POSIX shell quote shape, input discarded
ConnectorNo auth
723,611 tools. Updated 2026-10-30 00:19
"Shell" matching MCP tools:
- Free, read-only. Fetch a page and return its HTML minus scripts, styles, svg, iframes, comments and inline handlers; tags and attributes stay, so structure is readable. For inspecting or rebuilding markup, not plain text (fetch_extract gives that). Runs no JavaScript: SPAs return an empty shell. Cut at maxChars with a marker.ConnectorNo auth
- Returns instructions for creating a DPF account, verifying its email, resending the verification code, or resetting a forgotten password — it never performs these itself and never asks for a password. A password typed into this chat would sit in the conversation transcript, so every action instead returns the DPF website's own form, or a curl command that reads the password from a shell variable the user sets themselves in their own terminal. Hand the command to the user to run — do not run it yourself even if you have shell access, since composing the export line would require seeing the password. action "register": requires email, firstName, lastName, and termsAccepted: true (only after the user has explicitly agreed to the DPF Terms of Service and Privacy Policy in this conversation). action "verify": confirm the 6-digit code DPF emailed after registration (requires otp). action "resend": re-send that code if it never arrived. action "forgot-password": request a password-reset code (requires email). action "reset-password": submit that code and set a new password (requires otp).ConnectorOAuth
- Run a shell command inside a running container instance on Cycle, over the instance's SSH gateway, and return the shell output. Use this for one-time setup that must run inside a container — e.g. initializing a MongoDB replica set with 'mongosh --eval "rs.initiate({...})"'. The instance must be RUNNING (start the container first). If the container has multiple instances, pass 'instance' (id or hostname); otherwise the sole instance is used. Containers reach each other by hostname over the environment's private network, so commands can reference sibling containers (e.g. mongo-1:27017). This executes an arbitrary command inside your container — it is powerful and mutating. Always call with preview:true first: it echoes back the exact command and target without making any connection, so the user can confirm it is what they intend (nothing is validated — the command may still fail when run). Confirm with the user, then call again without preview. Never run a command without explicit confirmation. Short-lived SSH credentials are generated for the run and expired immediately after. The command runs in an interactive shell; make destructive commands idempotent where possible.ConnectorDestructiveAPI key
- Run one Comment.io command or restricted shell script in your workspace, exactly as an SSH exec: same commands, output and exit codes. Start with {"command":"help"}. The command runs on Comment.io, not on your machine; pass text for --stdin commands in stdin. Every call ends within 45 seconds: error: deadline (exit 3) means the outcome is unknown and writes may still land within seconds. After a deadline, a nonzero exit or a lost response, reread state rather than repeating a mutation.ConnectorDestructiveOAuth
- Create a one-time link to upload one audio file (up to 100 MB), valid for 15 minutes. With a shell, upload with: curl -T "<file>" "<upload_url>". A person can instead open the link in a browser and choose the file. Then call transcribe_upload with the upload_id. The file is kept in memory only, until it is transcribed or the link expires.ConnectorOAuth
Matching MCP Servers
shell-mcpofficial
AlicenseNot gradedqualityDmaintenanceGives AI agents shell access by providing a run_command tool for executing shell commands and returning stdout, stderr, and exit code.2 npm1ISC- AlicenseAqualityDmaintenanceA production-ready MCP server that enables AI assistants to execute shell commands, manage files, monitor system resources, and automate complex workflows with advanced features like stock tracking and web automation.712 npmMIT
Matching MCP Connectors
POSIX shell quote shape, input discarded
Turns vague automation requests into tool stacks, prompts, QA checks, and human boundaries.
- Upload a local image file with one shell command; its bytes never pass the model. Use this when your shell reaches the public internet and the PNG/JPEG/WebP (max 5 MB) is a file you can read: Claude Code, Codex, Cursor or a local terminal. If the PerfectVector CLI is installed, use it instead. Not in Claude chat: its sandbox usually can't reach PerfectVector. Returns a ready curl command for a 10-minute, single-use link on PerfectVector's own domain; replace IMAGE_PATH and run it. The upload only stores the image, charges nothing and prints its upload_id; then call check_price with that upload_id, then convert_to_svg. Use a new request_key per image and pass the image's file name as file_name: the SVG is named after it.ConnectorOAuth
- Create a document and return its public URL. Re-using an existing name adds a new immutable version. Omit the name to get a random one. For content larger than ~10KB or any file already on disk, do NOT inline it here - run `docbin push <file> [--name <doc>]` in your shell instead (set DOCBIN_TOKEN to an API key from https://docbin.app/settings/keys). Inlining large content streams it through the model token-by-token and will time out.ConnectorNo auth
- Create a document and return its public URL. Re-using an existing name adds a new immutable version. Omit the name to get a random one. For content larger than ~10KB or any file already on disk, do NOT inline it here - run `docbin push <file> [--name <doc>]` in your shell instead (set DOCBIN_TOKEN to an API key from https://docbin.app/settings/keys). Inlining large content streams it through the model token-by-token and will time out.ConnectorNo auth
- Run bash on the same remote sandbox as FLOWRA_JS_REMOTE_WORKBENCH for this session.id. Files under /home/user/files stay between calls. The shell itself starts fresh each time. With session.id and useWorkbenchSnapshot (default true), the latest FLOWRA_MULTI_EXECUTE_TOOL snapshot is at /home/user/files/multi_execute.json (also FLOWRA_WORKBENCH_JSON). That snapshot only exists if the earlier call set syncResponseToWorkbench: true. Use this for shell work on those files: jq, grep, sort, unzip, wc, listing directories. It has no run_tool, invoke_llm, or proxy_execute helpers and keeps no variables between calls. To call app tools, an LLM, or a connected API from the sandbox, or to keep state across steps, use FLOWRA_JS_REMOTE_WORKBENCH. Neither tool can call FLOWRA_MULTI_EXECUTE_TOOL or any other meta tool.ConnectorDestructiveAPI key
- Get upload URLs for a local image/video/audio file that has no public URL to hand to `popcraft_media_import_url`. THIS IS THE TOOL FOR VIDEO and for anything over 20 MB. Returns a `proxy_upload_url` on Popcraft's OWN host (PUT the bytes there — total file size up to the per-type cap: video 500 MB, image 30 MB, audio 50 MB; each individual REQUEST is capped at 28 MB by the transport, so files over 28 MB use the chunked recipe B — same URL, same total cap) and an `upload_url` for a direct PUT to storage.googleapis.com (fewer hops, but a different host that sandboxed clients often cannot reach). The result text contains ready-to-run shell recipes including the chunked one for large files — RUN one of them rather than reimplementing the upload. Running a shell command also keeps the file bytes out of your context, which is why this beats `popcraft_media_upload_inline` for video: that tool needs the whole file base64-encoded in its arguments, so it is only practical for small files. CAUTION on platform-mediated clients (e.g. claude.ai connectors): tool calls are made from the platform's servers, so this call succeeding does NOT prove your shell can reach Popcraft — run the 5-second egress probe in recipe 0 first. If your shell's egress is blocked: prefer asking the user for any shareable link to the file (Drive/Dropbox/etc) and `popcraft_media_import_url` (server-side fetch, immune to client egress blocks); if no link exists, open `popcraft_media_upload_widget` when the client renders widgets. After the upload, call `popcraft_media_confirm` with the returned `media_id` to verify it landed, then pass that `media_id` as a `medias[].value` for `popcraft_generate_image` / `popcraft_generate_video` / `popcraft_generate_audio`. If you have no shell and no network at all, fall back to `popcraft_media_upload_inline` — but never tell the user to upload the file on the website instead.ConnectorOAuth
- Get upload URLs for a local image/video/audio file that has no public URL to hand to `popcraft_media_import_url`. THIS IS THE TOOL FOR VIDEO and for anything over 20 MB. Returns a `proxy_upload_url` on Popcraft's OWN host (PUT the bytes there — total file size up to the per-type cap: video 500 MB, image 30 MB, audio 50 MB; each individual REQUEST is capped at 28 MB by the transport, so files over 28 MB use the chunked recipe B — same URL, same total cap) and an `upload_url` for a direct PUT to storage.googleapis.com (fewer hops, but a different host that sandboxed clients often cannot reach). The result text contains ready-to-run shell recipes including the chunked one for large files — RUN one of them rather than reimplementing the upload. Running a shell command also keeps the file bytes out of your context, which is why this beats `popcraft_media_upload_inline` for video: that tool needs the whole file base64-encoded in its arguments, so it is only practical for small files. CAUTION on platform-mediated clients (e.g. claude.ai connectors): tool calls are made from the platform's servers, so this call succeeding does NOT prove your shell can reach Popcraft — run the 5-second egress probe in recipe 0 first. If your shell's egress is blocked: prefer asking the user for any shareable link to the file (Drive/Dropbox/etc) and `popcraft_media_import_url` (server-side fetch, immune to client egress blocks); if no link exists, open `popcraft_media_upload_widget` when the client renders widgets. After the upload, call `popcraft_media_confirm` with the returned `media_id` to verify it landed, then pass that `media_id` as a `medias[].value` for `popcraft_generate_image` / `popcraft_generate_video` / `popcraft_generate_audio`. If you have no shell and no network at all, fall back to `popcraft_media_upload_inline` — but never tell the user to upload the file on the website instead.ConnectorOAuth
- Upload a PDF attachment without sending file bytes through this tool. Required: attachment.filename (local PDF path; no control characters). Optional: attachment.name only if the Common Paper attachment name should differ from the file basename; attachment.description. Do not send uploaded_by — the OAuth-authenticated MCP user is recorded as the uploader. Returns JSON with curl_command where the path is already shell-escaped — run that command exactly as returned. Do not base64-encode the PDF into this tool and do not use generate-api-key for uploads.ConnectorOAuth
- Upload a PDF attachment without sending file bytes through this tool. Required: attachment.filename (local PDF path; no control characters). Optional: attachment.name only if the Common Paper attachment name should differ from the file basename; attachment.description. Do not send uploaded_by — the OAuth-authenticated MCP user is recorded as the uploader. Returns JSON with curl_command where the path is already shell-escaped — run that command exactly as returned. Do not base64-encode the PDF into this tool and do not use generate-api-key for uploads.ConnectorOAuth
- Static validation firewall for outbound network destination URIs against cloud metadata IP addresses (169.254.169.254), RFC 1918 private IP blocks, and query-string secret exfiltration before agent dispatch. Use when validating a user-supplied or tool-supplied URI destination before network dispatch; for auditing local shell commands or general prompts, use verify_agent_command_safety instead. Read-only edge call (32 KB, 60 RPM): accepts 'destination_uri' ('egress_policy' defaults to 'block_private_and_metadata'), supports '?demo=true' or L402 (15 sats), and returns HTTP 400 if invalid.ConnectorNo auth
- Static validation firewall for outbound network destination URIs against cloud metadata IP addresses (169.254.169.254), RFC 1918 private IP blocks, and query-string secret exfiltration before agent dispatch. Use when validating a user-supplied or tool-supplied URI destination before network dispatch; for auditing local shell commands or general prompts, use verify_agent_command_safety instead. Read-only edge call (32 KB, 60 RPM): accepts 'destination_uri' ('egress_policy' defaults to 'block_private_and_metadata'), supports '?demo=true' or L402 (15 sats), and returns HTTP 400 if invalid.ConnectorNo auth
- Scan source code for injection vulnerabilities: SQL injection, command injection, path traversal via unsafe string concatenation/unsanitized input. Supports Python, JavaScript, TypeScript, Java, Go, Ruby, Shell, Bash. Use to detect input-handling bugs; for secrets use check_secrets. Companion code-security tools: check_secrets (hard-coded credential detection), check_dependencies (known-CVE vulnerability audit), check_headers (live HTTP security-header validation), scan_headers (live HTTP scan via domain). Free: 30/hr, Pro: 500/hr. Returns {total, by_severity, findings}. No data stored.ConnectorNo auth
- Free, read-only. Convert a fetched URL or an HTML string you pass (one of the two) to Markdown: headings, links, lists, emphasis, code, quotes. Drops nav, header, footer, aside, script and style. Returns text, cut at maxChars with a marker. Runs no JavaScript: SPAs return an empty shell. Tables become plain text.ConnectorNo auth
- PREFERRED tool for sending work to an AI agent. Dispatches a task to the agent's inbox — picked up and executed automatically. No list ID needed. REQUIRES the agent:dispatch permission on this connection (CODE:/SHELL: tasks also require agent:dispatch:code) — reconnect and tick the agent checkbox(es) if refused. Routing is by TITLE PREFIX only: CODE: SHELL: PLAN: MCP: → local Claude Code on Mike's PC; RESEARCH: WRITE: REVIEW: → cloud; no prefix (DEFAULT) → local while the PC agent is alive, else cloud. The cloud agent refuses CODE/SHELL/PLAN/MCP. Use "agent" param to target a specific agent (default: claude-code-local). Use tascan_list_agents to discover available agents; track progress with tascan_get_task (its "agent" block).ConnectorNo auth
- Add files to an open begin_deploy session; call it as often as needed, then commit_deploy publishes them together. Paths, extensions and encodings are checked on every call. A 100-250 KB text file usually fits in one call with encoding:'gzip+base64' (gzip locally, then base64); prefer that over add_file_chunk. If your shell can reach mcp.vibedeploy.be, one tar(.gz) POST to begin_deploy's uploadUrl is faster still.ConnectorNo auth
- Free machine checkout builder. Select a paid IntentFence outcome and receive the exact endpoint, validated request, USDC cap, shell-safe Agentic Wallet argv, MCP tool call, and opt-in local auto-payment budget. It never signs or initiates payment.ConnectorNo auth