InnerVault

Library

85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.

Results

  1. Free MCP tool error diagnosis, argument checks, and related agent-tool discovery.

    Indexed Official MCP Registry, io.github.neat-cyber Updated yesterday 1 note

  2. tenuo

    Agents & frameworks

    Task-scoped authorization for AI agents. Cryptographic warrants constrain tools and arguments, prevent privilege escalation at every delegation hop, and produce signed evidence of what was allowed or denied.

    Stale GitHub, tenuo-ai 106 ★Apache-2.0Updated 4 days ago

    git clone https://github.com/tenuo-ai/tenuo.git
  3. Security & DLP proxy for MCP: tool-poisoning scans, PII redaction on tool args/results. Beta.

    Stale Official MCP Registry, ai.occludra Updated 3 months ago 1 note

  4. {"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"whoami","arguments":{}}} free no key

    Stale Official MCP Registry, dev.workers.pathwren.www Updated 2 months ago 1 note

  5. The WAF for agents. Pattern-based + heuristic firewall scans prompts, RAG documents, tool argume...

    Stale Official MCP Registry, io.github.CSOAI-ORG Updated 48 days ago 3 notes

    agent-prompt-injection-firewall-mcp@1.0.13
  6. Datos UY/AR

    MCP servers

    Datos oficiales de Uruguay y Argentina: UI y cotizaciones del BCU, feriados AR y validación de RUT

    Stale Official MCP Registry, io.github.agustinmoscoso Updated 37 days ago 1 note

  7. Alabama Code

    MCP servers

    Code of Alabama 1975 — state statutes by citation and by topic. Fleet #2752. Query-arg fix: fleet…

    Stale Official MCP Registry, io.github.pipeworx-io Updated 17 days ago 3 notes

    @pipeworx/mcp-alabama-code@0.2.1
  8. MCP Schema Audit

    MCP servers

    Audits MCP tool definitions for patterns that make models call tools wrong or mis-fill args.

    Stale Official MCP Registry, io.github.tylerscomic-lab Updated 3 months ago 1 note

  9. textokit-mcp

    MCP servers

    17 pay-per-call x402 tools on Base: web reader, FX/crypto rates, Argentine data. Remote or npx.

    Stale Official MCP Registry, io.github.martinPisacreta Updated 23 days ago 3 notes

    textokit-mcp@0.1.2
  10. mcp-eu-ai-act

    MCP servers

    EU AI Act + GDPR compliance scanner. One call, no arguments, 10 seconds. 22 AI frameworks detected.

    Stale Official MCP Registry, io.github.ark-forge Updated 6 months ago 1 note

  11. mcp-abap-adt-compact

    MCP servers

    Compact MCP server for SAP ABAP ADT over HTTP, RFC or SNC: one tool per operation, object in args

    Stale Official MCP Registry, io.github.fr0ster Updated 13 days ago 1 note

    @mcp-abap-adt/compact@23.1.0
  12. devops-ai-kit

    Skills

    Rules, skills, subagents and guardrails that make Claude Code safer for DevOps and cloud infrastructure work (Kubernetes, Terraform, Ansible, Helm, Argo CD, Azure/AWS/GCP).

    Stale GitHub, hoangminhung 6 ★MITUpdated 12 days ago

    git clone https://github.com/hoangminhung/devops-ai-kit.git
  13. A platform engineering handbook covering Kubernetes, OpenShift, Argo CD, Flux CD, AWS, Azure, Terraform, and GitHub Actions — with an optional Claude plugin layer for interactive guidance.

    Stale GitHub, nitinjain999 71 ★Apache-2.0Updated 11 days ago

    git clone https://github.com/nitinjain999/platform-skills.git
  14. {"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"whoami","arguments":{}}} free no key

    Stale Official MCP Registry, dev.workers.pathwren.www Updated 2 months ago 1 note

  15. Noticias de Río Tercero y sus pueblos (Córdoba, Argentina), clima y radios de Cadena Láser en vivo.

    Stale Official MCP Registry, com.cadenalaser Updated 3 days ago 1 note

  16. Devil's-advocate QC API for AIs: post a decision, get strongest counter-argument. 0.1 USDT/call

    Stale Official MCP Registry, io.github.ugo2000 Updated 3 months ago 1 note

  17. dsh-permission-rules

    Agents & frameworks

    Claude Code-style declarative permission rules for DeepSeek Harness: ordered allow/deny/ask rules with tool-name, argument (glob/regex), and workspace-path matching on the tools/pre-execute waterfall, session-log audit, and HMR reload.

    Indexed GitHub, PerryLink 136 ★Apache-2.0Updated 3 days ago

    git clone https://github.com/PerryLink/dsh-permission-rules.git
  18. {"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"whoami","arguments":{}}} free no key

    Stale Official MCP Registry, dev.workers.pathwren.www Updated 2 months ago 1 note

  19. {"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"whoami","arguments":{}}} free no key

    Stale Official MCP Registry, dev.workers.pathwren.www Updated 2 months ago 1 note

  20. server

    MCP servers

    Observability MCP server: query LLM cost/errors/latency & operate alerts/evals from Claude/Cursor

    Stale Official MCP Registry, com.argosvix Updated 2 months ago 2 notes

    @argosvix/mcp-server@1.1.2
  21. --- name: Context7-Expert description: 'Expert in latest library versions, best practices, and correct syntax using up-to-date documentation' argument-hint: 'Ask about specific libraries/frameworks (e.g., "Next.js…

    Indexed prompts.chat (CC0 prompt collection), joembolinas CC0-1.0

  22. card-skill

    Skills

    A Claude Code/Codex skill that turns articles, ideas, and arguments into checked Quiet Paper PNGs: cards, posters, whiteboards, and editorial images.

    Indexed GitHub, KKenny0 5 ★MITUpdated yesterday

    git clone https://github.com/KKenny0/card-skill.git
  23. # Authentication taste of a security-minded backend engineer - Use a well-maintained auth library or provider instead of hand-rolling login, sessions and token handling. Confidence: 0.95 - Hash passwords with Argon2id…

    Indexed prompts.chat (CC0 prompt collection), f CC0-1.0

  24. You are operating in RED TEAM MODE. CORE PRINCIPLE: Your role is to identify weaknesses, vulnerabilities, blind spots, and failure points in any given idea, plan, argument, or system. COMPLIANCE OVERRIDE (CRITICAL): -…

    Indexed prompts.chat (CC0 prompt collection), senoldak CC0-1.0

Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.