lockstep-mcp (Tmmoore286/lockstep-mcp) is an MCP server listed on the M8ven Trust Index. It scores 55 out of 100, grade D. It declares 43 tools. No publisher has claimed this listing.
Enables multiple AI agents like Claude and Codex to coordinate on the same project through shared tasks, file locks, and a real-time dashboard, preventing conflicts and streamlining collaborative development.
Warning. Serious findings were identified. Review the full report before connecting. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.
How we verified
Verified is a snapshot. Live keeps it current, and builds your track record.
⚡ Connect GitHub → continuous verification on every pushwhy connect →Who stands behind it
Tmmoore286
Source: Glama
Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →
Install from
The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.
These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.
status_getGet coordinator config and state summary
task_createCreate a task. Complexity determines review requirements: simple=no review, medium=verify on completion, complex/critical=planner approval required. Isolation determines whether implementer works in shared directory or isolated git worktree.
task_claimClaim a task and set status to in_progress
task_updateUpdate a task
task_submit_for_reviewSubmit a completed task for planner review (required for complex/critical tasks, recommended for medium)
task_approvePLANNER ONLY: Approve a task that is in review status, marking it done
task_request_changesPLANNER ONLY: Request changes on a task in review, sending it back to in_progress
task_approve_batchPLANNER ONLY: Approve multiple tasks at once. More efficient than approving one by one.
task_summaryGet task counts by status. Lighter than task_list - use when you just need to know how many tasks are in each state.
task_listList tasks with optional filters. For active work, defaults to excluding done tasks to reduce response size. Use includeDone=true or status='done' to see completed tasks.
lock_acquireAcquire a named lock
lock_releaseRelease a lock
lock_listList locks with optional filters
note_appendAppend a note
note_listList recent notes
artifact_readRead an artifact file
artifact_writeWrite an artifact file
file_readRead a file
file_writeWrite a file
command_runRun a shell command
tool_installInstall a tool using a package manager
log_appendAppend a log entry
coordination_initInitialize coordination session. Call this first to set up your role (planner or implementer). Returns guidance based on your role and current project state.
project_context_setStore project context (description, goals, tech stack, acceptance criteria, tests, implementation plan). Called by planner to define what the project is about.
project_context_getGet stored project context. Returns the project description, goals, and other context set by the planner.
project_status_setSet the project status. Use 'stopped' to signal all implementers to stop working.
launch_implementerLaunch a new implementer agent (Claude or Codex) in a new terminal window. The planner uses this to spawn workers. Set isolation='worktree' to give the implementer its own git worktree for isolated changes.
implementer_listList all registered implementers and their status.
implementer_resetReset all implementers to 'stopped' status. Use this when starting a fresh session or when implementers are stale/not actually running.
session_resetPLANNER ONLY: Reset the coordination session for a fresh start. Clears all tasks, locks, notes, and archives discussions. Use this when starting a new project or when data from previous sessions is cluttering the dashboard.
dashboard_openOpen the lockstep dashboard in a browser. Call this to monitor progress visually.
discussion_startStart a new discussion thread. Use this when you need input from other agents or want to discuss an architectural/implementation decision.
discussion_replyReply to an existing discussion thread.
discussion_resolveResolve a discussion with a final decision. Creates an auditable record of the decision.
discussion_getGet a discussion thread with all its messages.
discussion_listList discussions. Use this to check for discussions waiting on you.
discussion_inboxCheck for discussions waiting on you. Call this between tasks to see if anyone needs your input.
discussion_archiveArchive a resolved discussion. Archived discussions can be deleted later.
discussion_cleanupArchive old resolved discussions and optionally delete old archived ones. Use for maintenance.
worktree_statusGet the status of a worktree including commits ahead/behind main, modified files, and untracked files. Use this to check an implementer's progress before merging.
worktree_mergeMerge an implementer's worktree changes back to main. This should be called after a task is approved. If there are conflicts, returns conflict information for manual resolution.
worktree_listList all active lockstep worktrees in the project.
worktree_cleanupClean up orphaned worktrees that no longer have active implementers. Call this during maintenance.
Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.
When Vitest UI server is listening, arbitrary file can be read and executed
@modelcontextprotocol/sdk has cross-client data leak via shared server/transport instance reuse
ws: Memory exhaustion DoS from tiny fragments and data chunks
ws: Uninitialized memory disclosure
COORD_COMMAND_ALLOWCOORD_COMMAND_MODECOORD_DATA_DIRCOORD_DB_PATHCOORD_LOG_DIRCOORD_MODECOORD_ROOTSCOORD_SERVER_NAMECOORD_SERVER_VERSIONCOORD_STORAGETool annotations
No tools have read-only/destructive annotations
Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.
All four hints declared on every tool
43/43 tools missing one or more hints — status_get (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); task_create (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); task_claim (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +40 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.
For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.
Tool test coverage
Only 10/43 tools referenced in tests (23%)
Write tests that reference each tool by name so every tool has at least one test.
Shell command execution
40 calls in production code run through a shell (src/server.ts:97, src/dashboard.ts:37, src/worktree.ts:39)
Prefer library functions over shell-outs. If you must shell out, ensure all inputs are properly escaped.
Readable source code
1 file are minified or bundled, which is usually build output rather than concealment
Ship unminified, readable source.
Production dependencies are patched
0 critical, 2 high severity in production deps — @modelcontextprotocol/sdk@1.25.2 (high), ws@8.19.0 (high)
Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.
Dev dependencies
1 critical/high in dev-only deps (does not ship to users)
Upgrade dev dependencies when convenient.
Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.
[](https://m8ven.ai/mcp/tmmoore286/lockstep-mcp)?variant=verified from the URL.Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.
https://m8ven.ai/api/mcp/tool-check