capabilities. Use this when the user wants to SEE THE FIELD — 'show me models under $1/1M', 'which providers have vision models', 'list open-weight models above ELO 1300'. For a single PICK under a budget use recommend-llm-model; to weigh 2-4 NAMED models against each other use compare-models-side-by-side. Prices come from optimtoken.optimnow.io where reachable; the response's `provenance` says which tier served them and whether they are vendor-verified. Filter by provider, price tier (category), openness, capability, price range, or minimum ELO score. Optionally enrich with business metrics for a use case. Price tier and openness are independent: a model can be Frontier-priced and open-weight at once. Reports both list-price cost and the optimized cost achievable with prompt caching and the batch API. IMPORTANT: Report all prices, costs, and scores EXACTLY as returned. Do NOT add commentary, opinions, or recommendations beyond what the data shows. Present the results as a table and let the user draw conclusions.

  Connector

• burnrate_optimize

  plith

  Get a cheaper equivalent plan by substituting models with lower-cost alternatives. Call after burnrate_estimate if the estimated cost exceeds your budget. Returns the optimized plan with substituted models, new per-step costs, total savings, and whether the target_budget is met. Optionally set target_budget to constrain the optimization. Costs 1 credit.

  Connector

• get_region_signal

  Horizon AI Intelligence

  The current AI signal for a region (china, korea, japan, or eu) — recent, relevance-scored items on that region's models, labs, and analysis, ranked by momentum. Includes local-language press translated into English. The canonical regional tool; get_china_signal is a preset of this with region "china". Returns titles, sources, and links.

  Connector

• dev_send

  Arcadia Finance

  DEV ONLY — Sign and broadcast an unsigned transaction using a local private key (PK env var). For production, use a dedicated wallet MCP server (Fireblocks, Safe, Turnkey, etc.) instead of this tool. Takes the transaction object returned by any write.* tool and submits it onchain.

  Connector

• list_models

  ScanBIM MCP

  List every object currently stored in the scanbim-models OSS bucket, with URN, size in MB, and a viewer URL for each. Returns the raw OSS inventory, not the D1 models table, so freshly uploaded items appear immediately. When to use: you need to enumerate previously uploaded models to find a URN, show an inventory, or pick one for a follow-up tool call. When NOT to use: you already know the exact URN — call get_model_metadata directly. This tool is not a search; it returns up to the OSS default page (typically first 10 objects unless OSS paginates). APS scopes: bucket:read data:read Rate limits: APS default ~50 req/min per app per endpoint; Model Derivative translation jobs ~60 req/min; OSS uploads size-limited per file to 100MB for direct upload, larger via resumable. Errors: 401 APS token expired/invalid — refresh; 403 scope or resource permission denied; 404 bucket not found — no models have been uploaded yet (upload one first); 429 rate limited — backoff and retry; 5xx APS upstream outage — retry with jitter. Side effects: READ-ONLY. Idempotent.

  Connector

• report

  kansei-mcp-server

  Record what happened after using a service: success/failure outcome, feedback, API change events, or qualitative experience. Data is saved to this installation's LOCAL database only (improves local recovery hints and stats) — nothing is sent to KanseiLink unless you separately opt in to sharing. PII is auto-masked before storage. This is step 4 of the standard flow: search_services → lookup → (execute) → report.

  Connector

• kanji.toKana

  Torify — Japan Locale APIs for AI Agents

  Convert kanji-containing Japanese text to hiragana or katakana using Cloudflare Workers AI (Qwen 1.5 14B, Japanese/Chinese optimized). 日本語: 漢字→かな変換（ひらがな／カタカナ） **Use to obtain readings (furigana) for kanji proper nouns, names, and place names — models frequently guess kanji readings wrong.**

  Connector

• generate_text

  Sats4AI - Bitcoin-Powered AI Tools

  Generate text using frontier AI language models. Pure per-character pricing (no minimum): Kimi K3 (best, ~10 chars/sat, 1M context, vision support, default), GPT-OSS-120B (standard, ~1000 chars/sat, 119 languages, best value). Rates are BTC-pegged and re-quoted hourly, so treat them as approximate — the 402 challenge is the authoritative price. Supports document Q&A via fileContext and vision analysis via imageBase64 (best model). Stable endpoints — models upgrade automatically. Pay per request with Bitcoin Lightning — no API key or signup needed. Requires create_payment with toolName='generate_text' and the exact prompt.

  Connector

• list_models

  Sats4AI - Bitcoin-Powered AI Tools

  Discover available AI models with numeric IDs, tier labels, capabilities, and per-call pricing in sats. Call this before create_payment to find the right modelId for your task. Returns JSON array: [{ id, name, tier, description, price, isDefault, category }]. Models marked isDefault=true are used when you omit modelId from create_payment. Filter by category to narrow results to a specific tool. This tool is free, requires no payment, and is idempotent — safe to call repeatedly.

  Connector

• user_agent_parse

  mcp

  Context lookup: Parse a User-Agent header string into structured browser, OS, device type, and rendering-engine components. Use to identify client capabilities from a raw UA string, e.g. when analysing server logs or request headers; does not perform any network lookups — entirely local parsing. Runs synchronously using the ua-parser-js library with no external calls. Returns a JSON object with browser.name, browser.version, os.name, os.version, device.type, device.vendor, and engine.name fields; unknown fields are empty strings.

  Connector

• compute.models

  DPX — Institutional Cross-Border Settlement

  List all AI models available through DPX Compute. All models are free-tier (no token cost) — routed via OpenRouter. Returns model IDs, provider, capability strengths, context window, and speed tier. Use this before compute.route to understand what models are available and pick the right one for a task. Free.

  Connector

• list_models

  CCAPI

  List the AI models this CCAPI key can actually call, with their capability category and the MCP tool that drives them. Call this before generating anything if you are unsure a model name is valid — availability depends on the key's group and changes over time. Never guess model names.

  Connector

• list_vendors

  EOSL.ai — Hardware End-of-Life Database

  List all vendors tracked by EOSL.ai with family counts and vendor page URLs. Read-only, no parameters. Use this first to check whether a vendor is covered at all; for specific models use search_models, for a part number use lookup_part.

  Connector

• local_vehicle_safety_profile

  NHTSA Vehicle Safety

  Get a vehicle safety profile using national complaint and recall trends. NHTSA complaints are not geocoded by state, so this returns national-level trends as context for local community safety assessments. Includes the most recent recalls and top complained-about vehicle makes. Args: state: Two-letter state abbreviation (e.g. 'CA', 'TX'). Used for crash statistics; complaint data is national.

  Connector

• create_flow

  CNAPS.ai MCP Server

  Create a flow. Provide the models in order — input/output nodes and connections are generated automatically by matching output→input port types, and the original input is shared (fan-out) when several models need it. Set run=true to start it immediately in the same call.

  Connector

• upload_avatar_from_chat_file

  Uwear

  Batch upload reusable avatars/models from person photos the user attached in chat. Each photo becomes the upper_body_front identity anchor. Keep names and optional user-given age_range, build, and height_cm in avatars[], then pass top-level image_file_1, image_file_2, etc. in the same order. Traits are never guessed. No base64, no local paths. Do not use ordinary text-to-image results as an upload fallback; use generate_avatar followed by save_generated_avatar for Uwear-created avatars. Use only when the user explicitly wants a specific or consistent person.

  Connector