Skip to main content
Connic
Back to BlogAnnouncement

Introducing Connic MCP: Operate Connic from Your Coding Agent

Connect any MCP coding agent, like Codex, Claude Code, or Cursor, to your Connic project. Debug runs, ship deployments, manage agents without leaving your editor.

August 10, 20267 min readAuthor: Connic Engineering

Today we are shipping Connic MCP: a direct connection between your coding agent and your Connic project. Any client that speaks MCP, whether that is Codex, Claude Code, Cursor, or something else, can now read live runs, traces, and logs, ship deployments, and manage your project in the same chat where it writes your agents. The detour through the dashboard is over.

Coding agents already write Connic agents well: the YAML, the tools, the middleware. Operating them was a different story. To find out why a run failed or what a deployment's tests said, you left the editor for the dashboard, read the answer, and typed a summary of it back into the chat. The client that wrote the code could not see the system it was running on. Now it can ask directly. This became practical with the 2026-07-28 MCP release, the first protocol revision we would trust between a coding agent and production. Connic MCP is built on it, with a fallback for clients on the older protocol.

The whole development loop in one chat

Building an agent was already fast on Connic. The slow part was everything around it: checking whether the deployment's tests passed, digging into last night's failed runs, confirming the new version actually behaves better than the old one. Connic MCP moves that work into the conversation you are already having.

Debug in place
"Why did the refund agent fail last night?" Your agent pulls the failed runs, reads the traces, finds the tool call that errored, and proposes the fix in the same conversation.
Ship and verify
The fix goes out without switching windows: create the deployment, watch the tests, and activate the new version when they pass.
Ask instead of digging
Yesterday's cost by agent, the queue on staging, the state of a connector: questions you used to answer with dashboard tabs become one line in the chat.

An agent that can see real traces writes better fixes than one working from your paraphrase of an error, and one that can watch deployment tests can iterate until they pass instead of handing the checking back to you. Every step it can verify itself is a step you no longer sit in the middle of.

What your agent can do

The connection covers the Connic platform end to end, reading and acting on the same things you see in the dashboard:

AreaSeeDo
Agents and runsRuns, traces, logs, input and output previewsCancel or rerun single and bulk runs
DeploymentsDeployments, tests, deployment runsCreate, cancel, activate, redeploy
ConnectorsDefinitions, links, runs, stats, logsCreate, update, delete, link agents
RetrievalNamespaces, entries, sources, statsUpload content, manage and sync sources
DatabaseStats, collections, inferred schemas, full document queries and countsUpdate existing rows; delete documents and collections
SessionsPersistent session state, agent and user identity, timestampsSearch and filter; delete individual or matching sessions
Approvals and channelsPending approvals, routing, channelsApprove or reject calls, manage routing and channels
Judges and A/B testsJudge stats and runs, variants, comparisonsManage judges and tests, queue evaluations
Budgets and auditCost summaries, rankings, audit eventsManage budget alerts
Environments and governanceEnvironments, health, AI governance recordsManage environments and governance records

Connect a client in one command

Setup is one command, then a sign-in with your Connic account in the browser:

# Codex
codex mcp add connic --url https://mcp.connic.co/mcp
codex mcp login connic

# Claude Code
claude mcp add --transport http --scope user connic https://mcp.connic.co/mcp

# Cursor Agent, after installing the Connic plugin
cursor-agent mcp login connic

The recommended setup is the Connic plugin, which bundles this connection with the Connic skill, so your client both knows how to write Connic agents and can operate the project they run in. Follow the AI agent setup guide for the plugin install in Codex, Claude Code, Cursor, and OpenCode, and for connecting any other MCP-compatible client manually.

Give your coding agent a project

Install the Connic plugin or connect Connic MCP directly, and let your client work on the system it builds for.

Set up your coding client

You stay in control

Connecting a client does not hand it your project. When you approve the connection, you choose which project it sees, which environments, and whether it can only read or also act. A client can never do more than your own account can, and if your access changes, its access changes with it. Every connection is listed in project settings with what it is allowed to do and when it was last used, every action lands in the audit log, and revoking takes one click.

Some things are simply not there to misuse. A connected client cannot spend your money, read your credentials, delete your project, or start agent runs. To trigger agents from external systems, use a connector, the production path built for it. There are also no API keys involved anywhere: never paste a Connic API key into an MCP configuration or a chat.

The third MCP surface

Connic now speaks MCP in three places, and they point in different directions:

MCP servers in agents
A deployed agent consumes external MCP servers as tools, declared under mcp_servers in its YAML. Tools flow into your agent.
MCP Server connector
The connector exposes your deployed agents as MCP tools that outside clients can call. Your agents flow out as tools.
Connic MCP
A coding client operates the platform itself: runs, deployments, connectors, budgets. Control flows from the client into your project.

Connic MCP does not add tools to a deployed agent and does not expose an agent as a tool. If that is what you need, read the MCP servers guide for agents or see the MCP Server connector reference.

How do I start?

  • 1.Install the Connic plugin for your client, or add https://mcp.connic.co/mcp directly. Open the AI agent setup guide for the exact commands.
  • 2.Approve the connection in the browser: pick the project, the environments, and what the client is allowed to do.
  • 3.Ask your agent something you would have opened the dashboard for: the last failed run, the state of a deployment, yesterday's cost by agent.

Frequently Asked Questions

Connic MCP connects coding agents such as Codex, Claude Code, and Cursor directly to a Connic project. The agent can read runs, traces, and logs, manage deployments and connectors, decide approvals, and answer cost questions inside the chat, within the access you grant when you approve the connection.

Codex, Claude Code, Cursor, and OpenCode have documented one-command setups, and any MCP-compatible client that can connect to remote servers with a browser sign-in works too. The AI agent setup guide at connic.co covers each client.

No. You sign in with your Connic account in the browser and approve the connection there. Never paste a Connic API key into an MCP configuration or a chat; there is no setup path that needs one.

No. There is deliberately no way to start an agent run through Connic MCP. Event-driven runs go through connectors, which are the production path for triggering agents from external systems. Connic MCP can cancel and rerun existing runs where allowed.

Exactly what you grant when you approve it: one project, all environments or a subset, and read-only or read-and-act access. A client can never do more than your own account can, and you can review or revoke every connection in project settings.

No. The MCP Server connector exposes your deployed agents as MCP tools for outside clients to call. Connic MCP points the other way: it gives a coding client scoped access to the platform your agents run on. The two work independently and can be used together.

More from the Blog

Announcement

Introducing Connic Models: Every Model EU-Hosted, Zero Config

Connic Models unify 30 EU-hosted models from nine creators behind one set of connic/* IDs. Name one in agent YAML: no provider account, no key, no region flag.

July 30, 202610 min read
Announcement

Introducing the Connic Marketplace

The Connic Marketplace is the new home for agent templates, connectors, and retrieval sources. One catalog, one publisher model, one CLI install.

July 5, 20265 min read
Industry Insights

Webhook vs Kafka vs SQS vs Postgres for AI Agent Triggers

Compare webhook, Kafka, SQS, and Postgres LISTEN/NOTIFY as AI agent triggers by delivery guarantees, ordering, replay, latency, and failure behavior.

June 29, 20269 min read
Industry Insights

Pre-built AI Agent Connectors: Platforms, Types & Checklist (2026)

Compare pre-built AI agent connector platforms, connector types, supported modes, and the delivery guarantees to verify before choosing one.

June 16, 20269 min read
Changelog

What We Shipped in May 2026

An agent testing framework, deploy gates with pull-request testing, deeper tracing for triggered and child runs, usage and budget dashboards, custom domains for connectors, and per-agent reasoning effort with cascading defaults.

June 1, 20267 min read
Product Spotlight

Connic Tests: Catch Agent Regressions Before They Reach Production

A YAML-driven testing framework built for non-deterministic AI agents. Repeated-run pass thresholds, expression-based assertions, custom-code mocking, multimodal fixtures, and a deploy gate that blocks failed checks by default.

May 6, 20268 min read
Changelog

What We Shipped in March 2026

A/B testing, agent guardrails, API spec tools, dashboard templates with percentile metrics, migration CLI, and more.

April 1, 20266 min read
Tutorial

Migrate from LangChain to Production AI Agents

Your LangChain prototype works. Now you need it to handle real traffic. Learn how to migrate existing agent code to a production-grade platform without rewriting from scratch.

March 23, 202611 min read
Changelog

What We Shipped in September 2025

Full audit logging with before/after diffs, data residency region selection, distributed rate limiting for connectors, and billing cost breakdown.

October 1, 20254 min read