The real catalog of tools for AI agents

Local, cross-provider preflight checks for LLM integration changes.

Preflight MCP OAuth compatibility with structured evidence and remediation guidance.

Jailbreak-proof AI guardrails. Automated Reasoning SMT solver, not an LLM. ZK proofs included.

Checks every LaTeX reference against Crossref, dblp, arXiv, DataCite, PubMed and OpenAlex. No LLM.

LLM provider intelligence: recommendations, pricing, and status

Scans an MCP server for security gaps before your agent connects. Free tier, no signup.

Deterministic MCP, JSON Schema, and SemVer preflight via Agothe's public MUV scope.

GPU-accelerated MCP server for neural network training, deep learning, and model experimentation

PreClick scans links for threats and confirms intent match with high accuracy before agents click.

Check if your MCP server is ready to publish on the MCP Registry, Smithery, or npm.

Check public MCP reachability, protocol handshake, auth and tool schemas before connecting.

Static MCP, source-code and injection-indicator checks with redacted signed receipts.

PreClick scans links for threats and confirms intent match with high accuracy before agents click.

Claim-level provenance preflight for sanitized nonfiction passages; automated triage only.

35-probe LLM/agent security red-team scan (injection, jailbreak, MCP abuse) with report.

Evidence-backed UBL, PDF, and image invoice checks before approval or payment.

Checks TypeORM migrations for data loss, table locks, and deploy problems before they run.

LLM and GPU rental prices: model price lookup, GPU listings, cheapest-GPU search, price history

Semantic context compression and cognitive memory layer for LLM swarms.

Budgeted agent preflight: allow|block|reuse|defer|advise. Never executes destination tools. Free MCP