vercel-mcp-server-for-zed
Provides an MCP server for the Zed editor that connects the editor’s AI assistant to AWS services (e.g., S3, DynamoDB, Lambda) using user-supplied AWS credentials and region.
Score Breakdown
⚙ Agent Friendliness
🔒 Security
Security assessment is limited to README facts. The extension requires user-supplied AWS Access Key ID and Secret Access Key, which increases risk if secrets are mishandled. The README does not describe least-privilege scoping, assumed roles, short-lived credentials, encryption in transit, or how secrets are stored/logged. Agents should avoid extracting or displaying credentials.
⚡ Reliability
Best When
You can configure least-privilege IAM credentials and want Zed’s AI to access AWS-backed context from within the editor via MCP.
Avoid When
You cannot restrict AWS permissions (broad credentials like admin), or you need clear guidance on data handling, error handling, and tool-level security guarantees.
Use Cases
- • Retrieve context from S3 for chat/analysis in Zed
- • Query DynamoDB tables for up-to-date information
- • Invoke Lambda functions to generate context or compute results
- • Build Zed AI workflows that combine AWS data/actions with editor context
Not For
- • Organizations that cannot allow client-provided long-term AWS credentials
- • Use cases requiring strongly scoped, audited access without custom IAM hardening
- • Teams needing documented, stable MCP tool contracts and detailed error/retry semantics
Interface
Authentication
Authentication appears to rely on long-lived AWS credentials entered into Zed settings. The README does not describe any additional auth flow (e.g., role assumption) or scope restrictions beyond what IAM permissions the keys grant.
Pricing
README does not describe pricing for the MCP server itself; AWS usage would incur AWS costs depending on the operations performed.
Agent Metadata
Known Gotchas
- ⚠ Credentials are configured via settings; agents should not be instructed to ask users for or print secrets.
- ⚠ No documented guidance on rate limits, retries, pagination, or idempotency for AWS actions is present in the provided README content.
- ⚠ AWS operations (e.g., writes/invocations) may have side effects; without tool-level semantics, agents must be cautious.
Alternatives
Full Evaluation Report
Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for vercel-mcp-server-for-zed.
AI-powered analysis · PDF + markdown · Delivered within 30 minutes
Package Brief
Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.
Delivered within 10 minutes
Score Monitoring
Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.
Continuous monitoring
Scores are editorial opinions as of 2026-04-04.