Gantry
This read-only Gantry MCP server lets you inspect project state, artifacts, evidence, reviews, bots, onboarding, and Studio collaboration context.
Read identity, product overview, project details, state, history, events, open items, outcomes, impact, and why-traces.
Retrieve development states, designs, work context, session details, and focused context with dependency/discussion paging.
List and read artifact files, batch parts, or hash-verified chunks; restore saved bytes or metadata-only manifests.
Query, view, and render evidence; read validation plans and design assessments.
Inspect change reviews, review context, review automation, related review context, team proposals, and team messages.
Access bot inboxes, issues, memories, persistent bots, bot context, crew setups, and review teams.
Use Studio read views for overview, context, related items, inbox, library, team, and work.
Read onboarding discovery, source manifests, prior answers, and customer-agent contracts.
Poll durable event notices with cursors and deduplicate by event_id.
All exposed tools are annotated read-only; they do not appear to write, approve, adopt, or execute project changes.
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., "@Gantry checkpoint this unverified change and submit it for review"
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.
Gantry
A shared place for people and agents to develop robot hardware and software.
Keep working in your CAD tools, editor and simulator. Use Gantry to share unfinished changes, preserve their context, and let another person or agent continue from the same version.
Try the demo · Get started · Tool support · Documentation
The website and demo source includes local preview and test instructions.
The demo uses invented, browser-only data. Local operation is the supported starting point. The latest packaged release is v3.4.2, including guided project onboarding and contextual Studio Bot work.
How it works
flowchart LR
A["Your tools and agents<br/>CAD · Code · Simulation"] -->|Capture saved work| B["Gantry Ledger<br/>Versions · Requirements · Evidence"]
B -->|Restore and continue| A
B <-->|Shared changes and discussions| C["Your team<br/>Studio · CLI · MCP"]Bring existing work. Select saved files from a project already in progress.
Share a checkpoint. Keep the changes, reasons, requirements and unfinished work together.
Discuss or review. Refer to a specific artifact version, CAD part or code line.
Continue. Restore the shared state, make the next change, and retain its evidence.
Sharing, passing a check and formally adopting a design are separate actions. An old test result never becomes a pass for a new combination of files.
Related MCP server: Nolane Habitat
Choose how to use Gantry
Both options use the same development history. You can start with Ledger alone.
Gantry Ledger | Gantry Crew | |
Use it to | Share and review development state | Delegate development to a persistent Bot team |
Who drives the work? | Your team and its existing agents | Bots with assigned roles and delegated authority |
Main capabilities | Versions, requirements, discussions, evidence, optional Mentor review | Role memory, consultation, hierarchical delegation and handoffs |
Entry point |
|
|
Guide |
Mentor reviews submitted changes and proposes follow-up work. Crew Bots reason and act within their roles; Mentor is not their manager. Core stores the decisions and enforces access and version integrity—it does not choose the best engineering design.
You supply the agent runtime and model account. No inference provider is enabled by default, and storing development state needs no model account.
Get started
Connect your local agent
Use patched Python 3.11+ on macOS or Linux. Before installing, follow the runtime and installer security guide, including its hash-pinned pip bootstrap.
git clone https://github.com/fourn9/gantry-oss.git
cd gantry-oss
python3 -m venv .venv
# Apply the installer updates described in the security guide above.
.venv/bin/python -m pip install .
.venv/bin/python -m gantry.security_check
.venv/bin/gantry connect /path/to/your/project --client codex \
--path src/ --path tests/ --write-path src/ \
--goal "Improve request clamping" \
--done "Existing boundary tests pass without changing their assertions"Review and confirm the permission plan: selected files, writable scope, test commands and completion conditions. Gantry creates the local ledger and scoped identities, captures saved files, and adds its project MCP entry. Client trust settings remain under your control.
Choose
--client claude,cursororgenericfor another client.The default permits scoped work. Choose
--mode record-onlyto record externally edited files instead.This local route needs no separately operated server. Tests are refused when a supported command sandbox is unavailable.
Full setup and daily commands →
Share work in Studio
For a visual workspace, follow Studio setup, then choose Import project:
Select files → Review scope → Clarify components → Open first work → Share update
Guided setup preserves answers and corrections across interruptions. Agent interpretation is optional; it does not execute the project or approve its design.
Studio keeps the product structure and team work together, with CAD, Code and Checks tabs. Conversations stay attached to their target and version. Another authorized participant can restore a shared version into a separate workspace.
Open Team to configure persistent Bot roles and customer runtimes. From a work, CAD part or code line, Ask a Bot queues a read-only question; Assign work queues a scoped edit. Answers return to the original conversation and Inbox; edits return as separate shared candidates. Browsing or mentioning a Bot does not start it. Studio Bot setup and handoff →
Guided onboarding · Sync, share and continue · Self-hosting and membership
What stays with the work
Saved information | What it enables |
Artifact snapshots and development states | Restore the exact saved files and their context |
Requirements, changes and declared dependencies | Trace the purpose of a change and what needs reassessment |
Evaluations tied to input versions | Distinguish current evidence from obsolete or missing checks |
Discussions, decisions and alternatives | Understand why a choice was made and what remains unresolved |
Bot roles, experience and execution journals | Carry context into later work and recover supported interrupted operations |
Gantry preserves original captured data. It does not infer complete cross-tool dependencies or certify physical safety. Native editing and engineering validation still require the appropriate tools and evidence.
Tool support
Capture, editing and live synchronization are different capabilities. Check the exact route before adopting an integration.
Route | Available today | Boundary |
Saved files and Git | Versioned capture, restoration, explicit sync and sharing | Only captured scope; unsaved edits are not included |
GitHub and external records | Issue, PR and CI ingestion; bounded readers and saved exports | Authentication and capture coverage depend on the connector |
Headless OCP / STEP | Optional local read, edit, write and static interference checks | Not a universal CAD editor or physical-validity guarantee |
Strength, tolerance and prototype results | Evidence capture against a frozen acceptance plan | Requires an actual evaluator or measured input |
Commercial CAD / ECAD | Experimental desktop operations and generated editor scripts | No verified live run for the eight listed vendor products; Zuken and Capital SDK implementations remain blocked |
Integration coverage · Native desktop support · Hardware adapter
Local workspace capture supports up to 10,000 files / 1 GiB with frozen, resumable uploads. Guided browser onboarding supports 1,000 files / 32 MiB, at most 16 MiB per file.
Watching saved files is opt-in. It never shares or formally adopts changes automatically.
Local reviews and tests have no Gantry count cap. Scope, revocation, command timeouts, branch limits and provider limits still apply. Existing finite credentials retain their approved expiry.
Default Mentor review uses your client through structured prepare/finish tools. It does not automatically launch an independent reviewer. Subscription-based review is an explicit opt-in.
Single-host deployment and backup/restore procedures are provided. They do not provision a cloud account, email invitations or enable paid inference.
Native-runtime qualification, broader physical validity and engineering speedup remain separate from functional tests.
Recovery · Executed acceptance and limits
Documentation
Browse all guides · Examples · Verification records
I want to… | Read |
Connect an agent and review a change | |
Import, share or restore a project | |
Link requirements, changes and checks | |
Configure a Bot organization | Studio team onboarding · CLI onboarding · Crew organization · Persistent Bots |
Use and evaluate Bot experience | |
Connect engineering tools | |
Operate a shared deployment | |
Understand the architecture |
Privacy and contributions
Feedback is off by default. You may opt into statistics and individually selected diagnostics. Nothing is sent in the background; every encrypted upload requires preview confirmation. No public receiver is preconfigured.
Privacy · Security policy · Optional encrypted feedback
Report issues, propose adapters or contribute tests. Use minimal synthetic examples—never confidential CAD, source, logs or credentials.
.venv/bin/python -m pip install ".[feedback]"
.venv/bin/python -m unittest discover -s tests -p 'test_*.py' -q
node --test tests/test_*.mjsCore tests use the standard library. Optional NumPy and CAD tests skip when dependencies are absent. Use GANTRY_CAD_PYTHON to select a separate interpreter with Gantry [cad] installed.
Contributing guide · Synthetic end-to-end example
License
MIT. The published source, including Core and Mentor orchestration, may be used, modified and redistributed. Third-party tools and models retain their own licenses and terms.
Available Tools
52 toolsbot_inboxDRead-only
bot inbox
Inputs: arguments (required), idempotency_key.
contextBRead-only
Read work context. Full is unchanged. Focused requires entry_ids, follows declared dependencies in the fixed design, and pages related discussion. Explicit omissions are not an impact analysis or approval.
Inputs: arguments (required), idempotency_key.
designDRead-only
design
Inputs: arguments (required), idempotency_key.
development_stateDRead-only
development state
Inputs: arguments (required), idempotency_key.
eventsCRead-only
Poll durable notices from a ledger sequence cursor; deduplicate by event_id.
Inputs: arguments (required), idempotency_key.
get_bot_contextDRead-only
get bot context
Inputs: arguments (required), idempotency_key.
get_bot_issueDRead-only
get bot issue
Inputs: arguments (required), idempotency_key.
get_change_reviewDRead-only
get change review
Inputs: arguments (required), idempotency_key.
get_crew_setupDRead-only
get crew setup
Inputs: arguments (required), idempotency_key.
get_design_assessmentDRead-only
get design assessment
Inputs: arguments (required), idempotency_key.
get_development_stateDRead-only
get development state
Inputs: arguments (required), idempotency_key.
get_evidence_viewDRead-only
get evidence view
Inputs: arguments (required), idempotency_key.
get_onboardingCRead-only
Read bounded discovery, exact source manifest, prior answers and the customer-agent contract.
Inputs: arguments (required), idempotency_key.
get_persistent_botDRead-only
get persistent bot
Inputs: arguments (required), idempotency_key.
get_review_teamDRead-only
get review team
Inputs: arguments (required), idempotency_key.
get_team_proposalDRead-only
get team proposal
Inputs: arguments (required), idempotency_key.
get_validation_planDRead-only
get validation plan
Inputs: arguments (required), idempotency_key.
historyDRead-only
history
Inputs: arguments (required), idempotency_key.
identityCRead-only
Read the authenticated identity, without credentials.
Inputs: arguments (required), idempotency_key.
impactDRead-only
impact
Inputs: arguments (required), idempotency_key.
list_artifact_filesDRead-only
list artifact files
Inputs: arguments (required), idempotency_key.
list_bot_issuesDRead-only
list bot issues
Inputs: arguments (required), idempotency_key.
list_bot_memoriesDRead-only
list bot memories
Inputs: arguments (required), idempotency_key.
list_change_reviewsDRead-only
list change reviews
Inputs: arguments (required), idempotency_key.
list_crew_setupsDRead-only
list crew setups
Inputs: arguments (required), idempotency_key.
list_development_statesDRead-only
list development states
Inputs: arguments (required), idempotency_key.
list_onboardingsDRead-only
list onboardings
Inputs: arguments (required), idempotency_key.
list_persistent_memoriesDRead-only
list persistent memories
Inputs: arguments (required), idempotency_key.
list_team_messagesDRead-only
list team messages
Inputs: arguments (required), idempotency_key.
openDRead-only
open
Inputs: arguments (required), idempotency_key.
outcomesDRead-only
outcomes
Inputs: arguments (required), idempotency_key.
product_overviewDRead-only
product overview
Inputs: arguments (required), idempotency_key.
project_detailsDRead-only
project details
Inputs: arguments (required), idempotency_key.
query_evidenceDRead-only
query evidence
Inputs: arguments (required), idempotency_key.
read_artifact_batchDRead-only
read artifact batch
Inputs: arguments (required), idempotency_key.
read_artifact_chunkBRead-only
Read one hash-verified part, at most 32 MiB. Ordinary files have only index 0.
Inputs: arguments (required), idempotency_key.
render_evidence_viewDRead-only
render evidence view
Inputs: arguments (required), idempotency_key.
restore_artifactBRead-only
Return saved bytes or metadata_only manifest. Chunked files require read_artifact_chunk; hashes cover each part and the complete file.
Inputs: arguments (required), idempotency_key.
review_automation_statusDRead-only
review automation status
Inputs: arguments (required), idempotency_key.
review_contextBRead-only
Read a consistent snapshot of the candidate diff, evidence, evaluations, work and review permissions.
Inputs: arguments (required), idempotency_key.
reviewsDRead-only
reviews
Inputs: arguments (required), idempotency_key.
session_detailsDRead-only
session details
Inputs: arguments (required), idempotency_key.
stateDRead-only
state
Inputs: arguments (required), idempotency_key.
studio_contextDRead-only
studio context
Inputs: arguments (required), idempotency_key.
studio_inboxDRead-only
studio inbox
Inputs: arguments (required), idempotency_key.
studio_libraryDRead-only
studio library
Inputs: arguments (required), idempotency_key.
studio_overviewDRead-only
studio overview
Inputs: arguments (required), idempotency_key.
studio_teamDRead-only
studio team
Inputs: arguments (required), idempotency_key.
studio_workDRead-only
studio work
Inputs: arguments (required), idempotency_key.
whyDRead-only
why
Inputs: arguments (required), idempotency_key.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 52 tools
Several tools appear to target the same thing: get_development_state vs. development_state vs. list_development_states, get_design_assessment vs. design, get_bot_context vs. bot_inbox vs. get_persistent_bot, and a dense cluster of review tools (reviews, get_change_review, list_change_reviews, review_context, related_review_context, review_automation_status). Many tools have no description beyond their own name (open, why, design, state, impact, outcomes), so an agent has almost nothing to separate them by. A few areas (artifact reading, evidence) are distinguishable, but the duplication dominates.
The set mixes a verb_noun convention (get_design_assessment, list_bot_issues, read_artifact_chunk) with bare noun tools (history, identity, impact, design, state, events, reviews, open), and the same concept is named both ways in places (get_development_state vs. development_state). Prefix families like studio_*, list_*, and get_* coexist without a clear rule. It is readable but clearly inconsistent.
52 tools is well past the point where each one earns its place, and the set contains near-duplicate pairs that suggest consolidation rather than expansion. With 15+ tools carrying no real description, many entries feel like surface area rather than necessary capability.
Read coverage is broad across design, development state, reviews, evidence, artifacts, bots, teams, and onboarding, but the surface looks read-heavy: there are inbox/listing tools without an obvious send or post counterpart, and no clear create/update operations for designs, teams, or bots. Restore exists for artifacts but other write paths appear absent, which will force workarounds.
Maintenance
Related MCP Connectors
Team memory for AI coding agents and code reviews, reviewed by humans and served over MCP.
Hosted MCP memory and agent control plane for durable conversations, jobs, and operations.
Permission-aware onboarding MCP server: answers about a codebase, filtered by the caller's role.
Read-only Remote MCP for externally grounded AI agent trust receipts.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables AI coding agents and hosts to enforce deterministic repository boundaries via MCP, providing structured reads, supervised edits, snapshots, audits, and recovery with machine-readable evidence.MIT

Nolane Habitatofficial
FlicenseNot gradedqualityBmaintenanceProvides coding agents with a durable, revision-aware project workspace for semantic context, governed source changes, verification, task checkpoints, and observability through an MCP interface.1-- FlicenseNot gradedqualityAmaintenanceEnables MCP clients to read a project's Git-backed kickoff, acceptance criteria, handoff package, progress, and next step, and to append validated, audited progress events as project records. It provides short-lived scoped credentials and fail-closed tool allowlisting for safe, resumable AI-assisted development.-
- AlicenseNot gradedqualityAmaintenanceEnables AI agents to retrieve Git-backed project context, handoff packages, progress, and next steps, and to append validated progress events with matching project-record commits. This supports visible agent progress, resumable work, and safe handoffs while keeping high-risk actions outside the MCP surface.MIT