Discover and fetch REPS agent-evaluation baseline material—scenario banks, drivers, checks, and eval configs—for assessing AI agents across reasoning, execution, performance, and security.
Apache 2.0
453,349 tools. Updated 2026-08-13 18:57
"Assessing security risks of inputting sensitive material into a hosted MCP server" matching MCP tools:
- Analyze a Git repository for 14 security vulnerability classes, including prompt injection and secret exposure, before running it as an MCP server.MIT
- Get an overview of Agni Folio, its MCP server capabilities, and instructions for connecting AI to your portfolio via the hosted OAuth server.MIT
- Identify and analyze security risks in blockchain transactions by retrieving endpoints for token security, NFT verification, phishing detection, and smart contract vulnerabilities.MIT
- Grade an MCP server's agent-readiness and security. Accepts npm package, GitHub repo, local directory, or hosted URL. Returns a 0-100 score, letter grade, and actionable fixes.MIT
- Restores MCP server configurations from a lockfile by reinstalling each server into the target client. Environment variables are not stored and must be set manually.MIT
Matching MCP Servers
- Flicense-qualityBmaintenanceThis MCP server provides secure access to databases for AI agents, enforcing authentication, authorization, human approval, logging, and notifications to prevent dangerous actions.
- AlicenseAqualityBmaintenanceAI-powered sensitive info detection and masking MCP server supporting 14+ types with regex, checksum, and optional LLM semantic detection, enabling flexible masking strategies like mask, replace, hash, and redact.6MIT
Matching MCP Connectors
Static MCP manifest and tool-policy security preflight with signed input-redacted receipts
Security Feeds MCP.
- Return the current Dali server version and changelog to verify MCP server connectivity and debug version mismatches between the pip package and hosted API.MIT
- Fetches the MCP server descriptor to get the Streamable HTTP endpoint, capabilities, pricing, and integration metadata.MIT
- Build a self-hosted MCP server package for an AIMarket capability. Assembles Docker image, MCP manifest, pricing tiers, and connection string.MIT
- Batch-scan MCP server names against a security registry, returning per-server risk verdicts: match status, category, CVEs, credentials, and high/medium/low/unvetted.Apache 2.0
- Check the current configuration and health of the Mercado Bitcoin MCP server. View operation mode, security limits, authentication status, and daily spending.MIT
- Scan SKILL.md packages and agent tool definitions for security vulnerabilities including tool poisoning, command injection, data exfiltration, and prompt injection. Maps findings to OWASP Agentic and MCP Top 10.Apache 2.0
- Deposit funds into a V2 escrow using a local signer. Hosted users must use the escrow build deposit transaction tool.MIT
- Scan an MCP server for security vulnerabilities, description quality, and architecture issues. Get a security rating from F to A+ with actionable recommendations for safe deployment.MIT
- Verify MCP server authentication to Odoo and access to PPM models, returning counts of portfolios, programs, projects, and risks.LGPL 3.0
- Assess your MCP server deployment against OWASP MCP Top 10 security risks. Describe your setup to receive vulnerability analysis and compliance guidance.MIT
- Check the security of an MCP server before installing. Get a trust score, risk level, and findings from 265+ automated probes.
- Retrieve the current release of the Xcode MCP Server.MIT
- Look up security metadata for MCP servers from the threat registry. Get risk level, verification status, known tools, and credential requirements by searching server or package name.Apache 2.0
- Discover available hosted MCP servers for GitHub, Stripe, Slack, OpenAI, Notion, and other REST APIs. View all 18 free servers to connect with your own API keys.AGPL 3.0