Developer Tools Codex plugins

Publisher subtitle

Build and deploy voice agents

Publisher subtitle

Build and deploy apps & agents

Publisher full description

…specification or repository; work through actual coding tools available in the host. Choose real subagents when available; otherwise use a sequential workflow. Supports a useful tool-only fallback for clients without MCP Apps UI. Generated files, running tests, repository access and deployment depend on available host capabilities and user authorization; the plugin itself does not operate a hosted code-execution service.

Publisher capabilities · listing

Create persistent hosted AI agents Configure agent instructions, models and supported tools Run agents and continue their conversations Read agent replies, run status and tool activity Schedule one-time or recurring agent tasks Answer pending agent questions, approvals and forms Preview and deploy reusable agent configurations

Publisher subtitle

Build specialist agents.

Publisher full description

Work with your saved ClawMaven governance profiles before you deploy an AI agent. Get a profile's posture score, grade, and category breakdown; retrieve the effective policy (allowed tools, blocked domains, budget caps, and autonomy level) for an agent you name;… …s your authorization. ClawMaven is pre-deployment governance design: it does not scan code, monitor agents, or enforce policy at runtime.

Publisher keywords · listing

cloudish deployment docker containers hal9 hosting agents

Publisher capabilities · listing

…nd Core Web Vitals Review API/data integrity, authorization, dependency and privacy risks Plan safe deployments, rollback, canary checks and post-release verification Coordinate specialist QA review with real agents when supported

Publisher subtitle

Enterprise agents & routing

Publisher description

The Complete AI Agent Platform Botpress is an all-in-one platform for building AI agents powered by the latest LLMs. Use this application to rapidly prototype agents that can do FAQ, sales, support and so much more! How it works: 1. Tag @Botpress in your chat and ask ChatGPT to cre… …. Iterate on design, business logic, information sources and more through natural language! 3. Once deployed, with the click of a button, you can open your agent in Botpress to access a comprehensive visual agent builder.

Publisher description

Brainbase MCP lets users create, inspect, update, test, deploy, and monitor managed AI agents from ChatGPT and Codex. It supports revision-safe agent changes, registry skills and MCP server configuration, evaluations, orchestrations, schedules, and task runs, with explicit confirmation…

Publisher full description

Enoki tests AI agents for security and safety weaknesses. It attacks your agent the way an adversary would, adapts to how the agent responds, and reports each weakness it finds with the exact attack and the agent's… …i workspace; an owner or admin of the workspace approves the connection. Register a test or staging deployment of your agent rather than production, because an assessment sends adversarial messages to it.

Publisher full description

…nomy. Compare deterministic code, single model calls, bounded tools, directed workflows, autonomous agents and multi-agent systems. Define secure tool contracts, permissions, approval flows, MCP integration, state and memory, evaluations, tracing, debugging, migrations and production readiness. Incl… …ferences and offline fixtures. It is skills-only: coding, real subagents, tools, eval execution and deployment require user-authorized capabilities available in the host environment.

Publisher full description

Build voice ai and multimodal agents with Pipecat, from an idea to a local app and Pipecat Cloud deployment. Explore speech-to-text (STT), language models (LLMs), text-to-speech (TTS), real-time speech-to-speech and other supported multimodal patterns using Pipecat documentation, API definitions…

Publisher full description

…back or attributed extensions, not duplicate copies. Search reusable experience learned by other AI agents and inspect provenance, observed outcomes and contradictions. This Remnant Read connection keeps its seven read-only tools. A separately authenticated Remnant Agent connection can automatically… …stays local. Existing grants are not silently upgraded. Availability and installation depend on the deployment and host. Optional installation setup can save per-task usage measurement instructions in your own Codex profile after explicit review. Statistics stay local, unknown values remain null, an…

Publisher description

…te health without any setup. Whether you're testing a production site, staging environment, preview deployment, or local environment, Testifly quickly identifies issues before they reach users. Testifly is especially valuable for AI-assisted and vibe coding workflows, where code is generated rapidly by AI coding agents. As development accelerates, automated end-to-end validation is critical to ensure features actually work in the browser. Testifly provides an independent verification layer that catches broken…

Publisher full description

ThunderPhone builds, tests and runs AI phone agents. From ChatGPT or Codex you can create an agent from a plain-language brief, check a change in a free text test before deploying it, run test calls, attach a phone number, add knowledge, change organization settings such as business hours, diagnose a number or a campaign, and get a call report. Every action is scoped…

Publisher description

Build and deploy web apps and AI agents on Vercel.

Publisher keywords · package

cloudflare workflow deployment edge-functions edge analytics wrangler agents-sdk serverless ai-gateway

Publisher keywords · listing

volcano agents serverless deploy cli

Publisher full description

…and alerts from your connected LogForge instances. In Codex desktop, set up local Docker telemetry, deploy agents to authorized remote Linux hosts, instrument a project and run its checks. In web clients, inspect connected data and receive setup guidance. Local diagnostic commands work without Docker or an…

Publisher capabilities · listing

…racing for answer evidence, latency, cost, failures, and index freshness Coordinate real specialist agents where supported; otherwise work sequentially Prepare regression checks and release evidence without inventing test results

Publisher full description

…and current official docs for version-sensitive APIs. Uses available host coding tools and real subagents only when supported; this skills-only plugin provides no hosted build service, database connection, or automatic deployment.

Publisher full description

…mate. One link opens the TokenOS Development Workspace with the prompt pre-filled — build, preview, deploy and host without leaving the browser. Tools: • plan_dapp — Turn the user's app idea into a spec (features, pages, components, data model, Web3 integrations, stack, steps, credit estimate) with… …s. • tokenos_capabilities — Reference: supported chains, deployment targets, hosting, token launch, agents, payments and credits. Targets questions like: “build a dapp with ai”; “generate solana app”; “ai web3 app builder”; “create nft minting website”; “build dao website”; “no code dapp builder”. D…

Publisher full description

…implementation, security and testing guidance, and independent code/visual review. Supports real subagents and coding tools only where the host provides them; does not itself include a hosted coding service or promise deployment, simulator access or live execution without tools.

Publisher keywords · listing

access permissions MCP AI agents developer tools

Publisher full description

Model gateway, compute, deployment, database, auth, and more. Every service built for AI coding agents to operate end to end through CLI and skills

Publisher full description

PromptingCraft.com helps you write, review and improve prompts for coding agents such as Codex, Claude Code and Cursor. Turn a development discussion into clear, execution-ready instructions for an AI developer. It identifies the task contract (requirements, decisions alrea… …e optional PromptingCraft.com guidance server (mcp.promptingcraft.com) adds read-only access to its deployed guidance ledger: it lists official guidance for a target agent, model family and topic, returns a record with its source, limits and verification date, and checks whether an official source p…

Publisher description

…autonomous software team. Assign a Linear, Jira or GitHub issue to SHIP, and its autonomous coding agents plan, build, review and test the change in your own GitHub repository. A mission works toward a pull request. Your CI, an automated code review and a test of its acceptance criteria each gate i… …ring practices in your repository, such as its agent instructions and skills. Your CI and a preview deploy are gates between the roles, and work that fails a gate goes back to the Builder with the reason. Schedule maintenance missions, such as a weekly dependency upgrade. Manage the preview environm…

Publisher description

Make a JavaScript web repo readable by LLMs and AI agents at build time: generate llms.txt, JSON-LD, markdown mirrors, AI-crawler robots.txt rules and Content-Signal headers, then validate the built output. Picks the right @agentmarkup adapter for whi…

Publisher description

…g frontend integrations, production scaling questions, and the bundled Convex quickstart runbook so agents follow the current deployment, auth, and component patterns instead of hand-rolling from stale memory.

Publisher full description

Specialized skills and agents covering Duende IdentityServer configuration, OAuth 2.0 / OpenID Connect protocols, ASP.NET Core authentication and authorization, BFF patterns, token management, SAML, key management, deployment, and security hardening.

Publisher description

Author, run, and deploy Flyte 2 workflows, apps, and agents with skills grounded in the Flyte SDK and documentation. In ChatGPT web, search Flyte docs and SDK examples. In a local ChatGPT environment with the Flyte CLI configured, run and manage your au…

Publisher full description

Connect your Inngest account to inspect deployed apps, functions, events, runs, traces, and Insights through OAuth MCP. Diagnose failures and carry out requested workflow operations in the selected environment. Coding hosts can also use the bundled skills to build durable functions and agents, audit codebases, and test locally with an optional Dev Server connection.

Publisher description

…d bootstrap configurations - validate workflow structure and configuration - assist with packaging, deployment, and licensing - provide guidance using the latest platform capabilities - generate examples and implementation patterns With MCP, the AI can use purpose-built tools that understand the Ops… …ackage for deployment." The server is intended for: - AI coding assistants - IDE integrations - CLI agents - automation developers - DevOps and platform engineers - custom AI applications that need authoritative knowledge of Opscotch