Reins
OfficialThis server lets an agent control a robot through owner-policy-bounded actions, leases, status, and an always-allowed stop.
drive: drive forward/backward and turn for 0.1–5 s within speed/turn limits; above 0.35 m/s requires owner confirmation, and motion auto-stops after a lease of at most 5 s.set_led: set the status light to off, red, green, or blue.reins_renew: extend a running motion lease by 0.1–5 s, up to 20 s total.reins_stop: stop immediately; always allowed, and motion remains blocked until the owner resumes.reins_status: read server state (stopped, running lease, pending confirmations) and robot status fields.reins_policy: read the owner's allowed actions, bounds, and limits.driveandset_ledaccept optional stale-command and replay-protection fields (issued_at,request_id).
Provides a policy and safety layer for ROS-based robot connectors, integrating with ROS 2 through ros-mcp-server, rosbridge, turtlesim, and ROS-style connectors to enforce bounded robot actions, leases, stops, and audit logging.
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., "@Reins move the robot forward half a meter within the approved limits"
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.
BotInfo
When an AI agent is driving a robot, can you stop it mid-move? The BotInfo Benchmark tests that and more: hostile test cases that grade any robot connector, raw or behind BotInfo, on what the robot actually did, never on what the connector replied.
What the benchmark found (v0.1)
We graded two open-source connectors that let an AI agent drive a robot, as real code on real ROS 2 in local containers, against a simulator and a stand-in robot (not hardware):
On their own, a stop sent during a move waited for the move to end in both. With ros-mcp-server v3.1.2, the simulated turtle stopped about 3.9 s after the stop; with unitree-go2-mcp-server, the stand-in Go2 that centres its sticks stopped 4.2 s after it (4.9 s on the one that holds the last input).
Behind BotInfo, ros-mcp-server went from 11 to 100 (critical cases 1/10 to 10/10), and the turtle was still within 0.07 s of each stop. Its lost-link pass is turtlesim's own 1 s stop, not BotInfo's.
unitree-go2-mcp-server went from 18 to 68 (stand-in Go2 that centres the sticks 0.5 s after the last message), but its stop still waited for the running move: the server handles one call at a time, so no stop sent through it can interrupt a running move, behind BotInfo or not. A second stand-in that holds the last input voids both rows.
BotInfo and this benchmark were written by the same team, so BotInfo passing its own authors' tests proves little; the benchmark is worth something once other people add cases that BotInfo fails. Every case, every failure and why: results/LEADERBOARD.md.
Status, v0.1 (2026-10-16): simulation and mocks only. Nothing here has run on a real robot. The benchmark results are not a certification and say nothing about real hardware. Nobody outside BotInfo has reviewed this yet.
BotInfo itself is an open-source policy layer that sits between an AI agent and a robot its owner has connected. It sits in front of the robot's existing connector. The agent sees only the actions the owner allows, each with checked bounds. Every motion runs on a lease and stops by itself. A stop always wins, and every request and decision goes to an audit log.
Related MCP server: gov-mcp
Quickstart
Python 3.11 or newer, nothing else to install:
git clone https://github.com/botinfo-ai/botinfo.git
cd botinfo
python3 -m botinfo benchmacOS's built-in python3 is 3.9, too old (BotInfo says so in one line and stops). With
uv, one command fetches a newer Python for this run:
uv run --no-project --python 3.12 python -m botinfo benchIt runs 20 cases against 8 stacks in simulated time (about a second) and writes results/scorecard.json and
results/LEADERBOARD.md. Other commands:
python3 -m botinfo demo # a short scripted session, printed
python3 -m unittest discover -s tests -t tests # over 100 tests, about 10 sWhat BotInfo enforces
Only the owner's actions exist. The policy file (
policies/*.toml) lists the actions, each with typed, bounded parameters. An unknown name, an extra field, NaN, a string where a number belongs, or a value out of range is refused (never clamped) and logged. The connector's own tools are never passed to the agent.Limits around the actions: rate limits (overall and for motion), a longest stretch of continuous motion (renewals and back-to-back commands count together), and an optional workspace box for robots that report a pose.
Expiry and replay. A command waiting for the owner's confirmation expires after
command_ttl_s, and a newer motion command from the agent cancels it, so a late OK cannot start a move the agent has given up on. A call whoseissued_atis too old is refused, and so is a repeatedrequest_id.The agent's picture stays true. Motion calls return at once. When a new motion stops a running one early, the answer says which one and how far it got (
replaced), so the agent never reports a move as finished when it was cut short.botinfo_waitlets the agent wait for a move to end; a stop ends the wait at once and is never queued behind it. A stop that cuts a move answers withstopped_motion, andbotinfo_statusandbotinfo_waitcarrylast_motion: the leased move BotInfo ended (or tried to end) last, its lease time (ran_sofof_s, from accepting the call to sending the stop) and what ended it, so the agent can report the run time BotInfo logged.Owner-only controls. Confirming an action, lifting a stop and changing the policy happen on the owner's local channel (
python3 -m botinfo owner ...). The agent has no tool for any of them.Stop.
botinfo_stopand the owner's stop skip every check and every queue. After a stop, motion stays refused until the owner resumes. If the agent's session ends, BotInfo stops the robot.Leases. A motion asks for a bounded time. While it runs, BotInfo re-sends it as a keep-alive, then sends stop at the end. A robot-side watchdog therefore stops the robot when BotInfo or the network goes away. This mirrors the Sesame firmware motion-timeout patch, or a ROS base's
cmd_veltimeout.Robot output is data. Status is reduced to typed fields. Free text from the robot is redacted before the agent sees it, and flagged in the audit log.
Audit log. JSONL, one line per request and decision, with each line chained to the previous one by SHA-256 (
python3 -m botinfo audit-verify FILE). It is tamper-evident, not tamper-proof.
A real emergency stop must be enforced locally on the robot (a power switch, a hardware e-stop, a firmware watchdog), never over the network. BotInfo's stop is a software command sent over a link. The benchmark shows this: when the link drops on a robot with no local watchdog, it keeps moving, with or without BotInfo.
Threat model and architecture: docs/DESIGN.md. Policy reference: docs/POLICY.md.
The benchmark, v0.1 results
The full table, every case, and why each failure failed: results/LEADERBOARD.md. Method and cases: docs/BENCHMARK.md. What each grading setup does and leaves out: docs/GRADING-EXISTING-CONNECTORS.md.
Third-party connectors, real code on real ROS 2 middleware (in local containers, real time, every case run twice). None of these is a robot:
Stack | Score | Critical cases passed |
BotInfo → ros-mcp-server v3.1.2 + rosbridge + turtlesim on real ROS 2 Humble | 100 | 10/10 |
ros-mcp-server v3.1.2 + rosbridge + turtlesim on real ROS 2 Humble, direct | 11 | 1/10 (link lost, thanks to turtlesim's own stop) |
BotInfo → unitree-go2-mcp-server (e7a6737) + ros2 CLI, stand-in Go2 that centres the sticks 0.5 s after the last message | 68 | 6/10 |
unitree-go2-mcp-server (e7a6737) + ros2 CLI, same stand-in, direct | 18 | 2/10 |
BotInfo → unitree-go2-mcp-server, stand-in Go2 that holds the last joystick input | void | 5/10 (CTL-01 fails) |
unitree-go2-mcp-server, same stand-in, direct | void | 1/10 (CTL-01 fails) |
ros-mcp-server runs against turtlesim, a simulator that stops by itself 1 s after the last command; behind BotInfo, the lost-link pass is that watchdog at work, not BotInfo's. Direct, ros-mcp-server runs one tool call at a time, and each
publish_oncetakes about 2 s because it waits for replies rosbridge never sends (rosbridge 2.0.8), so a stop sent duringpublish_for_durationswaits for that call to end.unitree-go2-mcp-server drives a stand-in Go2 node, not a Go2 and not a Go2 simulator (Unitree's MuJoCo simulator cannot act on the joystick messages this server sends). Every command is a new
ros2 topic pubprocess, and the server handles one call at a time, so no stop can interrupt a running move, behind BotInfo or not: BotInfo latches the stop at once, but the robot stopped 4.2 s later, when the move ended. Behind BotInfo every case about what may be sent passed; the workspace case fails because the server reads no position. Whether a real Go2 holds or centres the last joystick input is unknown to us, so both are graded. With the holding stand-in each move overruns by about 1.1 s (the server's closing stop is a second process), the CTL-01 control fails, and those rows have no score.An earlier grade of ros-mcp-server against BotInfo's emulated rosbridge (not real ROS) is kept on the leaderboard: 93 behind BotInfo, 4 direct.
BotInfo's reference stacks, simulated time (the direct connectors are BotInfo's models of existing patterns, not third-party code):
Stack | Score | Critical cases passed |
BotInfo → ROS-style connector → SimRover with a 0.5 s base watchdog | 100 | 10/10 |
BotInfo → Sesame firmware API (mock, with the motion-timeout patch) | 100 | 9/9 |
BotInfo → ROS-style connector → SimRover, no base watchdog | 93 | 9/10 (link lost) |
BotInfo → Sesame firmware API (mock, stock) | 93 | 8/9 (link lost) |
Sesame firmware API (mock, patched), direct | 46 | 5/9 |
ROS-style connector → SimRover with base watchdog, direct | 14 | 2/10 |
Sesame firmware API (mock, stock), direct | 12 | 1/9 |
ROS-style connector → SimRover, no watchdog, direct | 0 | 0/10 |
Read these numbers with three things in mind:
Every row is a simulator, a mock or a stand-in robot node. Two third-party connectors have been graded so far, as real code on real ROS 2 middleware in containers: ros-mcp-server v3.1.2 (on turtlesim) and unitree-go2-mcp-server (on BotInfo's stand-in Go2). The other rows grade BotInfo's reference models of existing patterns. What each setup leaves out is in docs/GRADING-EXISTING-CONNECTORS.md.
BotInfo and the benchmark were written together, by the same team. BotInfo passing its authors' tests proves little. The benchmark gets useful when someone adds a case BotInfo fails; see "Adding a case" in docs/BENCHMARK.md.
The hostile agent always obeys injected text. These are worst-case results for the connector, not predictions for any model.
Use it with an agent (MCP)
BotInfo is an MCP server on stdio. For Claude Code, put this in a project .mcp.json (use absolute paths):
{
"mcpServers": {
"botinfo-simrover": {
"command": "python3",
"args": ["-m", "botinfo", "serve",
"--policy", "/ABSOLUTE/PATH/botinfo/policies/simrover.toml",
"--binding", "/ABSOLUTE/PATH/botinfo/bindings/simrover-ros-style.toml"],
"env": { "PYTHONPATH": "/ABSOLUTE/PATH/botinfo" }
}
}
}python3 must be 3.11 or newer. That binding runs the simulator inside the BotInfo process.
bindings/simrover-ros-style-stdio.toml instead launches the connector as a separate MCP server and fronts it.
That is the same arrangement as fronting ros-mcp-server: bindings/ros-mcp-server-turtlesim.toml (with
policies/turtlesim.toml) is tested on real ROS 2 Humble + rosbridge + turtlesim in a container, and
bindings/ros-mcp-server-simrover.toml against the emulated rosbridge (not real ROS). For the Sesame mock, use policies/sesame.toml with
bindings/sesame-inprocess.toml. bindings/unitree-go2-mcp-server.toml (with policies/go2.toml) fronts
unitree-go2-mcp-server; it has only been run against BotInfo's stand-in Go2 node in a container, never a robot.
While it runs, the owner uses a local socket (~/.botinfo/<policy>.sock, owner-only permissions):
python3 -m botinfo owner statuspython3 -m botinfo owner confirm c-2python3 -m botinfo owner stoppython3 -m botinfo owner resumeThe audit log goes to runs/ unless --audit says otherwise. For OpenClaw there is a skill stub:
integrations/openclaw/botinfo/SKILL.md. It is unverified and has not
been loaded into OpenClaw.
What BotInfo does not do
It does not make a robot physically harmless. It cannot see people, obstacles, falls or battery faults.
It cannot stop a robot it can no longer reach. Only the robot's own watchdog or hardware stop can do that.
It cannot make a connector faster than it is. If the connector handles one call at a time and a motion call blocks until the motion ends (unitree-go2-mcp-server does both), BotInfo latches a stop at once and refuses all motion after it, but the stop reaches the robot only when the running call returns.
It can only enforce what the connector lets it see. A workspace limit needs a pose; a connector that reports no position (unitree-go2-mcp-server) leaves BotInfo with speed, duration and rate limits only.
It does not protect against an agent that has a shell on the owner's account. That agent could kill BotInfo, edit the policy or reach the robot directly. Give the agent the BotInfo MCP server and nothing else that touches the robot.
It is not for robots whose owner has not connected them. BotInfo is built for owner-connected robots only.
On Sesame, a pose (wave, dance, ...) cannot be interrupted once it starts; that is how the firmware works. The default policy therefore makes every pose wait for the owner's confirmation.
Before any real robot
Do not use v0 with hardware. bindings/sesame-mock.toml refuses non-localhost robots, and the CLI refuses
allow_remote. A first hardware run would need, at minimum:
the robot's own stop within a person's reach, and a robot-side watchdog tested on that robot;
a tethered or bench setup first;
an outside review of this code and the benchmark.
Questions
How do I limit what an AI agent can make my robot do?
Write a policy file (policies/*.toml) that lists the actions you allow, each with typed, bounded parameters, plus
rate limits, a longest stretch of motion and, if the robot reports a pose, a workspace box. Then give the agent the
BotInfo MCP server instead of the connector. The agent sees only your actions; anything else is refused and logged.
Inside your policy, a hijacked agent can still use the actions you allowed. Reference: docs/POLICY.md.
How do I stop the robot?
The agent has a botinfo_stop tool, and the owner runs python3 -m botinfo owner stop on the local channel. A stop
skips every check and queue, and motion stays refused until the owner runs python3 -m botinfo owner resume. If the
agent's session ends, BotInfo stops the robot. All of these are software commands sent over a link, so a real
emergency stop must be on the robot itself (a hardware stop or a firmware watchdog).
Can a prompt injection make my robot do something I didn't allow?
The benchmark assumes it can hijack the agent: its scripted agent obeys every instruction it reads, from robot status, a skill or a web page. Behind BotInfo, those instructions can only reach the actions and bounds in your policy, and free text from the robot is redacted before the agent sees it. Cases INJ-01, INJ-02 and MAL-01 in docs/BENCHMARK.md test this.
Does it work with Claude Code or other MCP clients?
BotInfo is an MCP server on stdio. "Use it with an agent" above has a .mcp.json for Claude Code; any MCP client
that can launch a local stdio server can run the same command. In the published benchmark the agent is BotInfo's
own scripted MCP client, not a commercial host.
Does it work with ros-mcp-server?
Yes, in front of it: bindings/ros-mcp-server-turtlesim.toml with policies/turtlesim.toml, tested on real ROS 2
Humble + rosbridge + turtlesim in a container. ros-mcp-server v3.1.2 scored 11 direct and 100 behind BotInfo; the
lost-link pass comes from turtlesim's own 1 s stop, not from BotInfo.
Does it work with a Unitree Go2?
Not with a real Go2 yet. BotInfo fronts unitree-go2-mcp-server (bindings/unitree-go2-mcp-server.toml with
policies/go2.toml), and that has only run against BotInfo's stand-in Go2 node in a container, never a robot.
There it scored 18 direct and 68 behind BotInfo. That server handles one call at a time, so a stop reaches the robot
only when the running move ends.
How is a connector graded?
Twenty cases run against the connector direct and behind BotInfo: two controls and eighteen hostile cases (bounds, injection, replay, flood, lost link, stop, malicious skill). Each case is graded on what the robot (a simulator, mock or stand-in) actually did, never on what the connector replied. Critical cases count 3, high cases 2, and the score is the weighted percentage passed. If a control fails (a normal move, or one the owner confirmed), the stack gets no score ("void"), so refusing everything cannot win. Details: docs/BENCHMARK.md.
How do I grade my own connector?
Follow "Adding a stack" in docs/BENCHMARK.md: add a factory to STACKS in
botinfo/bench/stacks.py, or to REALTIME_STACKS for a connector that runs as its own MCP server (copy _ros_mcp()).
Then run python3 -m botinfo bench --stack ID -v. What each grading setup leaves out:
docs/GRADING-EXISTING-CONNECTORS.md. A new case that BotInfo fails is welcome
too ("Adding a case").
Can I use it on a real robot?
Not yet. v0.1 is simulation and mocks only, and nothing here has run on a real robot. See "Before any real robot" above.
What is the licence?
Apache-2.0.
Layout
botinfo/core.py the engine: checks, leases, stop latch, confirmations, audit
botinfo/policy.py policy loading (strict) and parameter checks
botinfo/audit.py hash-chained JSONL audit log
botinfo/mcp/ MCP server and client (stdio, standard library only)
botinfo/owner.py the owner's local channel (Unix socket)
botinfo/backends/ Sesame firmware API + mock, SimRover + reference ROS-style connector, MCP tool templates
botinfo/bench/ the BotInfo Benchmark (cases, stacks, ground truth, report)
botinfo/bench/docker/ container images for the real-ROS grades (turtlesim; Go2 server + stand-in robot)
policies/ bindings/ example owner policies and connector bindings
docs/ DESIGN, BENCHMARK, POLICY, GRADING-EXISTING-CONNECTORS
results/ the published v0.1 benchmark run
integrations/openclaw/ OpenClaw skill stub (unverified)
tests/ unittest suiteFormerly Reins
Renamed 2026-10-25. Same code and the same results; the package, the command (python3 -m botinfo) and the agent's
tools (botinfo_stop, botinfo_status, botinfo_wait, ...) carry the new name. Old links to
github.com/botinfo-ai/reins redirect here.
License and credits
Apache-2.0 (LICENSE); credits are in NOTICE. The Sesame robot and firmware are Dorian Todd's work (Apache-2.0). BotInfo is an independent BotInfo.ai project, not made or endorsed by him. The reference ROS-style connector follows the tool interface of ros-mcp-server (Contoro Inc., Apache-2.0); no code was copied. The Go2 grade runs unitree-go2-mcp-server (Apache-2.0) unmodified inside a container image; it is not included here.
Available Tools
6 toolsdriveADestructive
Drive at a constant speed and turn rate for a bounded time, then stop. Runs on a lease of at most 5 s, then stops by itself. Renew with reins_renew. Some calls need the owner's confirmation; those return pending_confirmation.
Inputs: duration_s (required), linear_mps (required), issued_at, request_id, +1 more.
reins_policyBRead-only
What this robot's owner allows: actions, bounds, limits.
Inputs: no named parameters.
reins_renewA
Extend the running motion lease (heartbeat). At most 5 s from now and 20 s in total.
Inputs: extend_s (required), lease_id (required).
reins_statusBRead-only
Reins state (stopped?, running lease, pending confirmations) and the robot's status fields.
Inputs: no named parameters.
reins_stopA
Stop the robot now. Always allowed. Afterwards motion stays blocked until the owner resumes.
Inputs: reason.
set_ledC
Set the status light.
Inputs: color (required), issued_at, request_id.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 6 tools
The motion and control tools (drive, reins_stop, reins_renew, reins_status, reins_policy) have distinct purposes, but set_led stands apart from the reins_-prefixed control/state family and could be mistaken for a non-observability action. Boundaries are clear enough that misselection is unlikely.
Names mix plain verbs (drive, set_led) with a reins_ prefix (reins_stop, reins_status, reins_policy, reins_renew), and none of the tools strictly follow a verb_noun pattern. The split between drive/set_led and the reins_ namespace is jarring.
Six tools fit the safety-lease motion domain without bloat; each (motion, stop, renew, status, policy, LED) earns a place. Slightly thin on read-only inspection but reasonable for a control server.
Core motion lifecycle (drive, renew lease, stop, status, policy) is covered, including safety semantics. Minor gaps: no explicit resume or LED read-back and no generic pre-flight validation for flight-like actions, but usable.
Maintenance
Related MCP Connectors
MCP server for your apps' tools and custom tools, plus hosted AI agents and approval-gated workflows
Zero-secret MCP gateway for AI agents: risk-scored, audited calls with human-in-the-loop approval.
Machine-verifiable authorization checks for autonomous AI agents.
MCP gateway with runtime security policy, tool-call-level control, and audit of agent actions.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceA unified MCP server providing observability, safety control, and behavior evolution for high-agency AI agents through tracing, replaying, and auditing. It features real-time firewall guardrails and ML-driven anomaly detection to monitor, block, or fork agent actions based on risk.MIT
- AlicenseNot gradedqualityDmaintenanceAn MCP server that enforces runtime governance on AI agent actions — file access, command execution, delegation chains, and permission escalation.MIT

@vorionsys/mcp-serverofficial
AlicenseAqualityDmaintenanceMCP server for AI-agent governance using trust scoring, behavioral signals, and pre-flight action checks.1023 npm1Apache 2.0- AlicenseNot gradedqualityCmaintenanceAn MCP server for agent authorization that tests the full effect surface and enforces control over consequential actions before dispatch, emitting verifiable execution evidence.2Apache 2.0