About this integration
Scores your prompts against your real codebase — context-aware prompt intelligence
- Transport
- stdio
- Authentication
- api-key
- Initial setup
- credentials
- Runtime
- unattended
- Evidence
- documented
- Version
- 0.1.1
- Package
- prompyai-mcp
- Last compatibility test
- Not independently tested
Connect your agent
prompyai-mcpDirect AI rewriting can send context to Anthropic when ANTHROPIC_API_KEY is set; a documented no-key mode returns context for the host model to rewrite. Anonymous telemetry is enabled unless disabled according to the captured README. Documentation reviewed only; no codebase or service was accessed.
Capabilities: Score prompts against a local codebase, Index file paths, symbols, project structure, and session context, Suggest and generate codebase-grounded prompt rewrites
Connected profiles
Additional details
io.github.samouh-waleed/prompyai
Source ↗ · Checked 2026-09-170.1.1
Source ↗ · Checked 2026-09-17CC0-1.0; package licenses are separate
Source ↗ · Checked 2026-09-17npm
Source ↗ · Checked 2026-09-17prompyai-mcp
Source ↗ · Checked 2026-09-250.1.4
Source ↗ · Checked 2026-09-25The npm executable runs an MCP server that indexes the local workspace and can optionally call Anthropic for prompt rewriting.
Source ↗ · Checked 2026-09-19ANTHROPIC_API_KEY enables direct Haiku rewrites; the publisher also documents a subscription-host mode with no API key. Classified api-key because direct credentialed capability is included.
Source ↗ · Checked 2026-09-19Claude CLI launches npx prompyai-mcp serve through its MCP registration command.
Source ↗ · Checked 2026-09-19Publisher documentation reviewed; package and integration endpoint not executed or independently security-audited.
Source ↗ · Checked 2026-09-19