t3_openbot
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@t3_openbot ask Ada in OpenBot to summarise today's inbox"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
T3 Code × OpenBot connector
Lets an agent in a T3 Code thread hand work to an OpenBot agent and get the answer back in the same thread, and lets an OpenBot agent delegate coding work to T3 Code. It works with both apps as shipped.
How it works
The connector is a small stdio MCP server that the Codex or Claude provider inside T3 Code starts on demand. It keeps no state, opens no port, and holds no credential of its own. OpenBot is an MCP client but not an MCP server, so this adapter is T3 Code's way in. The way back is T3 Code's built-in MCP endpoint, which OpenBot connects to directly.
Related MCP server: opencode-mcp
Why not plain MCP in both directions?
One direction already is plain MCP: OpenBot connects straight to T3 Code's endpoint. The other direction cannot be, because OpenBot does not serve MCP. Its way in is a local HTTP API whose port and token change on every start.
Plain MCP only | With this connector | |
OpenBot agent calls T3 Code | ✅ T3 Code's built-in endpoint | ✅ The same endpoint, untouched |
T3 Code agent calls OpenBot | ❌ OpenBot has no MCP server | ✅ Six tools over the Local scripts API |
OpenBot's port and token after a restart | Re-entered by hand | Read fresh on every call |
Getting the answer back | Nothing links a reply to a request | Tagged report into the thread that asked |
Knowing which thread asked | You pass the thread ID yourself | Taken from the T3 Code session |
Retrying a send safely | Duplicates the task | Stable key, deduplicated by OpenBot for 24 hours |
Agent waiting for a reply that never comes | Common | The task states the report is one-way |
Failed tasks | Silent | Reported with |
Two agents answering each other in a loop | Possible | Results are sent with reporting off |
Extra processes, ports, or secrets | None | None |
The connector adds two things: a translation from OpenBot's HTTP API to MCP tools, and the convention that makes a one-way send behave like a round trip.
Requirements
Node 22 or newer
T3 Code with the Codex or Claude provider
OpenBot 0.40.0 or newer
Set up once
Build and register. Run this with the Node you want the providers to use.
git clone https://github.com/sdlyy/t3-openbot-connector.git cd t3-openbot-connector npm ci npm run build npm run registerregisteradds onet3_openbotentry to~/.codex/config.tomland one to~/.claude.json, and leaves everything else in those files alone.In OpenBot, allow access. Open the agent, choose Permissions, turn on Local scripts.
In OpenBot, connect to T3 Code. Add an MCP server of type Streamable HTTP with the URL
http://127.0.0.1:3773/mcp, then Sign in with a pairing code from T3 Code Settings → Connections.In OpenBot, give the agent its standing instructions. Copy them from docs/agent-instructions.md.
Check.
npm run doctorlists the agent and shows both registrations as current.
Use
Open a new T3 Code thread and say, for example, "ask Ada in OpenBot to summarise today's inbox". The T3 agent queues the task and ends its turn. The answer arrives in the same thread as a new message:
[OpenBot report] agent: Ada · request: inbox-1 · outcome: completed
...Tool | What it does |
| Checks the connection and shows the thread reports go to |
| Lists agents that allow Local scripts, with their routines |
| Queues a task; the agent reports back into the calling thread |
| Starts an existing routine now, with an optional payload |
| Shows questions and approvals an agent is waiting on |
| Answers a pending question |
How results come back
OpenBot has no way to read a finished answer from outside, so the agent delivers it. The connector
appends a short block to each task that tells the agent to post one tagged report into the T3 thread
and then end its turn. This relies on the agent following the instruction: an agent that crashes or
is stuck on a question does not report, and list_pending is how you find out.
Security
The connector talks only to
127.0.0.1and reads only the URL and token files OpenBot publishes for the current user.OpenBot's per-agent Local scripts switch is the grant. An agent without it is unreachable.
Approvals are never answered through the connector; they stay in OpenBot.
A report is text written by another agent. The T3 agent is told to treat it as data, not as instructions.
Development
npm testThe tests start the real CLI over stdio against a stand-in for OpenBot's Local scripts API. Set
T3_OPENBOT_DEBUG=1 to print raw tool errors to stderr.
More
This is an independent project, not affiliated with T3 Code or OpenBot. MIT licensed.
Available Tools
6 toolsanswer_promptADestructiveIdempotent
Answer a pending question from list_pending. Keys are question IDs, values are arrays of answer strings. An expired request returns openbot_conflict; read list_pending again instead of retrying.
Inputs: agent (required), answers (required), requestId (required).
list_agentsARead-onlyIdempotent
List the OpenBot agents that allow Local scripts, with their routine summaries.
Inputs: no named parameters.
list_pendingARead-onlyIdempotent
Read the agent's requests that wait for a person: questions, approvals, and browser takeovers. Only questions can be answered through this connector; approvals stay in OpenBot.
Inputs: agent (required).
openbot_statusBRead-onlyIdempotent
Check the connection: the OpenBot profile in use, its agents, and the T3 thread reports go to.
Inputs: no named parameters.
run_routineBDestructiveIdempotent
Start an existing routine now. The optional payload is appended to the routine's instruction as data. A run has no retry key. Routine IDs come from list_agents.
Inputs: agent (required), routineId (required), payload.
send_messageADestructiveIdempotent
Queue work for an OpenBot agent, by ID or name, and return immediately. When it is done the agent posts its tagged answer, or its failure, into the calling T3 thread as a new message. Each send is self-contained: include the context the agent needs. Set report to false for fire-and-forget work.
Inputs: text (required), agent (required), requestId (required), report, +1 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 6 tools
Most tools have clearly distinct purposes: status vs. listing agents vs. sending messages vs. handling pending questions. The only mild overlap is send_message and run_routine, both of which initiate work, but their descriptions distinguish agent-directed work from existing routines.
Five tools follow a clear verb_noun pattern (list_agents, send_message, run_routine, list_pending, answer_prompt). openbot_status is a minor deviation using a noun-prefixed status form, but it remains readable and predictable.
Six tools is well-scoped for a focused OpenBot connector. Each tool maps to a distinct operation with no obvious redundancy.
The set covers the core lifecycle: check status, list agents, dispatch work, run routines, inspect pending requests, and answer questions. Approvals and browser takeovers are intentionally handled outside the connector, and there is no cancel/stop operation, but these are minor gaps for the stated purpose.
Related MCP Connectors
Delegate tasks between AI agents on different platforms and collect the results.
One shared project for a team's coding agents: decisions, a task board and handoffs.
Agents message each other and partners' agents. Claude Code, Codex (beta): memory, board, key vault.
Hand off work between AI agents in any tool. Start Devin or Cursor cloud and share memory.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to explore, search, and reference code implementation details across different project repositories. It also supports a task delegation protocol for agents to request and track work between separate codebases.MIT
- AlicenseAqualityBmaintenanceEnables Claude Code to delegate tasks to OpenCode subagents asynchronously, with tools for starting tasks, polling status, and fetching results.7288 npm6MIT
- AlicenseAqualityCmaintenanceEnables Codex/ChatGPT to coordinate OpenCode agents, managing tasks, sessions, parallel execution, and project context through 25 local tools.254 npm1MIT
- AlicenseAqualityDmaintenanceLets Claude Code delegate coding tasks to external models running on a local opencode serve, preserving main agent tokens for planning and review.81MIT