Monitoring interface inspired by OpenStatus and Autosend
This listing identifies a third-party MCP server. MCPBundles is not affiliated with, sponsored by, or endorsed by the service or its operator unless stated on this page.
For AI agents — MCPBundles Directory API
Recommended: Directory API v1 over HTTP for detail and anonymous invoke when eligible (not MCP JSON-RPC on the publisher URL; no user MCPBundles credentials on v1).
GET https://www.mcpbundles.com/api/directory/v1/servers/uploop-mcp-07c781e132
GET https://www.mcpbundles.com/api/directory/v1/servers/uploop-mcp-07c781e132?live=1 (optional live refresh)
GET https://www.mcpbundles.com/api/directory/v1/servers/uploop-mcp-07c781e132/tools/<tool> (one tool: schema + invoke.url)
POST https://www.mcpbundles.com/api/directory/v1/servers/uploop-mcp-07c781e132/tools/{tool}
POST body: flat JSON of tool argument names and values; not an arguments wrapper. Replace {tool} with a tool name from GET detail.
Restricted agent shell (ChatGPT Codex desktop, some IDE sandboxes):
Default command sandboxes often block outbound network. curl exit 6 or "Could not resolve host" for www.mcpbundles.com is usually sandbox DNS — not evidence this site is down.
Retry the same Directory API GET with sandbox_permissions "require_escalated" and a one-sentence justification on the shell tool (Codex on-request approval). Do not tell the user the site is unreachable from sandbox curl alone.
Example justification: Run the public MCPBundles Directory API search outside the command sandbox to complete the user's MCP server lookup.
If the agent has browser access (e.g. Codex @Browser): open https://www.mcpbundles.com/?q=<query> or stay on this page — no shell network needed. Use WebMCP search_mcp_servers then get_mcp_server (document.modelContext / page tools; refresh with fetchTools or getTools if a tool id is missing from the snapshot). Read-only directory search; same index as Directory API v1 GETs. Neither WebMCP nor Directory API v1 uses user MCPBundles credentials.
Without a browser: after escalated curl fails, use GET https://www.mcpbundles.com/?q=<query> with Accept: text/markdown for ranked results.
Hub MCP (connected session): discover_mcp_servers — same filter semantics as search_mcp_servers.
Contract: https://www.mcpbundles.com/agents.md
OpenAPI: https://www.mcpbundles.com/api/directory/v1/openapi.json
Guide: https://www.mcpbundles.com/guides/mcpbundles-directory-api
For MCP client apps (human connect):
MCP connect URL: https://uploop.space/api/mcp
Skill page: https://www.mcpbundles.com/skills/uploop-mcp-07c781e132
Explore capabilities (26)
read 7
write 3
other 15
Showing 25 of 26
Showing 25 of 26 tools from the public preview. Connect the server to inspect the full live tool list.
List5
Delete2
Get2
Save2
Other capabilities14
Save Context
other
save_context
Writes a real, persistent record to the shared workspace database — not a note to yourself, a record any other AI model or agent (even one that has never seen this conversation) can read back via get_context or resources/read. This is how cross-session and cross-agent memory actually works here; without calling this, nothing about what you did survives past this conversation. CRITICAL FORMAT RULES for the summary field — write in plain language like this: 'The user asked me to [exact request]. I
Description may be truncated on the public preview.
Save Context — Writes a real, persistent record to the shared workspace database — not a note to yourself, a record any other AI model or agent (even one that has never seen this conversation) can read back via get_context or resources/read. This is how cross-session and cross-agent memory actually works here; without calling this, nothing about what you did survives past this conversation. CRITICAL FORMAT RULES for the summary field — write in plain language like this: 'The user asked me to [exact request]. I
Get Context — Retrieves the full context of a workspace. Call this at the start of a new chat to instantly know everything that was done before without re-explaining anything.
Register Agent — Writes your presence into a real shared registry for this workspace — a persistent record, not just something you say in chat. Once written, any other agent (different platform, different machine) calling list_agents or reading resources will genuinely see you listed, in real time. Call this once at the start of working in a multi-agent workspace; you don't strictly need it for solo/single-instance use, since other tools below (save_checkpoint, remember_preference) work without it.
List Agents — Lists all Claude instances currently active on a workspace. Use this before starting a task to check if another agent is already working on it.
Claim Task — Claims a task so other agents know not to touch it. Use a clear human-readable task_id like 'build-login-page' or 'write-api-docs'. The description must explain in plain English what you will do and the expected result.
Release Task — Releases a task you previously claimed, so other agents can work on it. Agents currently in listen_workspace will be notified immediately that this task is free.
List Tasks — Lists all currently claimed tasks in a workspace and who owns them.
Set Workspace Vision
Get your MCP into directories
A working endpoint is step one. Directory coverage is the coordinated launch across ChatGPT, Claude, Cursor, the MCP Registry, and community indexes.
Monitoring interface inspired by OpenStatus and Autosend
How do I connect Design is everything to my AI agent?
Use the MCP endpoint listed on this page in your MCP client configuration. One-click install pills support Claude, Cursor, VS Code, and other hosts. Copy the remote MCP URL if your client needs a manual entry.
How many tools does Design is everything provide?
Operate this server?
Request removal if you do not want Design is everything listed here, or claim the listing if you want to manage it on MCPBundles.
Operate Design is everything?
This server appears in the MCPBundles directory. Verify you operate it to take over the listing — name, description, logo, contact email, and skill content. We email a 6-digit code to a maintainer address your server publishes in /.well-known/security.txt or /.well-known/mcpbundles.json. Free, takes about a minute.
MCPBundles publishes this directory for MCP discovery. Except where we host or operate an offering, third-party services run under their own terms. Product and company names on this page are used in a descriptive, identifying way (including under nominative fair use where applicable); they remain the property of their owners. Nothing here grants you rights in those marks, and nothing here is an offer to sell a third party's services. Terms · Request removal
More in developer tools
Other MCP servers in this category from the directory index
— Writes the global vision/objective of the workspace to the shared database — a real, persistent field, not a summary you keep in your own head. All agents will see this vision in every get_context call, including agents that join later and have no other context. Use this to define what the project is trying to achieve at a high level. When updated, all listening agents are notified immediately via listen_workspace.
Wait For Event — Blocks and waits until another agent triggers a specific named event. Low-level primitive — in most cases prefer listen_workspace instead, which watches everything (claims, releases, context, broadcasts, reviews) and auto-chains across multiple rounds for you. Use wait_for_event only when you need to wait for one precise event name and nothing else. Max wait is 25 seconds. If timeout, call again to keep waiting.
Broadcast Message — Sends a message visible to ALL agents in the workspace. Use this to announce progress, ask a question to everyone, or share important info. Right after broadcasting, if you expect a reply, call listen_workspace to wait for it instead of stopping or guessing — other agents will see your message and may reply via broadcast_message themselves.
Request Review — Asks a specific agent to review your work before you continue. The target agent will see a pending review when they call list_agents or get_history. Use approve_review or reject_review to respond.
Respond Review — Approves or rejects a review request from another agent. The requesting agent will receive the feedback when they call wait_for_event or get_history.
Get History — Returns the full action history of a workspace — who did what and when. Includes saves, claims, releases, broadcasts, reviews. Useful for onboarding a new agent.
Listen Workspace — Watches the workspace for real-time changes from other agents — task claims, releases, context updates, broadcasts, reviews. Returns instantly when something happens, or gives a full workspace snapshot after 23s. Automatically chains up to 10 rounds (~230s total). IMPORTANT: if the response ends with 'Calling listen_workspace again (round N/10)...', you MUST immediately call listen_workspace again with round=N to keep watching.
Use Workflow Template — Applies a predefined team workflow to a workspace. Sets up the agent roles and task list automatically. Available templates: landing-page, content-team, bug-fix, travel-planning.
Push File — Writes the file's content to a real shared store other agents can actually read from — this is a genuine data transfer, not a status update. CRITICAL: agents on different machines, IDEs, or platforms (Claude Code on one laptop, Codex on another) NEVER see each other's local disk. If you create or edit a file that another agent in this workspace might need, you MUST call push_file right after writing it — saying 'I created the file' is not enough, nothing is shared until you push it. Keep it to o
List Files — Lists every file other agents have shared in this workspace (path, size, who pushed it, when). Call this at the start of a session alongside resources/list — do NOT assume a project is empty just because you don't see files on your own disk; another agent may have already pushed work here.
Pull File — Retrieves the content of a file another agent pushed to this workspace. Call this whenever a broadcast, history entry, or workspace context mentions a file you don't have locally — never assume you already have it just because another agent said they made it. You must then write the returned content to disk yourself; this tool only relays data, it does not touch any filesystem.
Delete File — Removes a file from the shared workspace once it's no longer needed by other agents.
Save Checkpoint — Writes a real, durable snapshot to an external database tied to this user's account — it persists across this conversation ending, across new sessions, and across switching to a different AI platform entirely, because it lives in the user's own database, not in your context window. This is NOT limited by your own lack of memory between conversations — calling this tool is precisely how content survives when your own memory wouldn't. Do not tell the user you have 'no way' to keep a version for th
List Checkpoints — Lists saved checkpoints so you can find the one the user is referring to when they say 'go back to the version where...' or 'remember when we had...'. Call this before recall_checkpoint.
Recall Checkpoint — Retrieves the full content and note of a specific checkpoint by id. You must then re-apply that content yourself (e.g. rewrite the file) — this tool only returns the saved data, it cannot directly modify files on the user's machine.
Delete Checkpoint — Deletes a saved checkpoint the user no longer needs.
Remember Preference — Writes a durable preference to the user's own database record — it will genuinely be there next session, independent of your own memory, even in a brand new conversation with no prior context. Use for lasting taste/style/workflow preferences, not one-off content (use save_checkpoint for that). Ex: key='styling', value='Always Tailwind, dark theme, no emojis in copy'. Call this whenever the user states a preference that should apply going forward, not just this session — don't wait for them to ex
List Preferences — Lists all remembered preferences for this user. Call this at the start of a session if resources/list did not already surface them, so you work the way the user expects without asking again.
Showing the first 25 tools — full list and schemas: Directory API.
MCPBundles probed 26 tools on the live server. The tool list on this page reflects what was discovered at the last refresh — connect your client to see the full set available to your session.
What authentication does Design is everything require?
No provider sign-in was required during MCPBundles' probe. Your client may still need MCPBundles credentials depending on how you connect.
Don't want this listed?
Request removal from the MCPBundles directory. We stop publishing this listing on mcpbundles.com.
MCPBundles is an independent platform built on the open Model Context Protocol standard. MCPBundles is not affiliated with, sponsored by, or endorsed by Anthropic PBC.