Skip to main content
Connic
Getting Started

AI Agent Setup

Give ChatGPT, Claude, or your coding agent the Connic playbook and permission-scoped platform tools. Use the full plugin when your client supports the Connic package, or connect the skill and MCP separately.

Last updated

Choose your setup

The full plugin is the recommended path. The same two capabilities are also available separately when you only need one or your client uses a different package format.

Full pluginRecommended

One install bundles the Connic skill with the Connic MCP connection. Use this path whenever a compatible Connic package is available for your client. The selector below covers verified client flows; other clients can use the same skill and MCP capabilities through their supported plugin format or the separate setup.

Connic skill

Adds the authoring playbook: current project structure, SDK and CLI workflows, connector patterns, tests, and platform conventions. It does not grant live access.

Connic MCP

Adds authenticated live project context and permission-scoped actions. It does not teach the agent how to author a Connic project by itself.

Set up your AI client

Choose a client for its current plugin, skill, and MCP instructions.

ChatGPT app setup

  1. Add the Connic marketplace

    Open the ChatGPT desktop app, select Plugins → Add → Add a marketplace, then enter connic-org/connic-skill in the Source field.

  2. Confirm the marketplace

    In the Add plugin marketplace dialog, leave Git ref and Sparse paths blank, then select Add marketplace.

  3. Install and connect Connic

    Open the new Connic marketplace, select the Connic plugin, and choose Install. Complete the connection prompt and choose the project, environments, and permissions in Connic.

  4. Use Connic

    Start a new Chat or Work conversation, or a Codex task. Type @ in the composer and choose Connic, then ask it to work with your Connic project.

    See the official OpenAI plugin instructions.

Give your agent a goal

Start a new task or session in the repository, then describe the outcome you want. The skill supplies the Connic conventions; MCP supplies the live project context and actions you authorized.

prompt
Build a customer-support agent in this repository with Connic.
Add the agent configuration, any required tools, and a focused test suite.
Validate the project with connic lint when you are done.

Full plugins bundle the skill and MCP connection. The project copies installed by connic skill are skill-only; accepting its optional client prompt installs the full plugin separately. npx skills add also does not change MCP configuration. MCP-only installs add live tools but not the Connic authoring playbook. View the plugin and skill source.

Connic MCP

Connic MCP connects a coding client to https://mcp.connic.co/mcp for live, permission-scoped project state and actions. It does not add tools to a deployed agent or expose an agent as an MCP tool. Review its official MCP Registry listing.

Access and permissions

OAuth narrows access; it never expands what your Connic membership can do.

Access boundaryHow it works
Project and environmentsEach authorization belongs to your user, one OAuth client, and one project. Choose all project environments or an explicit environment subset during consent.
Read and write permissionsConnic can only grant permissions your current project membership already allows. Keep all eligible reads or select individual read permissions. Write actions are optional and can be granted together or individually.
Review and revokeManage your connection under Project Settings → API Keys & MCP Auth. Permission edits take effect without reconnecting, MCP activity appears in the Audit Log, and revocation immediately ends access.

Projects that require two-factor authentication also require a recent two-factor sign-in before sensitive writes.

What you can do

Your client discovers only the tools allowed by the current authorization. Stored secret values are never returned.

AreaAvailable capabilities
Scope, stats & environmentsContext, health, aggregate stats, run history, environment lifecycle, defaults, and queued runs.
Agents & runsAgent details, runs, traces, inputs and outputs, logs, cancellation, reruns, and bulk operations.
DeploymentsDeployment details, tests, runs, creation, cancellation, activation, and redeployment.
ConnectorsConnector definitions, agent links, runs, stats, and logs.
RetrievalNamespaces, entries, chunks, statistics, uploads, deletion, sources, and sync runs.
DatabaseEnvironment-scoped stats, collections, inferred schemas, full document queries and counts, updates to existing rows, and document and collection deletion.
SessionsList, search, and filter environment-scoped persistent sessions with stored state, agent and user identity, timestamps, and pagination; delete individual sessions or matching sessions in bulk.
Approvals & channelsPending decisions, approval configuration and routing, and notification channel management.
Budgets, audit & BridgeCost summaries, rankings and alerts; audit views; Bridge routes and route updates.
Judges & A/B testsConfigurations, results, statistics, variants, plans, comparisons, lifecycle, and evaluation queues.
AI GovernanceSystems, assessments, controls, transparency, monitoring, incidents, and evidence snapshots.

Connic MCP does not start agent runs directly and does not expose payments, credential management, project deletion, or account-security operations. Use connectors for event-driven runs. Treat text returned from runs, logs, connectors, sessions, and retrieval as data, not instructions.

Continue with Connic

REST API

Use project API endpoints directly from your own software

CLI

Build, test, and deploy from your terminal

Runs & Traces

Understand the run data exposed by MCP tools

Approvals

Review and control tool calls that require approval