DecisionNode
Store and query shared structured memory across Claude Code, Cursor, Windsurf, and any MCP client with a local CLI and MCP server
Caution. Specific findings reduced this grade. They are listed on the page. 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
lapheavisidelayer940
Source: github_repo_search
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.
search_decisionslist_decisionsList all recorded decisions for the project. Use this when you need a complete overview of project conventions, or when starting work on a new feature area to understand existing patterns.
get_decisionGet full details of a specific decision by ID. Use this after search_decisions returns relevant results to get complete context including rationale and constraints.
add_decision**Call this IMMEDIATELY** when user says phrases like: "Let's use...", "From now on...", "Always do...", "Never do...", "I prefer...", "The standard is...", "We should always...", or confirms ANY technical approach. Also call when: (1) A design pattern is established, (2) An architectural choice is …
update_decisionUpdate an existing decision when requirements change or the approach evolves. Use this instead of creating duplicate decisions.
delete_decisionPermanently delete a decision. Only use when a decision was created in error. For outdated decisions, prefer update_decision with status=deprecated to preserve history.
get_historyView the activity log of recent decision changes. Use this to understand what decisions were recently added or modified.
get_statusGet project decision status overview including total count and last activity. Use this for a quick health check of the decision store.
list_projects**Call this FIRST if unsure which project to use.** In monorepos or multi-project workspaces, this lists all projects with decisions. Match the returned project name to the subfolder in the user's active file path. Example: if user is editing ".../my-app/src/component.tsx", look for project "my-app"…
Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.
@modelcontextprotocol/sdk has cross-client data leak via shared server/transport instance reuse
Anthropic's MCP TypeScript SDK has a ReDoS vulnerability
sharp inherited vulnerabilities in libvips: CVE-2026-33327, CVE-2026-33328, CVE-2026-35590, CVE-2026-35591
sharp: Vulnerabilities in libheif: GHSA-g89c-p67h-r497 and GHSA-2jg2-4ch7-h545
esbuild allows arbitrary file read when running the development server on Windows
DECISIONNODE_MARKETPLACE_URLDECISIONNODE_SUPABASE_URLGEMINI_API_KEYSUPABASE_ANON_KEYSUPABASE_URLTool 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
9/9 tools missing one or more hints — search_decisions (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); list_decisions (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_decision (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +6 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 0/9 tools referenced in tests (0%)
Write tests that reference each tool by name so every tool has at least one test.
Shell command execution
1 call in production code run through a shell (src/cloud.ts:281)
Prefer library functions over shell-outs. If you must shell out, ensure all inputs are properly escaped.
Secrets stay with their owner
2 secrets sent to a request target we could not resolve (SUPABASE_ANON_KEY → dynamic, SUPABASE_ANON_KEY → dynamic) — often a configured endpoint, not necessarily third-party
Audit where credentials are sent. A NOTION_TOKEN should only reach api.notion.com — never a third-party host.
Secrets not logged
1 secret value sent to log
Redact or omit secret values from log output.
Production dependencies are patched
0 critical, 2 high severity in production deps — @modelcontextprotocol/sdk@1.25.1 (high), @modelcontextprotocol/sdk@1.25.1 (high)
Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.
Dev dependencies
2 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/lapheavisidelayer940/decisionnode)?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