"Local small language model for filesystem and network tasks" matching MCP tools:

• picsart_enhance

  Picsart GenAI

  Upscales and enhances an image — sharpens edges, denoises, and raises resolution by an optional scale factor. Auto-picks the newest enabled Picsart upscale / enhance model unless overridden via the `model` param. Use this when the user asks to "upscale", "enhance", "make it higher resolution", "sharpen", "clean up this photo", or "make this 4k". Do NOT use this to remove the background (use `picsart_remove_bg`), replace the background (use `picsart_change_bg`), convert raster to SVG (use `picsart_vectorize`), or generate a new image (use `picsart_generate`). Required input: `image` — a publicly-accessible URL, not a local file path. Optional: `model` to pin a specific enhance model, `scaleFactor` (e.g. 2 or 4) for upscale ratio. Example: `{ image: "https://example.com/photo.jpg", scaleFactor: 4 }`. Returns `{ assets, id, model, created_at, summary, why_relevant, url, results: [{ url, metadata? }], drive? }` plus a `resource_link` block per result URL. `id` is the SDK's generation handle; `metadata` may include model-specific tags. Spends credits. Requires Authorization: Bearer <picsart_token>.

  Connector

• check_local_viability

  Local Model Suitability MCP

  Checks whether a task can be handled by a local model instead of a cloud API. Call this BEFORE your agent routes any task to a cloud model — at the moment a task is ready to be sent and the model has not yet been selected. Use this when your agent is about to make a cloud inference call and wants to determine whether a local model could handle it at lower cost. Returns LOCAL/CLOUD/EITHER verdict with recommended model. If verdict is LOCAL, skip the cloud call entirely — saves cost on every routable inference call. Pass data_sensitivity=CONFIDENTIAL to force LOCAL verdict for tasks that must not leave the machine. Do not route to cloud without checking local viability first.

  Connector

• upload_media

  SendIt

  FOR CLAUDE DESKTOP ONLY (with filesystem access). For Claude.ai/web: Use create_upload_session instead - it provides a browser upload link. Upload local media to cloud storage, returning a public HTTPS URL. WHEN TO USE: • Instagram, LinkedIn, Threads, X: REQUIRED for local files before calling publish_content • TikTok: NOT NEEDED - pass local path directly to publish_content SUPPORTED FORMATS: • Images: jpg, png, gif, webp (max 10MB) • Videos: mp4, mov, webm (max 100MB) Returns { url: 'https://...' } for use in publish_content mediaUrl parameter.

  Connector

• fvs_download_final_video

  Future Video Studio

  Download a completed Future Video Studio final render URL to a local file. Use this only after fvs_get_render_status or fvs_get_paid_render_status returns a final_video_url for a completed render. The tool performs an unauthenticated HTTPS GET to that signed URL and writes the response bytes to output_path on the MCP server's local filesystem. It does not call the FVS Agent API, spend wallet credits, require FVS_AGENT_API_KEY, cancel jobs, or modify remote render state. Side effects and constraints: output_path is a local filesystem path for the MCP server process, parent directories are created, existing files are not replaced unless overwrite is true, and large videos may take minutes to download. The request timeout is 600 seconds. Use a fresh status check to refresh expired signed URLs, and do not pass arbitrary or untrusted URLs.

  Connector

• query_tasks

  cnvs.app

  Read tasks from a 'todo' board with server-side filtering — handy for 'what's overdue?' / 'what's assigned to X?' without pulling the whole board. All filters are optional and AND together: `assignee` (exact match), `priority` ('H'|'M'|'L'), `done` (boolean), `overdue` (true → due_date strictly before today, not done), `due_before` / `due_after` (ISO date window on due_date). Returns `{ boardId, mode, tasks }` — tasks ordered by sort, each with the same fields as `list_tasks`.

  Connector

• check_text

  Writing Style Checker

  Analyze text for writing style issues: weasel words, passive voice, duplicate words, long sentences, nominalizations, hedging, filler adverbs, and research-cited AI tells. Read-only and stateless — text is analyzed in memory on the hosted server and never stored. Returns a plain-text report with each issue's line and column, the matched text, surrounding context, and the reason for AI tells; texts over 100,000 characters return an error message. This hosted server has no filesystem access — the wsc-mcp npm package adds a check_file tool for local files. It only reports issues — to auto-remove duplicate words, follow up with fix_duplicates.

  Connector

• run_code

  coremodels

  Execute a JavaScript program that orchestrates this server's tools, and return only its result. Prefer this over many individual tool calls when a task needs several steps, looping, filtering, or combining data: intermediate results stay in the sandbox, so only what you return reaches the model. Inside the script: - listTools() -> [{name, summary}] discover available tools - getToolDoc(name) -> {name, description, parameters, required} inspect one tool's inputs - tools.<name>(args) -> parsed result call a tool (graphProjectId is injected automatically; do NOT pass it) - console.log(...) captured and returned alongside the result - return <value> JSON-serialized and returned Environment: sandboxed JavaScript, no network or filesystem, with limits on time, memory, statements and number of tool calls. Currently only read-only tools are callable from code.

  Connector

• free2aitools_select_model

  Free2AITools

  Filter the Free2AITools catalog by declared hardware/license metadata and return FNI-ranked candidate entries. USE WHEN you have concrete constraints (VRAM, params, license, context length, local-runnability) and want candidates narrowed by them. Constraints are metadata/heuristic filters over stored fields, NOT verified compatibility analysis, model inference, or model execution; this tool does not decide for you and is not an inference router. The caller is responsible for the final selection. Results are FNI-ranked, never paid placement, with no billing. Read-only, no side effects. Use free2aitools_search for unconstrained keyword discovery, or free2aitools_rank for keyword ranking without metadata filters.

  Connector

• portal_list_networks

  SQD Portal

  Find the right network or chain name to use across EVM, Solana, Bitcoin, Substrate, and Hyperliquid. COMMON USER ASKS: - Find Base-like networks - Show Solana mainnets - Show Substrate mainnets FIRST CHOICE FOR: - finding the correct network before any other query WHEN TO USE: - You are not sure which network name, chain name, or alias to use. - You want to filter networks by VM family, network type, or real-time availability. DON'T USE: - You already know the exact network and want live data from that network. EXAMPLES: - Find Base-like networks: {"query":"base","limit":10} - Show Solana mainnets: {"vm":"solana","network_type":"mainnet"} - Show Substrate mainnets: {"vm":"substrate","network_type":"mainnet"}

  Connector

• picsart_preflight

  Picsart GenAI

  Free pre-flight check before `picsart_generate`: in ONE call it (1) validates a candidate params object against the model's parameter schema + inter-parameter constraints, and (2) quotes the credit cost — without running the model or charging the user. Use this after assembling params (user input, derived defaults, model swaps) and before generating, to surface bad arguments and show cost. Do NOT use it to look up which params a model accepts (use `picsart_model_params`) or to actually generate (use `picsart_generate`). Required inputs: `model` id and a `params` object (put the `prompt` inside `params`). Example: `{ model: "flux-2-pro", params: { prompt: "a cat in a hat", aspectRatio: "16:9", count: 1 } }`. Returns `{ model, valid, errors?, credits }`: `valid`/`errors` are from local validation (always present, no auth needed; `errors` only when invalid); `credits` is the dry-run cost (a number), or `null` when pricing is unavailable or the request is unauthenticated.

  Connector

• run_code

  CoreModels

  Execute a JavaScript program that orchestrates this server's tools, and return only its result. Prefer this over many individual tool calls when a task needs several steps, looping, filtering, or combining data: intermediate results stay in the sandbox, so only what you return reaches the model. Inside the script: - listTools() -> [{name, summary}] discover available tools - getToolDoc(name) -> {name, description, parameters, required} inspect one tool's inputs - tools.<name>(args) -> parsed result call a tool (graphProjectId is injected automatically; do NOT pass it) - console.log(...) captured and returned alongside the result - return <value> JSON-serialized and returned Environment: sandboxed JavaScript, no network or filesystem, with limits on time, memory, statements and number of tool calls. Currently only read-only tools are callable from code.

  Connector

• x711_code_sandbox

  x711 — Universal Agent Gas Station

  Execute JavaScript or Python code in an isolated sandbox. Use for: data processing, math, CSV parsing, JSON transformation, crypto calculations, algorithm testing. Secure — no filesystem access, no network. Returns: { output: string, runtime_ms: number, language: string }. Requires API key.

  Connector

• pathrule_read_memory

  Pathrule

  Read the full body and metadata for one Pathrule memory. Use this after pathrule_get_context, pathrule_goto, or pathrule_list_memories returns a memory_id. This reads cloud data only and does not inspect the user's local filesystem.

  Connector

• gdelt_get_coverage_breakdown

  gdelt-mcp-server

  Break down news coverage volume over time by source language or source country, returning a multi-series time series (one series per language or country). Shows which countries or languages drove early vs. late coverage — useful for tracing how a story propagated geographically or across language communities. Returns up to 10 series by total volume and aggregates the rest into an "Other" bucket, naming every series it folded in there under otherSeriesLabels — pass any of those labels back as the series input to get that series complete, ranked or not. Values are normalized: each point is the topic's share of media output, not an absolute article count. Small media markets with concentrated coverage therefore rank above large markets with diverse output — a high value means the topic dominated that source's coverage, not that it published the most articles. Use breakdownBy "country" with the signal-detection chain to map geographic attention, or "language" to detect non-English media surges.

  Connector

• assessment_review_report

  website-search

  Get Lenny Zeltser's expert criteria for reviewing an existing security assessment report or brief. Surfaces the 17 info-assessment review items across five groups (Key Takeaways, Assessment Scope, Prioritized Findings, Remediation Suggestions, Assessment Methodology), cross-cutting criteria, the risk-adjusted severity model, anti-patterns, and a pointer to rating_score_writing for a numeric score. This server never requests your assessment notes or report and instructs your AI to keep them local—the templates and guidelines flow to your AI for local analysis.

  Connector

• create_tasks

  Plate

  Create multiple tasks in a project in one action. Use this instead of calling create_task multiple times when the user asks to create several tasks at once. All tasks are created atomically — if validation fails for any item, nothing is created.

  Connector

• livonian_romanize

  hub

  Strip Livonian orthography down to clean, pronounceable ASCII for an English-trained downstream (a voice/TTS, a search box). See the `text` parameter doc for the exact letter mappings. Returns Markdown plus the romanized output as structuredContent matching the declared outputSchema. Pure local transform: no dictionary lookup, no network, and the output is always ASCII.

  Connector

• slavonic_transliterate

  hub

  Render Church Slavonic — Cyrillic or Glagolitic — in the scientific Latin transliteration Wiktionary uses (богъ → bogŭ, ⰱⱁⰳⱏ → bogŭ). Liturgical reading marks (titlos, accents) are dropped and late Church Slavonic spellings folded, so copied liturgical text works as-is. Returns Markdown plus the transliterated output as structuredContent matching the declared outputSchema. Pure local transform: no dictionary lookup and no network.

  Connector

• fs_read

  local-mcp

  Reads a text file from the local filesystem. Supports .txt, .md, .csv, .json, .xml, .log, .yaml, .toml and common code file types. For PDFs use pdf_read, for Word use word_read, for Excel use excel_read.

  Connector

• get_case_tasks

  mcp-server

  List the open tasks (action-items) attached to one specific case — same data as list_tasks, scoped to a single case. Use this when you're already working a specific case and want just its outstanding tasks. Note: account-level tasks that aren't tied to any one case (e.g. SignContract, AssignBankAccount — these block the whole account, not one case) never appear here; use list_tasks to see those. See list_tasks for the full task model (auto-resolve, solutionUrl, action).

  Connector