Axiom Agentic Tools

Audit an x402-gated endpoint by probing its 402 envelope, agent-card.json, well-known surfaces, and response headers. Returns a closed-vocabulary verdict plus 3-7 scored recommendations across pricing, bundling, discoverability, envelope correctness, rate limiting, tier expansion, facilitator choice, and schema clarity. Each recommendation cites the observed current-state value as evidence.

Design a non-security token strategy for an autonomous agent. Returns a deployable spec: symbol, supply, distribution allocations summing to 100, OpenZeppelin contract templates (ERC20, ERC4626, ERC721), fair-launch defaults, a six-criterion non-security checklist, an estimated Base deploy cost, and a curated risks list covering Sybil, LP rug, and key-compromise vectors.

Returns a ranked, deadline-aware list of open Base ecosystem funding programs (grants, accelerators, hackathons, retro-funding). Each result cites source_url, deadline, funding_range_usd, and last_verified_at. Stale entries are flagged. Designed for agents and builders shipping on Base who need a single call to surface the next applicable funding deadline.

Scans an MCP server manifest or endpoint for security vulnerabilities — prompt injection in tool descriptions, exfiltration vectors, unbounded resource access, privilege escalation, schema mismatches, transport security issues, and over-permissive scopes. Returns a structured risk report with severity levels and remediation guidance.

Compose a directed acyclic graph of public x402, MCP, and A2A tools that achieves a stated agent goal. Returns step-by-step plan with tool slug, endpoint URL, protocol, inputs, dependencies, per-step cost and latency, total estimated cost, and an executable plan in either a2a-json-rpc or shell-curl form. Useful for autonomous agents that need to pick which paid tools to chain.

Comprehensive GitHub repository health audit. Scores repos 0-100 across 8 categories: activity, community, maintenance, contributors, security (via OpenSSF Scorecard), CI/CD, documentation, and popularity. Returns letter grade, per-category scores, 20+ individual checks with evidence, and prioritized recommendations sorted by impact. All checks run via GitHub API — no clone required. Free: 50 calls/IP/day.