Productivity · Remote MCP server

Cobbles

The shared task board for teams and their AI agents — connect over OAuth, every action signed.

Visit Cobbles's website

What the MCP Registry states

The entry as published to the official MCP Registry (read 2026-10-04), latest version.

Registry name
ai.cobbles/cobbles
Version
1.0.0
Status
Active
Category
productivity
Transport
Streamable HTTP
Published
2026-07-07
Updated
2026-07-07
Publisher
ai.cobbles
Website
cobbles.ai
Repository
github.com/Yu1586/cobbles
Source
Registry API entry

Remote endpoints

TransportURLHeaders declared
Streamable HTTPhttps://api.cobbles.ai/mcpNone

How to connect Cobbles

Cobbles is a remote MCP server: there is nothing to install. Its endpoint is https://api.cobbles.ai/mcp, served over Streamable HTTP. In an assistant that accepts remote MCP servers (often under a setting named connectors, integrations or tools), add a new server and give it this URL; in a client configured by file, add it as a remote (HTTP) server with the same URL.

No headers are declared in the registry entry. If the server needs you to sign in, a client that supports MCP authorization opens the service's own sign-in page when it first connects.

Derived from the registry entry, not tested here. What the server does, and on what terms, is set by its publisher; check its repository or website before giving it access to your accounts or files. How to add an MCP server to an assistant · Before you connect

More productivity servers

All 3,040 →
ServerRunsEndpoint or package
Clpi Clp MCPManage simple context workflows with quick init and add actions. Access the 'Hello, World' origin…Remote · HTTPserver.smithery.ai
ClusterHackRun hackathons end to end: events, teams, submissions, judging and winners.Remote · HTTPclusterhack.dev
ClutterGenerate synthetic companies, documents & data via the Clutter API (e.g. to fill SharePoint).Local · stdionpm: clutter-mcp
cmxflowComposable, tunable cheminformatics workflows: library preparation, clustering, docking, and more.Local · stdioPyPI: cmxflow
Cockpit MCP40 AI prompts + self-hosted ops dashboard for homelab and small-team sysadmins.Local · stdionpm: cockpit-mcp
CodaInteract with Coda.io documents, tables, and rows via the Coda API.Local · stdioOCI image (Docker): ghcr.io/nkpar/coda-mcp:0.2.1
Codabench MCPMCP server for the Codabench REST API — drives a full ML-benchmark participant workflow.Local · stdioPyPI: codabench-mcp
CodehabitsTeam conventions, anti-patterns, and domain knowledge from.codehabits/ for AI coding agents.Local · stdionpm: @codehabits/mcp