lake-gate
NPM · LAKE-GATE
Plan review for coding agents: request review, wait for a version-bound approval, revise.
Available components
Last scanned (14 hours ago)
Scores higher than 41% of npm servers
Category Project Management
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security100
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- No install/post-install scripts declared.Pass
- No production dependencies, so there is no dependency health to assess. View diagnostics → Pass
Provenance & Transparency45
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 2 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability62
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 758 tokens (~189/item across 4 items; 4 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management17
- Stability observed for 5 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage97
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 92% of tool parameters carry a description.Partial
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 4 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 5 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Checks we ran (16)
- Malware scan
- Known CVEs
- Install scripts
- Dependency health
- Source repository
- Provenance
- License
- Maintenance
- Security disclosure
- Schema quality
- Stability
- Tool coverage
- Injection markers
- Destructive annotations
- Judged manipulation
- MCP protocol
Does not apply to this package (2)
- Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
- Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
The score does not measure everything. What the score does not measure →
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 20 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.
- 19 Nov 26 +15
- Malware scan: unverified → pass ▲ security
- 18 Nov 26 −14
- Malware scan: pass → unverified ▼ security
- Package version: 0.2.4 → 0.2.5 functional
- 17 Nov 26 +11
- Known CVEs: unverified → pass ▲ security
- Dependency health: unverified → pass ▲ functional
- 16 Nov 26 57
First indexed and scored.
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 21 Nov 2026 · Analysed npm/lake-gate@0.2.5
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | npm |
Background: How many MCP packages publish verified provenance →
Dependencies 0 packages
| Packages resolved | 0 |
|---|---|
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
lake_request_review ~170
Save a plan (markdown) as a versioned lake-gate plan and ask teammates to review it on the PR. Returns the plan id, version, model and cost estimate, and the review link. Use after planning, before implementing. Tip: add a "Model: <name>" line to declare which model runs it.
| Name | Type | Req | Description |
|---|---|---|---|
| note | string | – | Short note to reviewers |
| plan_id | string | – | Plan id (defaults to the active plan, or derived from the title) |
| plan_markdown | string | – | Full plan in markdown. Omit to request review of an existing plan. |
| push | boolean | – | Commit only the plan file and push the current branch (so the PR shows this version) |
| reviewers | array | – | GitHub logins to request review from |
No output schema declared.
No examples provided.
lake_review ~204
As a reviewer, act on a plan PR: approve, request_changes, comment (optionally on lines), reply (in a thread) or suggest (a structured change the author accepts in one click: suggestion_id or model). approve and request_changes post as the human GitHub account on this machine: ONLY use them when the user explicitly said so in this conversation, and pass the exact version they saw.
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | yes | – |
| end_line | number | – | – |
| line | number | – | First plan line to anchor a comment |
| model | string | – | Propose running the plan on this model |
| plan_id | string | – | Plan id |
| suggestion_id | string | – | Lake suggestion id to propose |
| text | string | – | Comment, reply, or verdict note (required for request_changes) |
| thread_id | string | – | Thread to reply in |
| version | string | – | 8-character version (approve / request_changes) |
No output schema declared.
No examples provided.
lake_review_status ~123
Review state of a plan: status, verdicts with notes, open comment threads anchored to plan lines, reviewer suggestions, budget approval, and the model/cost view with Lake's cost-cutting suggestion ids. Works locally before a PR exists. Set wait_seconds to wait for a decision or new feedback. Also syncs approvals so the lake-gate hook opens once approved.
| Name | Type | Req | Description |
|---|---|---|---|
| plan_id | string | – | Plan id (defaults to the active plan) |
| wait_seconds | number | – | Wait up to this long for a change (polls every 20s) |
No output schema declared.
No examples provided.
lake_submit_revision ~224
As the author, save a new plan version (earlier approvals no longer apply) and tell reviewers. Either pass the full revised plan_markdown, or apply a suggestion in one step: thread_id (a reviewer suggestion), suggestion_id (from lake_review_status) or model (run the whole plan on that model). Can also reply to threads and mark them resolved.
| Name | Type | Req | Description |
|---|---|---|---|
| addressed_threads | array | – | Thread ids this revision addresses (marked resolved) |
| model | string | – | Run the whole plan on this model, e.g. sonnet |
| note | string | – | What changed, for reviewers |
| plan_id | string | – | Plan id (defaults to the active plan) |
| plan_markdown | string | – | Full revised plan in markdown |
| push | boolean | – | Commit only the plan file and push (default on when applying a suggestion) |
| suggestion_id | string | – | Apply this Lake suggestion, e.g. models-2-4, cap-12, drop-5 |
| thread_id | string | – | Accept this reviewer suggestion thread |
No output schema declared.
No examples provided.
How do I install the lake-gate MCP server?
lake-gate runs locally as an npm package, launched with npx -y lake-gate mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · lake-gate
claude mcp add getlake-lake-gate -- npx -y lake-gate mcp
What is the lake-gate MCP server?
lake-gate is an MCP server listed in the public MCP registry as io.github.getlake/lake-gate. Plan review for coding agents: request review, wait for a version-bound approval, revise. This page covers its npm package (lake-gate).
Is the lake-gate MCP server safe to use?
lake-gate scores 70 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 November 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the lake-gate MCP server expose?
lake-gate exposes 4 tools: lake_request_review, lake_review_status, lake_submit_revision, lake_review. Their descriptions and schemas cost roughly 721 tokens of context every time the server is loaded.
Is the lake-gate MCP server still maintained?
lake-gate is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the lake-gate MCP server under?
lake-gate declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.
What did VerifyMCP test on the lake-gate MCP server?
VerifyMCP ran 16 checks on lake-gate, covering Malware scan, Known CVEs, Install scripts, Dependency health and 12 more. Endpoint Security and Transport & Reachability do not apply to an npm package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.