CLI MCP server
Cross-tool decision memory for AI coding agents: search your decision graph, check changes over MCP.
A94/100grade A
Adoption
Growing
1 stars748 downloads/wk
Reviews
Write oneNobody has reviewed CLI yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
CLI tools
No tool declarations could be read from the package source. They show once the server is installed.
Public scan report
scanner v0.1.8 · 2026-09-19 · same rubric, same numbers if you re-run it
no findings
- Code scan267 source files scanned25/25
- –Live reliabilityno gateway calls yet and no remote to proben/a
- –Tool poisoningtools not inspected (local package is not executed); not countedn/a
- Auth qualitylocal package, no credentials required12/15
- Maintenancelast push 1 days ago15/15
- Maintainer identityregistry namespace matches repository owner; GitHub account older than a year9/10
Overall 94/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON
Grade history
- 2026-09-19restoreB → Ascore 94
Install directly
Runs npx -y @aligndottech/cli on your machine. Read the scan report first; the gateway never runs local packages.
claude mcp add cli -- npx -y @aligndottech/cli
CLI: common questions
- Is CLI MCP server safe?
- Yes, by our scan: it is graded A (94/100). Read the CLI safety report
- How do I install CLI?
- It runs on your machine. Copy the Claude Code, Claude Desktop or Cursor config from the install section.
- Does CLI need an API key?
- Not as far as the registry entry and our scan can tell: no credentials are declared or required.
- Is CLI maintained?
- The last commit was in the last day (2026-09-18). The latest release is v0.40.1.
- What can I use instead of CLI?
- Servers from other publishers that do the same job: Misakanet MCP server, Link MCP server and Reverie MCP server. Compare all CLI alternatives.
Alternatives to CLI
Same job from other publishers: the closest match first, then the best rated.
- MisakanetFailure-memory layer for coding agents: search evidence-rated failure lessons by error text.not reviewedEstablishedA
- LinkLocal personal memory for agents as MCP tools — remember, recall, search, context, graph traversal.not reviewedEstablishedA
- ReverieGraph memory that dreams: Neo4j knowledge-graph memory for AI agents with hybrid searchnot reviewedEstablishedB
- OctobrainPersistent memory for AI assistants with semantic search and knowledge graph relationships.not reviewedGrowingA
- JunêShared, cited knowledge-graph memory for agents — ask, search, remember, keep standing instructionsnot reviewedGrowingB