"Accessing or using a remote MCP server endpoint" matching MCP connectors:
GET /v1/connectors – MCP directory API referenceMatching Connector Tools:
IncidentVault's operational MCP endpoint gives an assistant an incident dashboard, record review, follow-up creation, task edits and incident intake. It returns IDs, status, priority, dates and location IDs only; names, narratives, medical details and attachments are excluded. Write scopes are opt-in and role and location limits apply on every call.
Context for coding agents: checks a GitHub or Linear issue is ready before your agent starts it.
One board for every AI you use: agents claim tasks and finish with proof you accept or return.
SmartShifts' MCP server gives an assistant scheduling, time-off and task tools for multi-location businesses such as restaurants. Find staffing gaps, check team availability, request or approve time off, and complete tasks. Every action runs with the user's own role and location permissions, changes wait for approval by default, and sensitive personal fields are left out.
QuipAssist's MCP server lets an assistant look up equipment, repairs, work orders, maintenance schedules, parts, vendors, IoT readings and reports across the sites a user can access. With write access it drafts repair, maintenance and parts changes, which wait for human review by default. An agent can never dispatch work, sign off safety steps, approve spending or send messages.
One shared project for a team's coding agents: decisions, a task board and handoffs.
Connect Claude, ChatGPT, Cursor or your own app to Workspace369: clients and pipeline, proposals, e-sign contracts, invoices and payments, projects, tasks, time tracking and calendar. Build a custom CRM on it with any AI coding agent. Anything sent to a client waits for your approval.
Browse Paymo projects, tasks, timesheets and invoices, and create tasks, log time or run timers.
Turn a list of interests into a day-by-day plan for 3 to 7 days, with checkbox text for a todo app.
Read Bilflo clients, contract jobs, contractors and reports; update jobs, terminate or reopen them.
One hosted MCP server for the whole Dutify suite: project management (tasks, sprints, views, custom fields), Dutify Hub call recordings, transcripts and Lens chat, Codexum wiki pages, and Roadmarq feature requests and bugs. Auth: X-API-Key header with a Dutify personal key (du_live_...). Docs: https://github.com/dutifyai/dutify-mcp
Turn your AI assistant into your content partner. Bardiyah connects ChatGPT, Claude and any MCP client to your own ideas, projects and video scripts, so it can search your work, turn an idea into a full script card by card, and keep every video moving from idea to publish. Built Arabic first, works fully in Arabic and English. Secure OAuth sign in, no delete actions, your data stays yours.
Review your AI agents' work in minutes, not hours of chat. Approve it or send it back.
Retasc is a work queue for AI coding agents. The next agent picks up where the last one stopped.
Kanban tasks and project notes for AI clients, with OAuth and per-project read or write grants.
Field operations on a deterministic solver — run jobs, crews & fleet from Claude or ChatGPT.
RetailHardHat's MCP server lets an assistant work with an organization's retail sites, projects, budgets, bids, permits and field work, including an interactive operations dashboard. An organization admin grants modules and read-only or guarded-write access; sensitive writes need human review by default.
Connect Claude, ChatGPT, Cursor or any MCP client to Ybug. Read bug reports with screenshots, console logs and network requests, then triage them in chat.
Getting Things Done (GTD) board for AI agents: capture to Inbox, next actions by context, projects, waiting-for, someday/maybe. Remote Streamable HTTP server with OAuth 2.1 login (passwordless email code). 16 tools + 4 prompts. Setup guide: https://gtdbrain.com/connect?source=glama
Coding agents are fast, but they forget the plan when a session ends. Pizza Developer keeps it for them. You write down Ideas. Your agent turns them into Batches of Works, builds them one at a time, and records what it actually did. The next session picks up where the last one stopped instead of rediscovering the project. You stay in charge of how the work happens. Instructions tell the agent how you want things built. Workflows set the route each kind of request takes. Rules refuse a write that breaks them. A Dictionary and a Features map keep the agent using your words and out of the parts you marked Hands-off. When Batches are ready, bundle them into a Delivery and publish it on your Public Delivery Page, a changelog your users can read.
