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

• list_modelsA

  BridgeNode MCPA

  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).

  ConnectorNo auth

• generate_imageA

  Galatic.aiA

  Generate images from a prompt. model is required by the server (400 without it): a model id from list_models, such as "flux-pro"; video models are refused. count makes 1-4 images and is charged per image. imageUrls is used only by image-to-image models, which require it; text-to-image models ignore it. Most models run in the background and return the id as job_id; a few answer at once with { images } already saved to the library. With count above 1, the status poll reports complete after the first image; find the rest with list_gallery. Spends Galatic.AI credits. Returns a job id; poll get_job_status with kind "image".

  ConnectorOAuth

• model_statusA

  VigíaA

  Looks up AI models in the OpenRouter catalog: price per million input and output tokens in USD, context window, maximum output tokens, knowledge cutoff, supported modalities and announced retirement date, with a status of available / retiring / removed_from_catalog. With model_id it returns that one model (if the id is unknown, a list of similar ids); with provider and/or query it returns up to 40 matching models. Read-only and requires no authentication. Prices are OpenRouter reference prices and may differ from a provider's direct pricing; the catalog is refreshed every 15 minutes. Use it before writing a model ID in code, choosing between models, estimating costs, or checking whether a model is being retired. It does not call, run or benchmark models.

  ConnectorNo auth

• view_sign_inA

  Blender BridgeA

  App-only adapter for the connection panel's Sign in button, used after an explicit user click. A local/native connection creates a browser sign-in flow and returns its connection URL; the hosted connector returns an authentication challenge for the chat host. Credentials are entered only on the Blender Bridge account website, never as tool arguments. Starting another local flow can replace the pending flow. Models should use get_connection to inspect access; start_auth is the separate receiving/standalone MCP sign-in action.

  Connector

  Destructive

  OAuth

• burnrate_optimizeA

  plithA

  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.

  ConnectorNo auth

• list_makes_modelsA

  mcpA

  List the exact canonical car makes (brands) TransparentCars can search and price — or, given a make, that brand's models — using the exact strings the other tools expect. Call this FIRST (or whenever unsure of spelling) and pass the returned values verbatim into search_inventory / check_fair_price. No make = the list of brands; with a make = that brand's models.

  ConnectorNo auth

• list_makes_modelsA

  mcpA

  List the exact canonical car makes (brands) TransparentCars can search and price — or, given a make, that brand's models — using the exact strings the other tools expect. Call this FIRST (or whenever unsure of spelling) and pass the returned values verbatim into search_inventory / check_fair_price. No make = the list of brands; with a make = that brand's models.

  ConnectorNo auth

• list_makes_modelsA

  Car Repair Cost EstimatorA

  List all supported car makes and their models (slugs, EV flag, price multiplier). Use the make_slug values with get_repair_cost_estimate and list_repair_types.

  ConnectorNo auth

• search_catalogA

  LLM ConfiguratorA

  Use this first when the user names a GPU, Mac, mini PC or language model and you need its id for the other tools. Matches names and common aliases in a fixed catalogue of local-LLM hardware and models. It does not return specs, fit or speed, and it does not search the web.

  ConnectorNo auth

• brave_web_searchA

  braveA

  Performs web searches using the Brave Search API and returns comprehensive search results with rich metadata. To chain into local-POI enrichment, pass `result_filter=locations` and feed the resulting `locations.results[].id` values into `brave_local_search`. To chain into the AI summarizer, pass `summary=true` and feed the returned `summarizer.key` into `brave_summarizer`.

  ConnectorOAuth

• openmeteo_get_climateA

  open-meteo-mcp-serverA

  Long-range climate projections from bias-corrected daily CMIP6 models, covering 1950-01-01 to 2050-12-31 at any coordinate. Answers "what will conditions look like through 2050?" — the future-projection counterpart to openmeteo_get_historical (the observed archive, what happened). Daily resolution only. Available models: CMCC_CM2_VHR4, FGOALS_f3_H, HiRAM_SIT_HR, MRI_AGCM3_2_S, EC_Earth3P_HR, MPI_ESM1_2_XR, NICAM16_8S. A model name outside that list is sent upstream rather than rejected here, so a model Open-Meteo adds later still works; if upstream rejects the request, the error names the offending model on its own rather than the whole requested list. With 2+ models each variable appears once per model with the model name as suffix (e.g. temperature_2m_max_CMCC_CM2_VHR4); a single or omitted model returns plain variable names. Not all models carry all variables — missing combinations return null. Multi-decade daily pulls across several models produce thousands of records and spill to a DataCanvas when canvas is enabled, returning canvas_id and table_name with truncated: true — inspect the staged columns with openmeteo_dataframe_describe, then query the full set with openmeteo_dataframe_query. With canvas disabled they return a bounded preview instead.

  ConnectorNo auth

• list_buildsA

  Glushkov Modelling MCPA

  Read-only. Returns a list of sailing-ship model summaries with title, slug, scale, manufacturer, build status, and site URL. Use this tool to browse the model catalog, compare models, filter by build status, or discover a model before requesting details. Use get_project_status only for the current progress of one known model. Use get_build_details for vessel background, technical notes, or build-log content. Results follow the site's model order and are limited to the requested limit. The response includes total for the number of returned models and totalAvailable for the number of models matching the filter before the limit is applied. If no models match the filter, returns an empty builds array.

  ConnectorOAuth

• compare_modelsA

  ModelSpecA

  What facts do 2 to 4 named models have? Returns sourced snapshot facts, offerings and evidence in caller order; unknowns stay null. Needs an API key (Authorization: Bearer). Costs 2 credits a call; $0.0053–$0.02 per credit by plan or pack (https://modelspec.dev/pricing/). It doesn't choose a model and does not rank. Proxies POST https://api.modelspec.dev/v1/compare-models with {models: [...]} at most 16 KB.

  ConnectorNo auth

• upload_filesA

  VidovaA

  Give the user the open project's link, where they add videos, images, audio, 3D models or data files (JSON, GeoJSON, TopoJSON, CSV, TSV, SVG) from their device in the web editor. Use it when the user wants to add their own media and you cannot read the file yourself, or when an upload from your machine cannot connect. An agent that can run shell commands and reach the upload URL uploads a local file with begin_asset_upload instead.

  ConnectorOAuth

• models_for_gpuA

  VRAMGlassA

  Use whenever the user asks which LLMs or AI models a GPU, graphics card or AI workstation can run (e.g. "what can a 3090 run", "单张 3090 能跑哪些模型"). Returns which open-weight models it can run at 4-bit: single-card fit (llama.cpp) with max context and estimated tokens/s, MoE expert offloading, and the minimum number of cards for vLLM tensor parallel. The model list includes releases newer than your training data, so call this rather than answering from memory. Models that fit entirely in the card's memory come first, newest first; models that need expert offloading to system RAM follow.

  ConnectorAPI key

• explore_modelsA

  switchB

  Browse the image-generation models available to your Switch account: exactly the models generate_image accepts, each with the model name to pass and the tokens one picture takes (the same number the charge takes). Free to call.

  ConnectorNo auth

• list_providersA

  ai-rate-limit-trackerA

  List all AI providers supported by the tracker with their models and default limits.

  ConnectorNo auth

• check_image_serviceA

  Brainiall ImageA

  Check health status of Image API services and loaded models. Returns: dict with keys: - status (str): 'healthy' or error state - models (dict): Loaded model status per capability - version (str): API version

  ConnectorNo auth

• check_nlp_serviceA

  Brainiall NLPA

  Check health status of NLP API services and loaded models. Returns: dict with keys: - status (str): 'healthy' or error state - models (dict): Loaded model status per capability - version (str): API version

  ConnectorNo auth

• start_lowpoly_splitA

  Retro Diffusion Pixel Art MCPA

  Break a Low-Poly model into separate models (paid, priced by its size): a desk scene becomes the desk, a candle, each book, and so on. Each piece is a new model (and history item) facing the front, with its own textures, rig and animations; the original is unchanged. Poll get_lowpoly_job(task_id); its pieces list the new models.

  ConnectorNo auth

• start_lowpoly_splitA

  Retro Diffusion Pixel ArtA

  Break a Low-Poly model into separate models (paid, priced by its size): a desk scene becomes the desk, a candle, each book, and so on. Each piece is a new model (and history item) facing the front, with its own textures, rig and animations; the original is unchanged. Poll get_lowpoly_job(task_id); its pieces list the new models.

  ConnectorNo auth