by Rswcf
Free financial data: company analysis, DCF, comps, benchmarks, screening. No API key.
npm:deepviews-mcp · local package33/wkpublished 1 mo ago
Evaluate model or agent outputs.
Free financial data: company analysis, DCF, comps, benchmarks, screening. No API key.
MCP server exposing SharpeBench's luck-robust quantitative evaluation tools for trading agents, including deflated Sharpe, pass^k, process discipline, and risk analysis.
MCP server wrapping the PROTEUS resume-matching pipeline — deterministic scoring, gap analysis, rewrites, and cover letters
Security evals for the AI era. Probes · Targets · Graders · Proof. Confirmed XSS / SQLi / BOLA / prompt-injection / MCP-RCE with reproducible proof attached to every finding.
Score a public GitHub repo 0-100, or search Legit.Show for launched software by what we measured.
Local-first MCP server for versioning, searching, evaluating, and improving AI prompts.
Burnout risk scoring across 3 dimensions (physical, emotional, effectiveness)
Spec-driven software development with security-guided multi-agent orchestration. Terminal AI coding agent with a Sensei second opinion, a Checker, six Sec-Test security personas, a Business Agent for xlsx/docx/pptx/pdf deliverables, and free-model support
Explain fraud verdicts with evidence, surface account rings, and see who has burned other operators.
SuperBryn MCP server — run the voice-agent eval loop and read your production call logs from Claude Code, Claude Desktop, or Codex.
Deterministic regression testing, release bisection and plugin compatibility matrices for Claude Code
AI lead scoring & enrichment agent for Twenty CRM — auto-scores People and Opportunities 0-100 with reasoning, on create/update and via backfill.
Agent to Trust (A2T) 本地考场 CLI —— 一条命令给你的 agent 打分上榜（Don't trust an Agent. Test it.）
prosemeter MCP server — deterministic prose scoring and the agent revise/converge loop over MCP
doseedo CLI — music & audio for AI agents: 50+ AI instruments play your MIDI, sound effects, stems, audio to MIDI, mixing, DAW sessions and project conversion; every doseedo MCP job by name
A local-first workbench for developing, inspecting, and benchmarking MCP servers against local (LM Studio, Ollama) or remote (OpenRouter) models — Web UI, CLI, and MCP interface over one shared store.
Settle the argument. 37 board and card games including Xiangqi, 203 rulings, illustrations, free places to play, an MCP server and a JSON API.
Catch every time your AI coding agent touches auth, secrets, or skips a test, then turn the correction you made into a local regression eval. Local-first, deterministic, no LLM judge.
Structured fact memory MCP server — SQLite + FTS5, trust scoring, entity graph, bilingual retrieval for Claude Code & Codex
Check classifier confidence against accuracy, fit temperature scaling and save local reports.