"How to run desktop commands on a computer" matching MCP tools:

• canary_scan

  canaryusers

  Run a CanaryUsers UX scan on a DEPLOYED URL (your live or preview app — not source code). A flock of AI personas evaluates the page and reports where real users would get stuck, with concrete fixes. Returns AI-ready findings you can act on immediately. Use depth='deep' for the thorough scan that renders the page, checks it VISUALLY on desktop + mobile (catches mobile breakage and layout issues), and clicks through key flows like signup/checkout (slower, ~60-90s, uses one credit); depth='quick' (default) is a fast static check that does NOT see mobile or visual issues — use 'deep' when the user mentions mobile, layout, or visual problems. IMPORTANT: if this returns status 'running' with a scanId, the findings are not ready yet — wait ~30s, then call get_report_markdown(scanId), repeating until it returns the report. Always fetch and present the findings before stopping, then offer to fix the top issues.

  Connector

• query_docs_filesystem_n_top

  docs

  Run a read-only shell-like query against a virtualized, in-memory filesystem rooted at `/` that contains ONLY the nTop documentation pages and OpenAPI specs. This is NOT a shell on any real machine — nothing runs on the user's computer, the server host, or any network. The filesystem is a sandbox backed by documentation chunks. This is how you read documentation pages: there is no separate "get page" tool. To read a page, pass its `.mdx` path (e.g. `/quickstart.mdx`, `/api-reference/create-customer.mdx`) to `head` or `cat`. To search the docs with exact keyword or regex matches, use `rg`. To understand the docs structure, use `tree` or `ls`. **Workflow:** Start with the search tool for broad or conceptual queries like "how to authenticate" or "rate limiting". Use this tool when you need exact keyword/regex matching, structural exploration, or to read the full content of a specific page by path. Supported commands: rg (ripgrep), grep, find, tree, ls, cat, head, tail, stat, wc, sort, uniq, cut, sed, awk, jq, plus basic text utilities. No writes, no network, no process control. Run `--help` on any command for usage. Each call is STATELESS: the working directory always resets to `/` and no shell variables, aliases, or history carry over between calls. If you need to operate in a subdirectory, chain commands in one call with `&&` or pass absolute paths (e.g., `cd /api-reference && ls` or `ls /api-reference`). Do NOT assume that `cd` in one call affects the next call. Examples: - `tree / -L 2` — see the top-level directory layout - `rg -il "rate limit" /` — find all files mentioning "rate limit" - `rg -C 3 "apiKey" /api-reference/` — show matches with 3 lines of context around each hit - `head -80 /quickstart.mdx` — read the top 80 lines of a specific page - `head -80 /quickstart.mdx /installation.mdx /guides/first-deploy.mdx` — read multiple pages in one call - `cat /api-reference/create-customer.mdx` — read a full page when you need everything - `cat /openapi/spec.json | jq '.paths | keys'` — list OpenAPI endpoints Output is truncated to 30KB per call. Prefer targeted `rg -C` or `head -N` over broad `cat` on large files. To read only the relevant sections of a large file, use `rg -C 3 "pattern" /path/file.mdx`. Batch multiple file reads into a single `head` or `cat` call whenever possible. When referencing pages in your response to the user, convert filesystem paths to URL paths by removing the `.mdx` extension. For example, `/quickstart.mdx` becomes `/quickstart` and `/api-reference/overview.mdx` becomes `/api-reference/overview`.

  Connector

• setup_local_crypto

  seekrit — secrets for agents

  Get the exact commands for running the local crypto plane (the `@seekrit/mcp` npm server, the `@seekrit/cli` CLI, seekrit-run, seekrit-proxy), including a copy-paste .mcp.json that reuses this session's credential. Takes no arguments and returns prose plus config. Call this the moment you need to SET or READ a secret value — no tool on this server will ever return one. Use local_tool_for instead when you want the single command for one named operation.

  Connector

• query_docs_filesystem_site_gpt_docs

  SiteGPT Docs

  Run a read-only shell-like query against a virtualized, in-memory filesystem rooted at `/` that contains ONLY the SiteGPT Docs documentation pages and OpenAPI specs. This is NOT a shell on any real machine — nothing runs on the user's computer, the server host, or any network. The filesystem is a sandbox backed by documentation chunks. This is how you read documentation pages: there is no separate "get page" tool. To read a page, pass its `.mdx` path (e.g. `/quickstart.mdx`, `/api-reference/create-customer.mdx`) to `head` or `cat`. To search the docs with exact keyword or regex matches, use `rg`. To understand the docs structure, use `tree` or `ls`. **Workflow:** Start with the search tool for broad or conceptual queries like "how to authenticate" or "rate limiting". Use this tool when you need exact keyword/regex matching, structural exploration, or to read the full content of a specific page by path. Supported commands: rg (ripgrep), grep, find, tree, ls, cat, head, tail, stat, wc, sort, uniq, cut, sed, awk, jq, plus basic text utilities. No writes, no network, no process control. Run `--help` on any command for usage. Each call is STATELESS: the working directory always resets to `/` and no shell variables, aliases, or history carry over between calls. If you need to operate in a subdirectory, chain commands in one call with `&&` or pass absolute paths (e.g., `cd /api-reference && ls` or `ls /api-reference`). Do NOT assume that `cd` in one call affects the next call. Examples: - `tree / -L 2` — see the top-level directory layout - `rg -il "rate limit" /` — find all files mentioning "rate limit" - `rg -C 3 "apiKey" /api-reference/` — show matches with 3 lines of context around each hit - `head -80 /quickstart.mdx` — read the top 80 lines of a specific page - `head -80 /quickstart.mdx /installation.mdx /guides/first-deploy.mdx` — read multiple pages in one call - `cat /api-reference/create-customer.mdx` — read a full page when you need everything - `cat /openapi/spec.json | jq '.paths | keys'` — list OpenAPI endpoints Output is truncated to 30KB per call. Prefer targeted `rg -C` or `head -N` over broad `cat` on large files. To read only the relevant sections of a large file, use `rg -C 3 "pattern" /path/file.mdx`. Batch multiple file reads into a single `head` or `cat` call whenever possible. When referencing pages in your response to the user, convert filesystem paths to URL paths by removing the `.mdx` extension. For example, `/quickstart.mdx` becomes `/quickstart` and `/api-reference/overview.mdx` becomes `/api-reference/overview`.

  Connector

• query_docs_filesystem_cerebrium

  Cerebrium Docs

  Run a read-only shell-like query against a virtualized, in-memory filesystem rooted at `/` that contains ONLY the Cerebrium documentation pages and OpenAPI specs. This is NOT a shell on any real machine — nothing runs on the user's computer, the server host, or any network. The filesystem is a sandbox backed by documentation chunks. This is how you read documentation pages: there is no separate "get page" tool. To read a page, pass its `.mdx` path (e.g. `/quickstart.mdx`, `/api-reference/create-customer.mdx`) to `head` or `cat`. To search the docs with exact keyword or regex matches, use `rg`. To understand the docs structure, use `tree` or `ls`. **Workflow:** Start with the search tool for broad or conceptual queries like "how to authenticate" or "rate limiting". Use this tool when you need exact keyword/regex matching, structural exploration, or to read the full content of a specific page by path. Supported commands: rg (ripgrep), grep, find, tree, ls, cat, head, tail, stat, wc, sort, uniq, cut, sed, awk, jq, plus basic text utilities. No writes, no network, no process control. Run `--help` on any command for usage. Each call is STATELESS: the working directory always resets to `/` and no shell variables, aliases, or history carry over between calls. If you need to operate in a subdirectory, chain commands in one call with `&&` or pass absolute paths (e.g., `cd /api-reference && ls` or `ls /api-reference`). Do NOT assume that `cd` in one call affects the next call. Examples: - `tree / -L 2` — see the top-level directory layout - `rg -il "rate limit" /` — find all files mentioning "rate limit" - `rg -C 3 "apiKey" /api-reference/` — show matches with 3 lines of context around each hit - `head -80 /quickstart.mdx` — read the top 80 lines of a specific page - `head -80 /quickstart.mdx /installation.mdx /guides/first-deploy.mdx` — read multiple pages in one call - `cat /api-reference/create-customer.mdx` — read a full page when you need everything - `cat /openapi/spec.json | jq '.paths | keys'` — list OpenAPI endpoints Output is truncated to 30KB per call. Prefer targeted `rg -C` or `head -N` over broad `cat` on large files. To read only the relevant sections of a large file, use `rg -C 3 "pattern" /path/file.mdx`. Batch multiple file reads into a single `head` or `cat` call whenever possible. When referencing pages in your response to the user, convert filesystem paths to URL paths by removing the `.mdx` extension. For example, `/quickstart.mdx` becomes `/quickstart` and `/api-reference/overview.mdx` becomes `/api-reference/overview`.

  Connector

• query_docs_filesystem_honeydew_documentation

  Honeydew AI Documentation

  Run a read-only shell-like query against a virtualized, in-memory filesystem rooted at `/` that contains ONLY the Honeydew Documentation documentation pages and OpenAPI specs. This is NOT a shell on any real machine — nothing runs on the user's computer, the server host, or any network. The filesystem is a sandbox backed by documentation chunks. This is how you read documentation pages: there is no separate "get page" tool. To read a page, pass its `.mdx` path (e.g. `/quickstart.mdx`, `/api-reference/create-customer.mdx`) to `head` or `cat`. To search the docs with exact keyword or regex matches, use `rg`. To understand the docs structure, use `tree` or `ls`. **Workflow:** Start with the search tool for broad or conceptual queries like "how to authenticate" or "rate limiting". Use this tool when you need exact keyword/regex matching, structural exploration, or to read the full content of a specific page by path. Supported commands: rg (ripgrep), grep, find, tree, ls, cat, head, tail, stat, wc, sort, uniq, cut, sed, awk, jq, plus basic text utilities. No writes, no network, no process control. Run `--help` on any command for usage. Each call is STATELESS: the working directory always resets to `/` and no shell variables, aliases, or history carry over between calls. If you need to operate in a subdirectory, chain commands in one call with `&&` or pass absolute paths (e.g., `cd /api-reference && ls` or `ls /api-reference`). Do NOT assume that `cd` in one call affects the next call. Examples: - `tree / -L 2` — see the top-level directory layout - `rg -il "rate limit" /` — find all files mentioning "rate limit" - `rg -C 3 "apiKey" /api-reference/` — show matches with 3 lines of context around each hit - `head -80 /quickstart.mdx` — read the top 80 lines of a specific page - `head -80 /quickstart.mdx /installation.mdx /guides/first-deploy.mdx` — read multiple pages in one call - `cat /api-reference/create-customer.mdx` — read a full page when you need everything - `cat /openapi/spec.json | jq '.paths | keys'` — list OpenAPI endpoints Output is truncated to 30KB per call. Prefer targeted `rg -C` or `head -N` over broad `cat` on large files. To read only the relevant sections of a large file, use `rg -C 3 "pattern" /path/file.mdx`. Batch multiple file reads into a single `head` or `cat` call whenever possible. When referencing pages in your response to the user, convert filesystem paths to URL paths by removing the `.mdx` extension. For example, `/quickstart.mdx` becomes `/quickstart` and `/api-reference/overview.mdx` becomes `/api-reference/overview`.

  Connector

• get_project_context

  Zephex

  Answer what the user's project is — name, stack, how to run/test/build, auth, database, deploy, folder layout — from their files on disk, not from training data. ALWAYS call this before you invent npm/pip/cargo commands or read package.json yourself. ALWAYS call when the user says: what is this app, what's the stack, how do I run it, how do I test, is this a monorepo, where is auth, what database, how do we deploy. If they named Zephex or MCP, call this first on their project. One topic per call. Start with topic=identity on a new folder, then follow next_calls (usually run or framework). Other topics: backend, frontend, database, auth, deploy, structure, integrations, security. This is the user's machine, any project: Node, Python, Go, Rust, Java, PHP, a monorepo, an unsaved folder. Local/stdio: omit path to use the editor cwd, or pass path as their project folder. No disk on this transport: inline_files with package.json or pyproject.toml/go.mod/Cargo.toml plus 2–4 source files. Returns topic, summary, data (identity, commands, key_paths), hint, next_calls. Copy dev/test/build from data — do not guess bun vs npm vs uv. Not for finding a function name (find_code) or reading a file body (read_code). Those come after you know what the project is. Example: get_project_context({ topic: "identity" }) then get_project_context({ topic: "run" }). Also call topic=auth before touching login, topic=database before schema work, topic=structure when you need the folder map. force:true if the project just changed. Brief is enough for orientation; do not skip this tool to save a round-trip — one identity call replaces reading several manifests.

  Connector

• works_verify_public_repository

  WORKS Public Verifier

  Use only after works_public_eligibility returns eligible. Download that immutable public GitHub snapshot, run the selected pinned static contract without executing repository commands, and return a signed receipt. Return the report field verbatim and stop.

  Connector

• list_opt_demos

  SCModeling

  List the bundled SCModeling optimization demos. Returns id + label + one-line summary for each (Tariff, Coffee Co-pack, SSO Basic). Use this before describe_opt_demo or get_opt_result to know which demo_id values are valid. All demos are precomputed sample-only fixtures — for optimization on real client data, the SCModeling desktop tool is the product.

  Connector

• select_surface

  mcp

  For a repo with SEVERAL runnable parts, call this BEFORE plan_deploy. You enumerate the candidate surfaces (find every Dockerfile/Containerfile, OPEN each, classify by its EXPOSE + CMD — never by directory name) and pass them in; redu RANKS them with fixed rules (a standalone browser desktop/noVNC > a self-contained web app > a keys-required playground > an API > a headless worker > docs/examples). GUIDED: returns the ranked list to present to the user, who picks. YOLO: auto-selects the TOP-ranked surface. Then run plan_deploy on the chosen surface's path + http_port. (A single-surface repo doesn't need this.)

  Connector

• input.click_xy

  Glasswarp

  Click at native screen coordinates (0…native_width-1, 0…native_height-1 from screen.observe). Last resort when no suitable UIA target exists — prefer input.click_target. Never use JPEG/downscaled pixel coords. Side effect: real mouse click on the remote desktop.

  Connector

• input.send_actions

  Glasswarp

  PREFERRED multi-step tool: run 1–10 predictable UI actions in one call (input.click_target, input.click_xy, input.type_text, input.send_keys, input.drag, input.scroll). Side effects: all actions execute on the remote desktop; fails fast before sending if any action is invalid. observe_after defaults true (verification observe: text+targets; set observe_image=true for JPEG). Do not batch across unpredictable waits (page loads, installers, modals) — single-step those. Prefer this over chaining solo click/type/keys tools.

  Connector

• get_quantum_exposure

  mcp

  Call this when the user asks how much Bitcoin is vulnerable to a quantum computer, about quantum-exposed supply, P2PK coins, or Satoshi-era exposure. Returns the latest daily measurement from ByKaranteli's own Bitcoin Core node: exposed BTC and its share of held value and UTXO count, composition by script family, dormancy cohorts, the dormant-P2PK watch set, and provenance hashes (base_height, base_hash, txoutset_hash) so any figure can be re-verified against any node.

  Connector

• convert_to_terraform

  Control Plane

  Convert a Control Plane resource manifest (YAML or JSON) into the equivalent Terraform (HCL). The manifest is first DRY-RUN VALIDATED against the API (no resource is created) — if it fails validation you get the error instead of HCL, so the returned Terraform always corresponds to a schema-valid resource. Pass `gvc` when the kind is GVC-scoped (workload, identity, volumeset). Set `generateImports` to also return ready-to-run `terraform import` commands. To convert an EXISTING resource instead of a manifest, use export_terraform.

  Connector

• get_autopilot_status

  MisarReach MCP Server

  Get the current progress and results of one autopilot run. This is how you follow a run started by start_autopilot: call it with the runId, leaving time between polls. Reading status does not pause, stop, or alter the run in any way — it keeps going regardless, and there is no tool here to stop it. Reads only and costs no credits, however often you call it. Requires an API key. A run still in progress is a normal answer, not an error.

  Connector

• spawn-ori-eval

  OpenRouter

  Get the instructions for running a model eval with Ori, then follow them. Ori runs the user's own agent on their own prompts, on a pinned harness and model, and grades what it did — so a score change means the model changed, not the environment. Call this tool FIRST, before writing any eval code: it returns a step-by-step recipe (install and auth checks, how to spawn `ori code -p`, how to relay Ori's scoping questions to the user, how to report results) that you carry out yourself. Do not hand-roll an eval instead. Use it when the user asks which model they should use, wants to compare or bake off models, wants to measure whether their agent or prompt does the right thing, wants to catch regressions in agent behavior, or asks how good their current model is. Works for any codebase in any language. Do not use it for plain unit tests that involve no model, and do not use it to re-run an eval that already exists (run `ori eval <file>` directly instead). Takes no arguments; the same document is published at https://openrouter.ai/skills/spawn-ori-eval.

  Connector

• get-quickstart-guide

  JxBrowser MCP Server

  Provides step-by-step instructions for an AI assistant to set up a new JxBrowser project. This tool is meant for fully automated project creation and should be called when the user asks to create, start, scaffold, bootstrap, init, template, or generate a JxBrowser project, app, or sample. CRITICAL RULES: 1. NEVER call this tool before knowing the user’s preferences. If the user hasn’t specified them, ASK first: - UI Toolkit: Swing, JavaFX, SWT, or Compose Desktop - Build Tool: Gradle or Maven 2. Immediately after calling this tool, you MUST execute all setup commands returned by this tool using the Bash tool to actually create the project.

  Connector

• query_docs_filesystem_political_comms

  docs

  Run a read-only shell-like query against a virtualized, in-memory filesystem rooted at `/` that contains ONLY the Political Comms documentation pages and OpenAPI specs. This is NOT a shell on any real machine — nothing runs on the user's computer, the server host, or any network. The filesystem is a sandbox backed by documentation chunks. This is how you read documentation pages: there is no separate "get page" tool. To read a page, pass its `.mdx` path (e.g. `/quickstart.mdx`, `/api-reference/create-customer.mdx`) to `head` or `cat`. To search the docs with exact keyword or regex matches, use `rg`. To understand the docs structure, use `tree` or `ls`. **Workflow:** Start with the search tool for broad or conceptual queries like "how to authenticate" or "rate limiting". Use this tool when you need exact keyword/regex matching, structural exploration, or to read the full content of a specific page by path. Supported commands: rg (ripgrep), grep, find, tree, ls, cat, head, tail, stat, wc, sort, uniq, cut, sed, awk, jq, plus basic text utilities. No writes, no network, no process control. Run `--help` on any command for usage. Each call is STATELESS: the working directory always resets to `/` and no shell variables, aliases, or history carry over between calls. If you need to operate in a subdirectory, chain commands in one call with `&&` or pass absolute paths (e.g., `cd /api-reference && ls` or `ls /api-reference`). Do NOT assume that `cd` in one call affects the next call. Examples: - `tree / -L 2` — see the top-level directory layout - `rg -il "rate limit" /` — find all files mentioning "rate limit" - `rg -C 3 "apiKey" /api-reference/` — show matches with 3 lines of context around each hit - `head -80 /quickstart.mdx` — read the top 80 lines of a specific page - `head -80 /quickstart.mdx /installation.mdx /guides/first-deploy.mdx` — read multiple pages in one call - `cat /api-reference/create-customer.mdx` — read a full page when you need everything - `cat /openapi/spec.json | jq '.paths | keys'` — list OpenAPI endpoints Output is truncated to 30KB per call. Prefer targeted `rg -C` or `head -N` over broad `cat` on large files. To read only the relevant sections of a large file, use `rg -C 3 "pattern" /path/file.mdx`. Batch multiple file reads into a single `head` or `cat` call whenever possible. When referencing pages in your response to the user, convert filesystem paths to URL paths by removing the `.mdx` extension. For example, `/quickstart.mdx` becomes `/quickstart` and `/api-reference/overview.mdx` becomes `/api-reference/overview`.

  Connector

• get_generation_results

  Uwear

  Look up generation results by exact IDs, filters, or hybrid image/name/SKU search. Returns labeled native ImageContent previews; use them directly and never Markdown-embed result URLs. They are display previews, not originals: url/download_url are originals, preview_url is the fallback link, and poster_url/thumbnail_url is a video poster. Every result includes generation_result_id and the response includes generation_result_ids; use those exact integers for queue_generation_result_qa/read_generation_result_qa or as durable generation_result command.source values in canonical edit, upscale, and video commands. Confirmation-gated clients use propose_brief(commands=[...], execute_immediately=true) when the user asked to run now, update_brief for a complete command replacement, or confirm_brief(execute=true) for a visible brief. Pass generation_result_id to fetch one result or generation_id to list a job's results. Returns raw payload when available so prior prompts can be recovered. Use start_date/end_date for requests like 'last week'.

  Connector

• upload_file

  Clueso

  Upload one or more files to Clueso. Three modes — pick by client + where the file lives: 1. **file_name** — HOSTED upload, the default for any non-UI / programmatic upload (Claude Code, Cursor, Claude Desktop, scripts). Returns an upload URL on Clueso's OWN base domain + a ready-to-run curl that streams a single local file to it; Clueso relays the bytes to storage server-side. The PUT targets the base domain — NOT cloud storage directly — so it works on desktop/agent clients that can't reach or are blocked from S3. Requirement: the client must be able to PUT bytes to the Clueso base domain (run the returned curl, or any HTTP PUT). The agent (or the user at a shell prompt) runs the curl. Prefer this whenever there's no human at a browser. 2. **file_url**: Pass a public https URL. Server fetches and stages the file. Returns mcp_upload_id immediately. Use when the file is already on the open web — no user interaction needed. 3. **request_hosted_upload** (UI mode — use ONLY when a human should pick files in a browser: many files at once, or a host with no shell / no PUT capability): Returns a single upload_token + upload_page URL. Share the link with the user; they open it in a new browser tab, drop their files, click Done. Then call check_uploads(upload_token) to retrieve all mcp_upload_ids. Call once for all files. Hosted uploads cover any number of files per call: one call issues one upload_token, and that token covers every file the user drops on the page. Repeat calls issue additional tokens, each tracking only its own files. The returned mcp_upload_id (prefixed `mup_`) can be passed to: - add_elements / update_elements (image or video → an element ON a clip: pass it as `type_data.mcp_upload_id`, on either tool — this is how a local image becomes on-canvas content, and how an existing element's source is swapped). To fill an animation's image slot, pass it inside `type_data.parameter_values` on update_elements only — parameter_values is an update-path field and is stripped on add. - add_audio (audio → project music track that plays under all clips) - add_clips(kind='video') (video or audio → sequential clip with auto-transcription) - add_clips(kind='pptx') (.ppt/.pptx → slide clips) - add_article_media (image/GIF → article asset) - analyze_audio (audio → transcript / silences / beats / features)

  Connector